public interface ModelBuilders
| Modifier and Type | Interface and Description |
|---|---|
static class |
ModelBuilders.Helper |
| Modifier and Type | Method and Description |
|---|---|
retrofit2.Call<ModelIdV3> |
calcModelId(java.lang.String algo) |
retrofit2.Call<ModelIdV3> |
calcModelId(java.lang.String algo,
java.lang.String _exclude_fields)
Return a new unique model_id for the specified algorithm.
|
retrofit2.Call<ModelBuildersV3> |
fetch(java.lang.String algo) |
retrofit2.Call<ModelBuildersV3> |
fetch(java.lang.String algo,
java.lang.String _exclude_fields)
Return the Model Builder metadata for the specified algorithm.
|
retrofit2.Call<ModelBuildersV3> |
list() |
retrofit2.Call<ModelBuildersV3> |
list(java.lang.String algo,
java.lang.String _exclude_fields)
Return the Model Builder metadata for all available algorithms.
|
retrofit2.Call<AggregatorV99> |
trainAggregator() |
retrofit2.Call<AggregatorV99> |
trainAggregator(DataInfoTransformType transform,
PCAMethod pca_method,
int k,
int max_iterations,
int target_num_exemplars,
double rel_tol_num_exemplars,
long seed,
boolean use_all_factor_levels,
boolean save_mapping_frame,
int num_iteration_without_new_exemplar,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a Aggregator model.
|
retrofit2.Call<CoxPHV3> |
trainCoxph() |
retrofit2.Call<CoxPHV3> |
trainCoxph(java.lang.String start_column,
java.lang.String stop_column,
java.lang.String[] stratify_by,
CoxPHTies ties,
double init,
double lre_min,
int max_iterations,
java.lang.String[] interactions_only,
java.lang.String[] interactions,
StringPairV3[] interaction_pairs,
boolean use_all_factor_levels,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a CoxPH model.
|
retrofit2.Call<DeepLearningV3> |
trainDeeplearning() |
retrofit2.Call<DeepLearningV3> |
trainDeeplearning(boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
DeepLearningActivation activation,
int[] hidden,
double epochs,
long train_samples_per_iteration,
double target_ratio_comm_to_comp,
long seed,
boolean adaptive_rate,
double rho,
double epsilon,
double rate,
double rate_annealing,
double rate_decay,
double momentum_start,
double momentum_ramp,
double momentum_stable,
boolean nesterov_accelerated_gradient,
double input_dropout_ratio,
double[] hidden_dropout_ratios,
double l1,
double l2,
float max_w2,
DeepLearningInitialWeightDistribution initial_weight_distribution,
double initial_weight_scale,
java.lang.String[] initial_weights,
java.lang.String[] initial_biases,
DeepLearningLoss loss,
double score_interval,
long score_training_samples,
long score_validation_samples,
double score_duty_cycle,
double classification_stop,
double regression_stop,
boolean quiet_mode,
DeepLearningClassSamplingMethod score_validation_sampling,
boolean overwrite_with_best_model,
boolean autoencoder,
boolean use_all_factor_levels,
boolean standardize,
boolean diagnostics,
boolean variable_importances,
boolean fast_mode,
boolean force_load_balance,
boolean replicate_training_data,
boolean single_node_mode,
boolean shuffle_training_data,
DeepLearningMissingValuesHandling missing_values_handling,
boolean sparse,
boolean col_major,
double average_activation,
double sparsity_beta,
int max_categorical_features,
boolean reproducible,
boolean export_weights_and_biases,
int mini_batch_size,
boolean elastic_averaging,
double elastic_averaging_moving_rate,
double elastic_averaging_regularization,
java.lang.String pretrained_autoencoder,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a DeepLearning model.
|
retrofit2.Call<DeepWaterV3> |
trainDeepwater() |
retrofit2.Call<DeepWaterV3> |
trainDeepwater(DeepWaterParametersProblemType problem_type,
DeepWaterParametersActivation activation,
int[] hidden,
double input_dropout_ratio,
double[] hidden_dropout_ratios,
int max_confusion_matrix_size,
boolean sparse,
int max_hit_ratio_k,
double epochs,
long train_samples_per_iteration,
double target_ratio_comm_to_comp,
long seed,
double learning_rate,
double learning_rate_annealing,
double momentum_start,
double momentum_ramp,
double momentum_stable,
double score_interval,
long score_training_samples,
long score_validation_samples,
double score_duty_cycle,
double classification_stop,
double regression_stop,
boolean quiet_mode,
boolean overwrite_with_best_model,
boolean autoencoder,
boolean diagnostics,
boolean variable_importances,
boolean replicate_training_data,
boolean single_node_mode,
boolean shuffle_training_data,
int mini_batch_size,
double clip_gradient,
DeepWaterParametersNetwork network,
DeepWaterParametersBackend backend,
int[] image_shape,
int channels,
boolean gpu,
int[] device_id,
boolean cache_data,
java.lang.String network_definition_file,
java.lang.String network_parameters_file,
java.lang.String mean_image_file,
java.lang.String export_native_parameters_prefix,
boolean standardize,
boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a DeepWater model.
|
retrofit2.Call<DRFV3> |
trainDrf() |
retrofit2.Call<DRFV3> |
trainDrf(int mtries,
boolean binomial_double_trees,
double sample_rate,
boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
int ntrees,
int max_depth,
double min_rows,
int nbins,
int nbins_top_level,
int nbins_cats,
double r2_stopping,
long seed,
boolean build_tree_one_node,
double[] sample_rate_per_class,
double col_sample_rate_per_tree,
double col_sample_rate_change_per_level,
int score_tree_interval,
double min_split_improvement,
TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type,
boolean calibrate_model,
java.lang.String calibration_frame,
boolean check_constant_response,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a DRF model.
|
retrofit2.Call<GBMV3> |
trainGbm() |
retrofit2.Call<GBMV3> |
trainGbm(double learn_rate,
double learn_rate_annealing,
double sample_rate,
double col_sample_rate,
KeyValueV3[] monotone_constraints,
double max_abs_leafnode_pred,
double pred_noise_bandwidth,
boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
int ntrees,
int max_depth,
double min_rows,
int nbins,
int nbins_top_level,
int nbins_cats,
double r2_stopping,
long seed,
boolean build_tree_one_node,
double[] sample_rate_per_class,
double col_sample_rate_per_tree,
double col_sample_rate_change_per_level,
int score_tree_interval,
double min_split_improvement,
TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type,
boolean calibrate_model,
java.lang.String calibration_frame,
boolean check_constant_response,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a GBM model.
|
retrofit2.Call<GenericV3> |
trainGeneric() |
retrofit2.Call<GenericV3> |
trainGeneric(java.lang.String path,
java.lang.String model_key,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a Generic model.
|
retrofit2.Call<GLMV3> |
trainGlm() |
retrofit2.Call<GLMV3> |
trainGlm(long seed,
GLMFamily family,
GLMFamily[] rand_family,
double tweedie_variance_power,
double tweedie_link_power,
double theta,
GLMSolver solver,
double[] alpha,
double[] lambda,
boolean lambda_search,
boolean early_stopping,
int nlambdas,
boolean standardize,
GLMMissingValuesHandling missing_values_handling,
java.lang.String plug_values,
boolean non_negative,
int max_iterations,
double beta_epsilon,
double objective_epsilon,
double gradient_epsilon,
double obj_reg,
GLMLink link,
GLMLink[] rand_link,
double[] startval,
int[] random_columns,
boolean calc_like,
boolean intercept,
boolean HGLM,
double prior,
double lambda_min_ratio,
java.lang.String beta_constraints,
int max_active_predictors,
java.lang.String[] interactions,
StringPairV3[] interaction_pairs,
boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
boolean compute_p_values,
boolean remove_collinear_columns,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a GLM model.
|
retrofit2.Call<GLRMV3> |
trainGlrm(DataInfoTransformType transform,
int k,
GenmodelalgosglrmGlrmLoss loss,
GenmodelalgosglrmGlrmLoss multi_loss,
GenmodelalgosglrmGlrmLoss[] loss_by_col,
int[] loss_by_col_idx,
int period,
GenmodelalgosglrmGlrmRegularizer regularization_x,
GenmodelalgosglrmGlrmRegularizer regularization_y,
double gamma_x,
double gamma_y,
int max_iterations,
int max_updates,
double init_step_size,
double min_step_size,
long seed,
GenmodelalgosglrmGlrmInitialization init,
SVDMethod svd_method,
java.lang.String user_y,
java.lang.String user_x,
java.lang.String loading_name,
boolean expand_user_y,
boolean impute_original,
boolean recover_svd,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a GLRM model.
|
retrofit2.Call<GLRMV3> |
trainGlrm(int k) |
retrofit2.Call<IsolationForestV3> |
trainIsolationforest() |
retrofit2.Call<IsolationForestV3> |
trainIsolationforest(long sample_size,
double sample_rate,
int mtries,
boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
int ntrees,
int max_depth,
double min_rows,
int nbins,
int nbins_top_level,
int nbins_cats,
double r2_stopping,
long seed,
boolean build_tree_one_node,
double[] sample_rate_per_class,
double col_sample_rate_per_tree,
double col_sample_rate_change_per_level,
int score_tree_interval,
double min_split_improvement,
TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type,
boolean calibrate_model,
java.lang.String calibration_frame,
boolean check_constant_response,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a IsolationForest model.
|
retrofit2.Call<KMeansV3> |
trainKmeans() |
retrofit2.Call<KMeansV3> |
trainKmeans(java.lang.String user_points,
int max_iterations,
boolean standardize,
long seed,
KMeansInitialization init,
boolean estimate_k,
int[] cluster_size_constraints,
int k,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a KMeans model.
|
retrofit2.Call<NaiveBayesV3> |
trainNaivebayes() |
retrofit2.Call<NaiveBayesV3> |
trainNaivebayes(boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
double laplace,
double min_sdev,
double eps_sdev,
double min_prob,
double eps_prob,
boolean compute_metrics,
long seed,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a NaiveBayes model.
|
retrofit2.Call<PCAV3> |
trainPca(DataInfoTransformType transform,
PCAMethod pca_method,
PCAImplementation pca_impl,
int k,
int max_iterations,
long seed,
boolean use_all_factor_levels,
boolean compute_metrics,
boolean impute_missing,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a PCA model.
|
retrofit2.Call<PCAV3> |
trainPca(int k) |
retrofit2.Call<PSVMV3> |
trainPsvm() |
retrofit2.Call<PSVMV3> |
trainPsvm(double hyper_param,
GenmodelalgospsvmKernelType kernel_type,
double gamma,
double rank_ratio,
double positive_weight,
double negative_weight,
boolean disable_training_metrics,
double sv_threshold,
int max_iterations,
double fact_threshold,
double feasible_threshold,
double surrogate_gap_threshold,
double mu_factor,
long seed,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a PSVM model.
|
retrofit2.Call<StackedEnsembleV99> |
trainStackedensemble(java.lang.String[] base_models) |
retrofit2.Call<StackedEnsembleV99> |
trainStackedensemble(java.lang.String[] base_models,
EnsembleMetalearnerAlgorithm metalearner_algorithm,
int metalearner_nfolds,
ModelParametersFoldAssignmentScheme metalearner_fold_assignment,
java.lang.String metalearner_fold_column,
boolean keep_levelone_frame,
java.lang.String metalearner_params,
java.lang.String blending_frame,
long seed,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a StackedEnsemble model.
|
retrofit2.Call<SVDV99> |
trainSvd() |
retrofit2.Call<SVDV99> |
trainSvd(DataInfoTransformType transform,
SVDMethod svd_method,
int nv,
int max_iterations,
long seed,
boolean keep_u,
java.lang.String u_name,
boolean use_all_factor_levels,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a SVD model.
|
retrofit2.Call<TargetEncoderV3> |
trainTargetencoder() |
retrofit2.Call<TargetEncoderV3> |
trainTargetencoder(boolean blending,
double k,
double f,
H2otargetencodingTargetEncoderDataLeakageHandlingStrategy data_leakage_handling,
double noise_level,
long seed,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a TargetEncoderBuilder model.
|
retrofit2.Call<Word2VecV3> |
trainWord2vec() |
retrofit2.Call<Word2VecV3> |
trainWord2vec(int vec_size,
int window_size,
float sent_sample_rate,
Word2VecNormModel norm_model,
int epochs,
int min_word_freq,
float init_learning_rate,
Word2VecWordModel word_model,
java.lang.String pre_trained,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a Word2Vec model.
|
retrofit2.Call<XGBoostV3> |
trainXgboost() |
retrofit2.Call<XGBoostV3> |
trainXgboost(int ntrees,
int max_depth,
double min_rows,
double min_child_weight,
double learn_rate,
double eta,
double sample_rate,
double subsample,
double col_sample_rate,
double colsample_bylevel,
double col_sample_rate_per_tree,
double colsample_bytree,
KeyValueV3[] monotone_constraints,
float max_abs_leafnode_pred,
float max_delta_step,
int score_tree_interval,
long seed,
float min_split_improvement,
float gamma,
int nthread,
boolean build_tree_one_node,
java.lang.String save_matrix_directory,
boolean calibrate_model,
java.lang.String calibration_frame,
int max_bins,
int max_leaves,
float min_sum_hessian_in_leaf,
float min_data_in_leaf,
TreexgboostXGBoostModelXGBoostParametersTreeMethod tree_method,
TreexgboostXGBoostModelXGBoostParametersGrowPolicy grow_policy,
TreexgboostXGBoostModelXGBoostParametersBooster booster,
float reg_lambda,
float reg_alpha,
boolean quiet_mode,
TreexgboostXGBoostModelXGBoostParametersDartSampleType sample_type,
TreexgboostXGBoostModelXGBoostParametersDartNormalizeType normalize_type,
float rate_drop,
boolean one_drop,
float skip_drop,
TreexgboostXGBoostModelXGBoostParametersDMatrixType dmatrix_type,
TreexgboostXGBoostModelXGBoostParametersBackend backend,
int gpu_id,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Train a XGBoost model.
|
retrofit2.Call<AggregatorV99> |
validate_parametersAggregator() |
retrofit2.Call<AggregatorV99> |
validate_parametersAggregator(DataInfoTransformType transform,
PCAMethod pca_method,
int k,
int max_iterations,
int target_num_exemplars,
double rel_tol_num_exemplars,
long seed,
boolean use_all_factor_levels,
boolean save_mapping_frame,
int num_iteration_without_new_exemplar,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of Aggregator model builder parameters.
|
retrofit2.Call<CoxPHV3> |
validate_parametersCoxph() |
retrofit2.Call<CoxPHV3> |
validate_parametersCoxph(java.lang.String start_column,
java.lang.String stop_column,
java.lang.String[] stratify_by,
CoxPHTies ties,
double init,
double lre_min,
int max_iterations,
java.lang.String[] interactions_only,
java.lang.String[] interactions,
StringPairV3[] interaction_pairs,
boolean use_all_factor_levels,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of CoxPH model builder parameters.
|
retrofit2.Call<DeepLearningV3> |
validate_parametersDeeplearning() |
retrofit2.Call<DeepLearningV3> |
validate_parametersDeeplearning(boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
DeepLearningActivation activation,
int[] hidden,
double epochs,
long train_samples_per_iteration,
double target_ratio_comm_to_comp,
long seed,
boolean adaptive_rate,
double rho,
double epsilon,
double rate,
double rate_annealing,
double rate_decay,
double momentum_start,
double momentum_ramp,
double momentum_stable,
boolean nesterov_accelerated_gradient,
double input_dropout_ratio,
double[] hidden_dropout_ratios,
double l1,
double l2,
float max_w2,
DeepLearningInitialWeightDistribution initial_weight_distribution,
double initial_weight_scale,
java.lang.String[] initial_weights,
java.lang.String[] initial_biases,
DeepLearningLoss loss,
double score_interval,
long score_training_samples,
long score_validation_samples,
double score_duty_cycle,
double classification_stop,
double regression_stop,
boolean quiet_mode,
DeepLearningClassSamplingMethod score_validation_sampling,
boolean overwrite_with_best_model,
boolean autoencoder,
boolean use_all_factor_levels,
boolean standardize,
boolean diagnostics,
boolean variable_importances,
boolean fast_mode,
boolean force_load_balance,
boolean replicate_training_data,
boolean single_node_mode,
boolean shuffle_training_data,
DeepLearningMissingValuesHandling missing_values_handling,
boolean sparse,
boolean col_major,
double average_activation,
double sparsity_beta,
int max_categorical_features,
boolean reproducible,
boolean export_weights_and_biases,
int mini_batch_size,
boolean elastic_averaging,
double elastic_averaging_moving_rate,
double elastic_averaging_regularization,
java.lang.String pretrained_autoencoder,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of DeepLearning model builder parameters.
|
retrofit2.Call<DeepWaterV3> |
validate_parametersDeepwater() |
retrofit2.Call<DeepWaterV3> |
validate_parametersDeepwater(DeepWaterParametersProblemType problem_type,
DeepWaterParametersActivation activation,
int[] hidden,
double input_dropout_ratio,
double[] hidden_dropout_ratios,
int max_confusion_matrix_size,
boolean sparse,
int max_hit_ratio_k,
double epochs,
long train_samples_per_iteration,
double target_ratio_comm_to_comp,
long seed,
double learning_rate,
double learning_rate_annealing,
double momentum_start,
double momentum_ramp,
double momentum_stable,
double score_interval,
long score_training_samples,
long score_validation_samples,
double score_duty_cycle,
double classification_stop,
double regression_stop,
boolean quiet_mode,
boolean overwrite_with_best_model,
boolean autoencoder,
boolean diagnostics,
boolean variable_importances,
boolean replicate_training_data,
boolean single_node_mode,
boolean shuffle_training_data,
int mini_batch_size,
double clip_gradient,
DeepWaterParametersNetwork network,
DeepWaterParametersBackend backend,
int[] image_shape,
int channels,
boolean gpu,
int[] device_id,
boolean cache_data,
java.lang.String network_definition_file,
java.lang.String network_parameters_file,
java.lang.String mean_image_file,
java.lang.String export_native_parameters_prefix,
boolean standardize,
boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of DeepWater model builder parameters.
|
retrofit2.Call<DRFV3> |
validate_parametersDrf() |
retrofit2.Call<DRFV3> |
validate_parametersDrf(int mtries,
boolean binomial_double_trees,
double sample_rate,
boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
int ntrees,
int max_depth,
double min_rows,
int nbins,
int nbins_top_level,
int nbins_cats,
double r2_stopping,
long seed,
boolean build_tree_one_node,
double[] sample_rate_per_class,
double col_sample_rate_per_tree,
double col_sample_rate_change_per_level,
int score_tree_interval,
double min_split_improvement,
TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type,
boolean calibrate_model,
java.lang.String calibration_frame,
boolean check_constant_response,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of DRF model builder parameters.
|
retrofit2.Call<GBMV3> |
validate_parametersGbm() |
retrofit2.Call<GBMV3> |
validate_parametersGbm(double learn_rate,
double learn_rate_annealing,
double sample_rate,
double col_sample_rate,
KeyValueV3[] monotone_constraints,
double max_abs_leafnode_pred,
double pred_noise_bandwidth,
boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
int ntrees,
int max_depth,
double min_rows,
int nbins,
int nbins_top_level,
int nbins_cats,
double r2_stopping,
long seed,
boolean build_tree_one_node,
double[] sample_rate_per_class,
double col_sample_rate_per_tree,
double col_sample_rate_change_per_level,
int score_tree_interval,
double min_split_improvement,
TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type,
boolean calibrate_model,
java.lang.String calibration_frame,
boolean check_constant_response,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of GBM model builder parameters.
|
retrofit2.Call<GenericV3> |
validate_parametersGeneric() |
retrofit2.Call<GenericV3> |
validate_parametersGeneric(java.lang.String path,
java.lang.String model_key,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of Generic model builder parameters.
|
retrofit2.Call<GLMV3> |
validate_parametersGlm() |
retrofit2.Call<GLMV3> |
validate_parametersGlm(long seed,
GLMFamily family,
GLMFamily[] rand_family,
double tweedie_variance_power,
double tweedie_link_power,
double theta,
GLMSolver solver,
double[] alpha,
double[] lambda,
boolean lambda_search,
boolean early_stopping,
int nlambdas,
boolean standardize,
GLMMissingValuesHandling missing_values_handling,
java.lang.String plug_values,
boolean non_negative,
int max_iterations,
double beta_epsilon,
double objective_epsilon,
double gradient_epsilon,
double obj_reg,
GLMLink link,
GLMLink[] rand_link,
double[] startval,
int[] random_columns,
boolean calc_like,
boolean intercept,
boolean HGLM,
double prior,
double lambda_min_ratio,
java.lang.String beta_constraints,
int max_active_predictors,
java.lang.String[] interactions,
StringPairV3[] interaction_pairs,
boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
boolean compute_p_values,
boolean remove_collinear_columns,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of GLM model builder parameters.
|
retrofit2.Call<GLRMV3> |
validate_parametersGlrm(DataInfoTransformType transform,
int k,
GenmodelalgosglrmGlrmLoss loss,
GenmodelalgosglrmGlrmLoss multi_loss,
GenmodelalgosglrmGlrmLoss[] loss_by_col,
int[] loss_by_col_idx,
int period,
GenmodelalgosglrmGlrmRegularizer regularization_x,
GenmodelalgosglrmGlrmRegularizer regularization_y,
double gamma_x,
double gamma_y,
int max_iterations,
int max_updates,
double init_step_size,
double min_step_size,
long seed,
GenmodelalgosglrmGlrmInitialization init,
SVDMethod svd_method,
java.lang.String user_y,
java.lang.String user_x,
java.lang.String loading_name,
boolean expand_user_y,
boolean impute_original,
boolean recover_svd,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of GLRM model builder parameters.
|
retrofit2.Call<GLRMV3> |
validate_parametersGlrm(int k) |
retrofit2.Call<IsolationForestV3> |
validate_parametersIsolationforest() |
retrofit2.Call<IsolationForestV3> |
validate_parametersIsolationforest(long sample_size,
double sample_rate,
int mtries,
boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
int ntrees,
int max_depth,
double min_rows,
int nbins,
int nbins_top_level,
int nbins_cats,
double r2_stopping,
long seed,
boolean build_tree_one_node,
double[] sample_rate_per_class,
double col_sample_rate_per_tree,
double col_sample_rate_change_per_level,
int score_tree_interval,
double min_split_improvement,
TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type,
boolean calibrate_model,
java.lang.String calibration_frame,
boolean check_constant_response,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of IsolationForest model builder parameters.
|
retrofit2.Call<KMeansV3> |
validate_parametersKmeans() |
retrofit2.Call<KMeansV3> |
validate_parametersKmeans(java.lang.String user_points,
int max_iterations,
boolean standardize,
long seed,
KMeansInitialization init,
boolean estimate_k,
int[] cluster_size_constraints,
int k,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of KMeans model builder parameters.
|
retrofit2.Call<NaiveBayesV3> |
validate_parametersNaivebayes() |
retrofit2.Call<NaiveBayesV3> |
validate_parametersNaivebayes(boolean balance_classes,
float[] class_sampling_factors,
float max_after_balance_size,
int max_confusion_matrix_size,
int max_hit_ratio_k,
double laplace,
double min_sdev,
double eps_sdev,
double min_prob,
double eps_prob,
boolean compute_metrics,
long seed,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of NaiveBayes model builder parameters.
|
retrofit2.Call<PCAV3> |
validate_parametersPca(DataInfoTransformType transform,
PCAMethod pca_method,
PCAImplementation pca_impl,
int k,
int max_iterations,
long seed,
boolean use_all_factor_levels,
boolean compute_metrics,
boolean impute_missing,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of PCA model builder parameters.
|
retrofit2.Call<PCAV3> |
validate_parametersPca(int k) |
retrofit2.Call<PSVMV3> |
validate_parametersPsvm() |
retrofit2.Call<PSVMV3> |
validate_parametersPsvm(double hyper_param,
GenmodelalgospsvmKernelType kernel_type,
double gamma,
double rank_ratio,
double positive_weight,
double negative_weight,
boolean disable_training_metrics,
double sv_threshold,
int max_iterations,
double fact_threshold,
double feasible_threshold,
double surrogate_gap_threshold,
double mu_factor,
long seed,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of PSVM model builder parameters.
|
retrofit2.Call<StackedEnsembleV99> |
validate_parametersStackedensemble(java.lang.String[] base_models) |
retrofit2.Call<StackedEnsembleV99> |
validate_parametersStackedensemble(java.lang.String[] base_models,
EnsembleMetalearnerAlgorithm metalearner_algorithm,
int metalearner_nfolds,
ModelParametersFoldAssignmentScheme metalearner_fold_assignment,
java.lang.String metalearner_fold_column,
boolean keep_levelone_frame,
java.lang.String metalearner_params,
java.lang.String blending_frame,
long seed,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of StackedEnsemble model builder parameters.
|
retrofit2.Call<SVDV99> |
validate_parametersSvd() |
retrofit2.Call<SVDV99> |
validate_parametersSvd(DataInfoTransformType transform,
SVDMethod svd_method,
int nv,
int max_iterations,
long seed,
boolean keep_u,
java.lang.String u_name,
boolean use_all_factor_levels,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of SVD model builder parameters.
|
retrofit2.Call<TargetEncoderV3> |
validate_parametersTargetencoder() |
retrofit2.Call<TargetEncoderV3> |
validate_parametersTargetencoder(boolean blending,
double k,
double f,
H2otargetencodingTargetEncoderDataLeakageHandlingStrategy data_leakage_handling,
double noise_level,
long seed,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of TargetEncoderBuilder model builder parameters.
|
retrofit2.Call<Word2VecV3> |
validate_parametersWord2vec() |
retrofit2.Call<Word2VecV3> |
validate_parametersWord2vec(int vec_size,
int window_size,
float sent_sample_rate,
Word2VecNormModel norm_model,
int epochs,
int min_word_freq,
float init_learning_rate,
Word2VecWordModel word_model,
java.lang.String pre_trained,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of Word2Vec model builder parameters.
|
retrofit2.Call<XGBoostV3> |
validate_parametersXgboost() |
retrofit2.Call<XGBoostV3> |
validate_parametersXgboost(int ntrees,
int max_depth,
double min_rows,
double min_child_weight,
double learn_rate,
double eta,
double sample_rate,
double subsample,
double col_sample_rate,
double colsample_bylevel,
double col_sample_rate_per_tree,
double colsample_bytree,
KeyValueV3[] monotone_constraints,
float max_abs_leafnode_pred,
float max_delta_step,
int score_tree_interval,
long seed,
float min_split_improvement,
float gamma,
int nthread,
boolean build_tree_one_node,
java.lang.String save_matrix_directory,
boolean calibrate_model,
java.lang.String calibration_frame,
int max_bins,
int max_leaves,
float min_sum_hessian_in_leaf,
float min_data_in_leaf,
TreexgboostXGBoostModelXGBoostParametersTreeMethod tree_method,
TreexgboostXGBoostModelXGBoostParametersGrowPolicy grow_policy,
TreexgboostXGBoostModelXGBoostParametersBooster booster,
float reg_lambda,
float reg_alpha,
boolean quiet_mode,
TreexgboostXGBoostModelXGBoostParametersDartSampleType sample_type,
TreexgboostXGBoostModelXGBoostParametersDartNormalizeType normalize_type,
float rate_drop,
boolean one_drop,
float skip_drop,
TreexgboostXGBoostModelXGBoostParametersDMatrixType dmatrix_type,
TreexgboostXGBoostModelXGBoostParametersBackend backend,
int gpu_id,
java.lang.String model_id,
java.lang.String training_frame,
java.lang.String validation_frame,
int nfolds,
boolean keep_cross_validation_models,
boolean keep_cross_validation_predictions,
boolean keep_cross_validation_fold_assignment,
boolean parallelize_cross_validation,
GenmodelutilsDistributionFamily distribution,
double tweedie_power,
double quantile_alpha,
double huber_alpha,
java.lang.String response_column,
java.lang.String weights_column,
java.lang.String offset_column,
java.lang.String fold_column,
ModelParametersFoldAssignmentScheme fold_assignment,
ModelParametersCategoricalEncodingScheme categorical_encoding,
int max_categorical_levels,
java.lang.String[] ignored_columns,
boolean ignore_const_cols,
boolean score_each_iteration,
java.lang.String checkpoint,
int stopping_rounds,
double max_runtime_secs,
ScoreKeeperStoppingMetric stopping_metric,
double stopping_tolerance,
java.lang.String custom_metric_func,
java.lang.String custom_distribution_func,
java.lang.String export_checkpoints_dir)
Validate a set of XGBoost model builder parameters.
|
@FormUrlEncoded @POST(value="/3/ModelBuilders/xgboost") retrofit2.Call<XGBoostV3> trainXgboost(@Field(value="ntrees") int ntrees, @Field(value="max_depth") int max_depth, @Field(value="min_rows") double min_rows, @Field(value="min_child_weight") double min_child_weight, @Field(value="learn_rate") double learn_rate, @Field(value="eta") double eta, @Field(value="sample_rate") double sample_rate, @Field(value="subsample") double subsample, @Field(value="col_sample_rate") double col_sample_rate, @Field(value="colsample_bylevel") double colsample_bylevel, @Field(value="col_sample_rate_per_tree") double col_sample_rate_per_tree, @Field(value="colsample_bytree") double colsample_bytree, @Field(value="monotone_constraints") KeyValueV3[] monotone_constraints, @Field(value="max_abs_leafnode_pred") float max_abs_leafnode_pred, @Field(value="max_delta_step") float max_delta_step, @Field(value="score_tree_interval") int score_tree_interval, @Field(value="seed") long seed, @Field(value="min_split_improvement") float min_split_improvement, @Field(value="gamma") float gamma, @Field(value="nthread") int nthread, @Field(value="build_tree_one_node") boolean build_tree_one_node, @Field(value="save_matrix_directory") java.lang.String save_matrix_directory, @Field(value="calibrate_model") boolean calibrate_model, @Field(value="calibration_frame") java.lang.String calibration_frame, @Field(value="max_bins") int max_bins, @Field(value="max_leaves") int max_leaves, @Field(value="min_sum_hessian_in_leaf") float min_sum_hessian_in_leaf, @Field(value="min_data_in_leaf") float min_data_in_leaf, @Field(value="tree_method") TreexgboostXGBoostModelXGBoostParametersTreeMethod tree_method, @Field(value="grow_policy") TreexgboostXGBoostModelXGBoostParametersGrowPolicy grow_policy, @Field(value="booster") TreexgboostXGBoostModelXGBoostParametersBooster booster, @Field(value="reg_lambda") float reg_lambda, @Field(value="reg_alpha") float reg_alpha, @Field(value="quiet_mode") boolean quiet_mode, @Field(value="sample_type") TreexgboostXGBoostModelXGBoostParametersDartSampleType sample_type, @Field(value="normalize_type") TreexgboostXGBoostModelXGBoostParametersDartNormalizeType normalize_type, @Field(value="rate_drop") float rate_drop, @Field(value="one_drop") boolean one_drop, @Field(value="skip_drop") float skip_drop, @Field(value="dmatrix_type") TreexgboostXGBoostModelXGBoostParametersDMatrixType dmatrix_type, @Field(value="backend") TreexgboostXGBoostModelXGBoostParametersBackend backend, @Field(value="gpu_id") int gpu_id, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
ntrees - (same as n_estimators) Number of trees.max_depth - Maximum tree depth.min_rows - (same as min_child_weight) Fewest allowed (weighted) observations in a leaf.min_child_weight - (same as min_rows) Fewest allowed (weighted) observations in a leaf.learn_rate - (same as eta) Learning rate (from 0.0 to 1.0)eta - (same as learn_rate) Learning rate (from 0.0 to 1.0)sample_rate - (same as subsample) Row sample rate per tree (from 0.0 to 1.0)subsample - (same as sample_rate) Row sample rate per tree (from 0.0 to 1.0)col_sample_rate - (same as colsample_bylevel) Column sample rate (from 0.0 to 1.0)colsample_bylevel - (same as col_sample_rate) Column sample rate (from 0.0 to 1.0)col_sample_rate_per_tree - (same as colsample_bytree) Column sample rate per tree (from 0.0 to 1.0)colsample_bytree - (same as col_sample_rate_per_tree) Column sample rate per tree (from 0.0 to 1.0)monotone_constraints - A mapping representing monotonic constraints. Use +1 to enforce an increasing
constraint and -1 to specify a decreasing constraint.max_abs_leafnode_pred - (same as max_delta_step) Maximum absolute value of a leaf node predictionmax_delta_step - (same as max_abs_leafnode_pred) Maximum absolute value of a leaf node predictionscore_tree_interval - Score the model after every so many trees. Disabled if set to 0.seed - Seed for pseudo random number generator (if applicable)min_split_improvement - (same as gamma) Minimum relative improvement in squared error reduction for a split
to happengamma - (same as min_split_improvement) Minimum relative improvement in squared error reduction for a split
to happennthread - Number of parallel threads that can be used to run XGBoost. Cannot exceed H2O cluster limits
(-nthreads parameter). Defaults to maximum availablebuild_tree_one_node - Run on one node only; no network overhead but fewer cpus used. Suitable for small
datasets.save_matrix_directory - Directory where to save matrices passed to XGBoost library. Useful for debugging.calibrate_model - Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide
more accurate estimates of class probabilities.calibration_frame - Calibration frame for Platt Scalingmax_bins - For tree_method=hist only: maximum number of binsmax_leaves - For tree_method=hist only: maximum number of leavesmin_sum_hessian_in_leaf - For tree_method=hist only: the mininum sum of hessian in a leaf to keep splittingmin_data_in_leaf - For tree_method=hist only: the mininum data in a leaf to keep splittingtree_method - Tree methodgrow_policy - Grow policy - depthwise is standard GBM, lossguide is LightGBMbooster - Booster typereg_lambda - L2 regularizationreg_alpha - L1 regularizationquiet_mode - Enable quiet modesample_type - For booster=dart only: sample_typenormalize_type - For booster=dart only: normalize_typerate_drop - For booster=dart only: rate_drop (0..1)one_drop - For booster=dart only: one_dropskip_drop - For booster=dart only: skip_drop (0..1)dmatrix_type - Type of DMatrix. For sparse, NAs and 0 are treated equally.backend - Backend. By default (auto), a GPU is used if available.gpu_id - Which GPU to use.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/xgboost") retrofit2.Call<XGBoostV3> trainXgboost()
@FormUrlEncoded @POST(value="/3/ModelBuilders/xgboost/parameters") retrofit2.Call<XGBoostV3> validate_parametersXgboost(@Field(value="ntrees") int ntrees, @Field(value="max_depth") int max_depth, @Field(value="min_rows") double min_rows, @Field(value="min_child_weight") double min_child_weight, @Field(value="learn_rate") double learn_rate, @Field(value="eta") double eta, @Field(value="sample_rate") double sample_rate, @Field(value="subsample") double subsample, @Field(value="col_sample_rate") double col_sample_rate, @Field(value="colsample_bylevel") double colsample_bylevel, @Field(value="col_sample_rate_per_tree") double col_sample_rate_per_tree, @Field(value="colsample_bytree") double colsample_bytree, @Field(value="monotone_constraints") KeyValueV3[] monotone_constraints, @Field(value="max_abs_leafnode_pred") float max_abs_leafnode_pred, @Field(value="max_delta_step") float max_delta_step, @Field(value="score_tree_interval") int score_tree_interval, @Field(value="seed") long seed, @Field(value="min_split_improvement") float min_split_improvement, @Field(value="gamma") float gamma, @Field(value="nthread") int nthread, @Field(value="build_tree_one_node") boolean build_tree_one_node, @Field(value="save_matrix_directory") java.lang.String save_matrix_directory, @Field(value="calibrate_model") boolean calibrate_model, @Field(value="calibration_frame") java.lang.String calibration_frame, @Field(value="max_bins") int max_bins, @Field(value="max_leaves") int max_leaves, @Field(value="min_sum_hessian_in_leaf") float min_sum_hessian_in_leaf, @Field(value="min_data_in_leaf") float min_data_in_leaf, @Field(value="tree_method") TreexgboostXGBoostModelXGBoostParametersTreeMethod tree_method, @Field(value="grow_policy") TreexgboostXGBoostModelXGBoostParametersGrowPolicy grow_policy, @Field(value="booster") TreexgboostXGBoostModelXGBoostParametersBooster booster, @Field(value="reg_lambda") float reg_lambda, @Field(value="reg_alpha") float reg_alpha, @Field(value="quiet_mode") boolean quiet_mode, @Field(value="sample_type") TreexgboostXGBoostModelXGBoostParametersDartSampleType sample_type, @Field(value="normalize_type") TreexgboostXGBoostModelXGBoostParametersDartNormalizeType normalize_type, @Field(value="rate_drop") float rate_drop, @Field(value="one_drop") boolean one_drop, @Field(value="skip_drop") float skip_drop, @Field(value="dmatrix_type") TreexgboostXGBoostModelXGBoostParametersDMatrixType dmatrix_type, @Field(value="backend") TreexgboostXGBoostModelXGBoostParametersBackend backend, @Field(value="gpu_id") int gpu_id, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
ntrees - (same as n_estimators) Number of trees.max_depth - Maximum tree depth.min_rows - (same as min_child_weight) Fewest allowed (weighted) observations in a leaf.min_child_weight - (same as min_rows) Fewest allowed (weighted) observations in a leaf.learn_rate - (same as eta) Learning rate (from 0.0 to 1.0)eta - (same as learn_rate) Learning rate (from 0.0 to 1.0)sample_rate - (same as subsample) Row sample rate per tree (from 0.0 to 1.0)subsample - (same as sample_rate) Row sample rate per tree (from 0.0 to 1.0)col_sample_rate - (same as colsample_bylevel) Column sample rate (from 0.0 to 1.0)colsample_bylevel - (same as col_sample_rate) Column sample rate (from 0.0 to 1.0)col_sample_rate_per_tree - (same as colsample_bytree) Column sample rate per tree (from 0.0 to 1.0)colsample_bytree - (same as col_sample_rate_per_tree) Column sample rate per tree (from 0.0 to 1.0)monotone_constraints - A mapping representing monotonic constraints. Use +1 to enforce an increasing
constraint and -1 to specify a decreasing constraint.max_abs_leafnode_pred - (same as max_delta_step) Maximum absolute value of a leaf node predictionmax_delta_step - (same as max_abs_leafnode_pred) Maximum absolute value of a leaf node predictionscore_tree_interval - Score the model after every so many trees. Disabled if set to 0.seed - Seed for pseudo random number generator (if applicable)min_split_improvement - (same as gamma) Minimum relative improvement in squared error reduction for a split
to happengamma - (same as min_split_improvement) Minimum relative improvement in squared error reduction for a split
to happennthread - Number of parallel threads that can be used to run XGBoost. Cannot exceed H2O cluster limits
(-nthreads parameter). Defaults to maximum availablebuild_tree_one_node - Run on one node only; no network overhead but fewer cpus used. Suitable for small
datasets.save_matrix_directory - Directory where to save matrices passed to XGBoost library. Useful for debugging.calibrate_model - Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide
more accurate estimates of class probabilities.calibration_frame - Calibration frame for Platt Scalingmax_bins - For tree_method=hist only: maximum number of binsmax_leaves - For tree_method=hist only: maximum number of leavesmin_sum_hessian_in_leaf - For tree_method=hist only: the mininum sum of hessian in a leaf to keep splittingmin_data_in_leaf - For tree_method=hist only: the mininum data in a leaf to keep splittingtree_method - Tree methodgrow_policy - Grow policy - depthwise is standard GBM, lossguide is LightGBMbooster - Booster typereg_lambda - L2 regularizationreg_alpha - L1 regularizationquiet_mode - Enable quiet modesample_type - For booster=dart only: sample_typenormalize_type - For booster=dart only: normalize_typerate_drop - For booster=dart only: rate_drop (0..1)one_drop - For booster=dart only: one_dropskip_drop - For booster=dart only: skip_drop (0..1)dmatrix_type - Type of DMatrix. For sparse, NAs and 0 are treated equally.backend - Backend. By default (auto), a GPU is used if available.gpu_id - Which GPU to use.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/xgboost/parameters") retrofit2.Call<XGBoostV3> validate_parametersXgboost()
@FormUrlEncoded @POST(value="/3/ModelBuilders/targetencoder") retrofit2.Call<TargetEncoderV3> trainTargetencoder(@Field(value="blending") boolean blending, @Field(value="k") double k, @Field(value="f") double f, @Field(value="data_leakage_handling") H2otargetencodingTargetEncoderDataLeakageHandlingStrategy data_leakage_handling, @Field(value="noise_level") double noise_level, @Field(value="seed") long seed, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
blending - Blending enabled/disabledk - Inflection point. Used for blending (if enabled). Blending is to be enabled separately using the
'blending' parameter.f - Smoothing. Used for blending (if enabled). Blending is to be enabled separately using the 'blending'
parameter.data_leakage_handling - Data leakage handling strategy.noise_level - Noise levelseed - Seed for the specified noise levelmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/targetencoder") retrofit2.Call<TargetEncoderV3> trainTargetencoder()
@FormUrlEncoded @POST(value="/3/ModelBuilders/targetencoder/parameters") retrofit2.Call<TargetEncoderV3> validate_parametersTargetencoder(@Field(value="blending") boolean blending, @Field(value="k") double k, @Field(value="f") double f, @Field(value="data_leakage_handling") H2otargetencodingTargetEncoderDataLeakageHandlingStrategy data_leakage_handling, @Field(value="noise_level") double noise_level, @Field(value="seed") long seed, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
blending - Blending enabled/disabledk - Inflection point. Used for blending (if enabled). Blending is to be enabled separately using the
'blending' parameter.f - Smoothing. Used for blending (if enabled). Blending is to be enabled separately using the 'blending'
parameter.data_leakage_handling - Data leakage handling strategy.noise_level - Noise levelseed - Seed for the specified noise levelmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/targetencoder/parameters") retrofit2.Call<TargetEncoderV3> validate_parametersTargetencoder()
@FormUrlEncoded @POST(value="/3/ModelBuilders/deeplearning") retrofit2.Call<DeepLearningV3> trainDeeplearning(@Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="activation") DeepLearningActivation activation, @Field(value="hidden") int[] hidden, @Field(value="epochs") double epochs, @Field(value="train_samples_per_iteration") long train_samples_per_iteration, @Field(value="target_ratio_comm_to_comp") double target_ratio_comm_to_comp, @Field(value="seed") long seed, @Field(value="adaptive_rate") boolean adaptive_rate, @Field(value="rho") double rho, @Field(value="epsilon") double epsilon, @Field(value="rate") double rate, @Field(value="rate_annealing") double rate_annealing, @Field(value="rate_decay") double rate_decay, @Field(value="momentum_start") double momentum_start, @Field(value="momentum_ramp") double momentum_ramp, @Field(value="momentum_stable") double momentum_stable, @Field(value="nesterov_accelerated_gradient") boolean nesterov_accelerated_gradient, @Field(value="input_dropout_ratio") double input_dropout_ratio, @Field(value="hidden_dropout_ratios") double[] hidden_dropout_ratios, @Field(value="l1") double l1, @Field(value="l2") double l2, @Field(value="max_w2") float max_w2, @Field(value="initial_weight_distribution") DeepLearningInitialWeightDistribution initial_weight_distribution, @Field(value="initial_weight_scale") double initial_weight_scale, @Field(value="initial_weights") java.lang.String[] initial_weights, @Field(value="initial_biases") java.lang.String[] initial_biases, @Field(value="loss") DeepLearningLoss loss, @Field(value="score_interval") double score_interval, @Field(value="score_training_samples") long score_training_samples, @Field(value="score_validation_samples") long score_validation_samples, @Field(value="score_duty_cycle") double score_duty_cycle, @Field(value="classification_stop") double classification_stop, @Field(value="regression_stop") double regression_stop, @Field(value="quiet_mode") boolean quiet_mode, @Field(value="score_validation_sampling") DeepLearningClassSamplingMethod score_validation_sampling, @Field(value="overwrite_with_best_model") boolean overwrite_with_best_model, @Field(value="autoencoder") boolean autoencoder, @Field(value="use_all_factor_levels") boolean use_all_factor_levels, @Field(value="standardize") boolean standardize, @Field(value="diagnostics") boolean diagnostics, @Field(value="variable_importances") boolean variable_importances, @Field(value="fast_mode") boolean fast_mode, @Field(value="force_load_balance") boolean force_load_balance, @Field(value="replicate_training_data") boolean replicate_training_data, @Field(value="single_node_mode") boolean single_node_mode, @Field(value="shuffle_training_data") boolean shuffle_training_data, @Field(value="missing_values_handling") DeepLearningMissingValuesHandling missing_values_handling, @Field(value="sparse") boolean sparse, @Field(value="col_major") boolean col_major, @Field(value="average_activation") double average_activation, @Field(value="sparsity_beta") double sparsity_beta, @Field(value="max_categorical_features") int max_categorical_features, @Field(value="reproducible") boolean reproducible, @Field(value="export_weights_and_biases") boolean export_weights_and_biases, @Field(value="mini_batch_size") int mini_batch_size, @Field(value="elastic_averaging") boolean elastic_averaging, @Field(value="elastic_averaging_moving_rate") double elastic_averaging_moving_rate, @Field(value="elastic_averaging_regularization") double elastic_averaging_regularization, @Field(value="pretrained_autoencoder") java.lang.String pretrained_autoencoder, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logs.max_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable).activation - Activation function.hidden - Hidden layer sizes (e.g. [100, 100]).epochs - How many times the dataset should be iterated (streamed), can be fractional.train_samples_per_iteration - Number of training samples (globally) per MapReduce iteration. Special values
are 0: one epoch, -1: all available data (e.g., replicated training data), -2:
automatic.target_ratio_comm_to_comp - Target ratio of communication overhead to computation. Only for multi-node
operation and train_samples_per_iteration = -2 (auto-tuning).seed - Seed for random numbers (affects sampling) - Note: only reproducible when running single threaded.adaptive_rate - Adaptive learning rate.rho - Adaptive learning rate time decay factor (similarity to prior updates).epsilon - Adaptive learning rate smoothing factor (to avoid divisions by zero and allow progress).rate - Learning rate (higher => less stable, lower => slower convergence).rate_annealing - Learning rate annealing: rate / (1 + rate_annealing * samples).rate_decay - Learning rate decay factor between layers (N-th layer: rate * rate_decay ^ (n - 1).momentum_start - Initial momentum at the beginning of training (try 0.5).momentum_ramp - Number of training samples for which momentum increases.momentum_stable - Final momentum after the ramp is over (try 0.99).nesterov_accelerated_gradient - Use Nesterov accelerated gradient (recommended).input_dropout_ratio - Input layer dropout ratio (can improve generalization, try 0.1 or 0.2).hidden_dropout_ratios - Hidden layer dropout ratios (can improve generalization), specify one value per
hidden layer, defaults to 0.5.l1 - L1 regularization (can add stability and improve generalization, causes many weights to become 0).l2 - L2 regularization (can add stability and improve generalization, causes many weights to be small.max_w2 - Constraint for squared sum of incoming weights per unit (e.g. for Rectifier).initial_weight_distribution - Initial weight distribution.initial_weight_scale - Uniform: -value...value, Normal: stddev.initial_weights - A list of H2OFrame ids to initialize the weight matrices of this model with.initial_biases - A list of H2OFrame ids to initialize the bias vectors of this model with.loss - Loss function.score_interval - Shortest time interval (in seconds) between model scoring.score_training_samples - Number of training set samples for scoring (0 for all).score_validation_samples - Number of validation set samples for scoring (0 for all).score_duty_cycle - Maximum duty cycle fraction for scoring (lower: more training, higher: more scoring).classification_stop - Stopping criterion for classification error fraction on training data (-1 to disable).regression_stop - Stopping criterion for regression error (MSE) on training data (-1 to disable).quiet_mode - Enable quiet mode for less output to standard output.score_validation_sampling - Method used to sample validation dataset for scoring.overwrite_with_best_model - If enabled, override the final model with the best model found during training.autoencoder - Auto-Encoder.use_all_factor_levels - Use all factor levels of categorical variables. Otherwise, the first factor level is
omitted (without loss of accuracy). Useful for variable importances and auto-enabled
for autoencoder.standardize - If enabled, automatically standardize the data. If disabled, the user must provide properly
scaled input data.diagnostics - Enable diagnostics for hidden layers.variable_importances - Compute variable importances for input features (Gedeon method) - can be slow for
large networks.fast_mode - Enable fast mode (minor approximation in back-propagation).force_load_balance - Force extra load balancing to increase training speed for small datasets (to keep all
cores busy).replicate_training_data - Replicate the entire training dataset onto every node for faster training on small
datasets.single_node_mode - Run on a single node for fine-tuning of model parameters.shuffle_training_data - Enable shuffling of training data (recommended if training data is replicated and
train_samples_per_iteration is close to #nodes x #rows, of if using
balance_classes).missing_values_handling - Handling of missing values. Either MeanImputation or Skip.sparse - Sparse data handling (more efficient for data with lots of 0 values).col_major - #DEPRECATED Use a column major weight matrix for input layer. Can speed up forward propagation,
but might slow down backpropagation.average_activation - Average activation for sparse auto-encoder. #Experimentalsparsity_beta - Sparsity regularization. #Experimentalmax_categorical_features - Max. number of categorical features, enforced via hashing. #Experimentalreproducible - Force reproducibility on small data (will be slow - only uses 1 thread).export_weights_and_biases - Whether to export Neural Network weights and biases to H2O Frames.mini_batch_size - Mini-batch size (smaller leads to better fit, larger can speed up and generalize better).elastic_averaging - Elastic averaging between compute nodes can improve distributed model convergence.
#Experimentalelastic_averaging_moving_rate - Elastic averaging moving rate (only if elastic averaging is enabled).elastic_averaging_regularization - Elastic averaging regularization strength (only if elastic averaging is
enabled).pretrained_autoencoder - Pretrained autoencoder model to initialize this model with.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/deeplearning") retrofit2.Call<DeepLearningV3> trainDeeplearning()
@FormUrlEncoded @POST(value="/3/ModelBuilders/deeplearning/parameters") retrofit2.Call<DeepLearningV3> validate_parametersDeeplearning(@Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="activation") DeepLearningActivation activation, @Field(value="hidden") int[] hidden, @Field(value="epochs") double epochs, @Field(value="train_samples_per_iteration") long train_samples_per_iteration, @Field(value="target_ratio_comm_to_comp") double target_ratio_comm_to_comp, @Field(value="seed") long seed, @Field(value="adaptive_rate") boolean adaptive_rate, @Field(value="rho") double rho, @Field(value="epsilon") double epsilon, @Field(value="rate") double rate, @Field(value="rate_annealing") double rate_annealing, @Field(value="rate_decay") double rate_decay, @Field(value="momentum_start") double momentum_start, @Field(value="momentum_ramp") double momentum_ramp, @Field(value="momentum_stable") double momentum_stable, @Field(value="nesterov_accelerated_gradient") boolean nesterov_accelerated_gradient, @Field(value="input_dropout_ratio") double input_dropout_ratio, @Field(value="hidden_dropout_ratios") double[] hidden_dropout_ratios, @Field(value="l1") double l1, @Field(value="l2") double l2, @Field(value="max_w2") float max_w2, @Field(value="initial_weight_distribution") DeepLearningInitialWeightDistribution initial_weight_distribution, @Field(value="initial_weight_scale") double initial_weight_scale, @Field(value="initial_weights") java.lang.String[] initial_weights, @Field(value="initial_biases") java.lang.String[] initial_biases, @Field(value="loss") DeepLearningLoss loss, @Field(value="score_interval") double score_interval, @Field(value="score_training_samples") long score_training_samples, @Field(value="score_validation_samples") long score_validation_samples, @Field(value="score_duty_cycle") double score_duty_cycle, @Field(value="classification_stop") double classification_stop, @Field(value="regression_stop") double regression_stop, @Field(value="quiet_mode") boolean quiet_mode, @Field(value="score_validation_sampling") DeepLearningClassSamplingMethod score_validation_sampling, @Field(value="overwrite_with_best_model") boolean overwrite_with_best_model, @Field(value="autoencoder") boolean autoencoder, @Field(value="use_all_factor_levels") boolean use_all_factor_levels, @Field(value="standardize") boolean standardize, @Field(value="diagnostics") boolean diagnostics, @Field(value="variable_importances") boolean variable_importances, @Field(value="fast_mode") boolean fast_mode, @Field(value="force_load_balance") boolean force_load_balance, @Field(value="replicate_training_data") boolean replicate_training_data, @Field(value="single_node_mode") boolean single_node_mode, @Field(value="shuffle_training_data") boolean shuffle_training_data, @Field(value="missing_values_handling") DeepLearningMissingValuesHandling missing_values_handling, @Field(value="sparse") boolean sparse, @Field(value="col_major") boolean col_major, @Field(value="average_activation") double average_activation, @Field(value="sparsity_beta") double sparsity_beta, @Field(value="max_categorical_features") int max_categorical_features, @Field(value="reproducible") boolean reproducible, @Field(value="export_weights_and_biases") boolean export_weights_and_biases, @Field(value="mini_batch_size") int mini_batch_size, @Field(value="elastic_averaging") boolean elastic_averaging, @Field(value="elastic_averaging_moving_rate") double elastic_averaging_moving_rate, @Field(value="elastic_averaging_regularization") double elastic_averaging_regularization, @Field(value="pretrained_autoencoder") java.lang.String pretrained_autoencoder, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logs.max_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable).activation - Activation function.hidden - Hidden layer sizes (e.g. [100, 100]).epochs - How many times the dataset should be iterated (streamed), can be fractional.train_samples_per_iteration - Number of training samples (globally) per MapReduce iteration. Special values
are 0: one epoch, -1: all available data (e.g., replicated training data), -2:
automatic.target_ratio_comm_to_comp - Target ratio of communication overhead to computation. Only for multi-node
operation and train_samples_per_iteration = -2 (auto-tuning).seed - Seed for random numbers (affects sampling) - Note: only reproducible when running single threaded.adaptive_rate - Adaptive learning rate.rho - Adaptive learning rate time decay factor (similarity to prior updates).epsilon - Adaptive learning rate smoothing factor (to avoid divisions by zero and allow progress).rate - Learning rate (higher => less stable, lower => slower convergence).rate_annealing - Learning rate annealing: rate / (1 + rate_annealing * samples).rate_decay - Learning rate decay factor between layers (N-th layer: rate * rate_decay ^ (n - 1).momentum_start - Initial momentum at the beginning of training (try 0.5).momentum_ramp - Number of training samples for which momentum increases.momentum_stable - Final momentum after the ramp is over (try 0.99).nesterov_accelerated_gradient - Use Nesterov accelerated gradient (recommended).input_dropout_ratio - Input layer dropout ratio (can improve generalization, try 0.1 or 0.2).hidden_dropout_ratios - Hidden layer dropout ratios (can improve generalization), specify one value per
hidden layer, defaults to 0.5.l1 - L1 regularization (can add stability and improve generalization, causes many weights to become 0).l2 - L2 regularization (can add stability and improve generalization, causes many weights to be small.max_w2 - Constraint for squared sum of incoming weights per unit (e.g. for Rectifier).initial_weight_distribution - Initial weight distribution.initial_weight_scale - Uniform: -value...value, Normal: stddev.initial_weights - A list of H2OFrame ids to initialize the weight matrices of this model with.initial_biases - A list of H2OFrame ids to initialize the bias vectors of this model with.loss - Loss function.score_interval - Shortest time interval (in seconds) between model scoring.score_training_samples - Number of training set samples for scoring (0 for all).score_validation_samples - Number of validation set samples for scoring (0 for all).score_duty_cycle - Maximum duty cycle fraction for scoring (lower: more training, higher: more scoring).classification_stop - Stopping criterion for classification error fraction on training data (-1 to disable).regression_stop - Stopping criterion for regression error (MSE) on training data (-1 to disable).quiet_mode - Enable quiet mode for less output to standard output.score_validation_sampling - Method used to sample validation dataset for scoring.overwrite_with_best_model - If enabled, override the final model with the best model found during training.autoencoder - Auto-Encoder.use_all_factor_levels - Use all factor levels of categorical variables. Otherwise, the first factor level is
omitted (without loss of accuracy). Useful for variable importances and auto-enabled
for autoencoder.standardize - If enabled, automatically standardize the data. If disabled, the user must provide properly
scaled input data.diagnostics - Enable diagnostics for hidden layers.variable_importances - Compute variable importances for input features (Gedeon method) - can be slow for
large networks.fast_mode - Enable fast mode (minor approximation in back-propagation).force_load_balance - Force extra load balancing to increase training speed for small datasets (to keep all
cores busy).replicate_training_data - Replicate the entire training dataset onto every node for faster training on small
datasets.single_node_mode - Run on a single node for fine-tuning of model parameters.shuffle_training_data - Enable shuffling of training data (recommended if training data is replicated and
train_samples_per_iteration is close to #nodes x #rows, of if using
balance_classes).missing_values_handling - Handling of missing values. Either MeanImputation or Skip.sparse - Sparse data handling (more efficient for data with lots of 0 values).col_major - #DEPRECATED Use a column major weight matrix for input layer. Can speed up forward propagation,
but might slow down backpropagation.average_activation - Average activation for sparse auto-encoder. #Experimentalsparsity_beta - Sparsity regularization. #Experimentalmax_categorical_features - Max. number of categorical features, enforced via hashing. #Experimentalreproducible - Force reproducibility on small data (will be slow - only uses 1 thread).export_weights_and_biases - Whether to export Neural Network weights and biases to H2O Frames.mini_batch_size - Mini-batch size (smaller leads to better fit, larger can speed up and generalize better).elastic_averaging - Elastic averaging between compute nodes can improve distributed model convergence.
#Experimentalelastic_averaging_moving_rate - Elastic averaging moving rate (only if elastic averaging is enabled).elastic_averaging_regularization - Elastic averaging regularization strength (only if elastic averaging is
enabled).pretrained_autoencoder - Pretrained autoencoder model to initialize this model with.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/deeplearning/parameters") retrofit2.Call<DeepLearningV3> validate_parametersDeeplearning()
@FormUrlEncoded @POST(value="/3/ModelBuilders/glm") retrofit2.Call<GLMV3> trainGlm(@Field(value="seed") long seed, @Field(value="family") GLMFamily family, @Field(value="rand_family") GLMFamily[] rand_family, @Field(value="tweedie_variance_power") double tweedie_variance_power, @Field(value="tweedie_link_power") double tweedie_link_power, @Field(value="theta") double theta, @Field(value="solver") GLMSolver solver, @Field(value="alpha") double[] alpha, @Field(value="lambda") double[] lambda, @Field(value="lambda_search") boolean lambda_search, @Field(value="early_stopping") boolean early_stopping, @Field(value="nlambdas") int nlambdas, @Field(value="standardize") boolean standardize, @Field(value="missing_values_handling") GLMMissingValuesHandling missing_values_handling, @Field(value="plug_values") java.lang.String plug_values, @Field(value="non_negative") boolean non_negative, @Field(value="max_iterations") int max_iterations, @Field(value="beta_epsilon") double beta_epsilon, @Field(value="objective_epsilon") double objective_epsilon, @Field(value="gradient_epsilon") double gradient_epsilon, @Field(value="obj_reg") double obj_reg, @Field(value="link") GLMLink link, @Field(value="rand_link") GLMLink[] rand_link, @Field(value="startval") double[] startval, @Field(value="random_columns") int[] random_columns, @Field(value="calc_like") boolean calc_like, @Field(value="intercept") boolean intercept, @Field(value="HGLM") boolean HGLM, @Field(value="prior") double prior, @Field(value="lambda_min_ratio") double lambda_min_ratio, @Field(value="beta_constraints") java.lang.String beta_constraints, @Field(value="max_active_predictors") int max_active_predictors, @Field(value="interactions") java.lang.String[] interactions, @Field(value="interaction_pairs") StringPairV3[] interaction_pairs, @Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="compute_p_values") boolean compute_p_values, @Field(value="remove_collinear_columns") boolean remove_collinear_columns, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
seed - Seed for pseudo random number generator (if applicable)family - Family. Use binomial for classification with logistic regression, others are for regression
problems.rand_family - Random Component Family array. One for each random component. Only support gaussian for now.tweedie_variance_power - Tweedie variance powertweedie_link_power - Tweedie link powertheta - Thetasolver - AUTO will set the solver based on given data and the other parameters. IRLSM is fast on on problems
with small number of predictors and for lambda-search with L1 penalty, L_BFGS scales better for
datasets with many columns.alpha - Distribution of regularization between the L1 (Lasso) and L2 (Ridge) penalties. A value of 1 for
alpha represents Lasso regression, a value of 0 produces Ridge regression, and anything in between
specifies the amount of mixing between the two. Default value of alpha is 0 when SOLVER = 'L-BFGS';
0.5 otherwise.lambda - Regularization strengthlambda_search - Use lambda search starting at lambda max, given lambda is then interpreted as lambda minearly_stopping - Stop early when there is no more relative improvement on train or validation (if provided)nlambdas - Number of lambdas to be used in a search. Default indicates: If alpha is zero, with lambda search
set to True, the value of nlamdas is set to 30 (fewer lambdas are needed for ridge regression)
otherwise it is set to 100.standardize - Standardize numeric columns to have zero mean and unit variancemissing_values_handling - Handling of missing values. Either MeanImputation, Skip or PlugValues.plug_values - Plug Values (a single row frame containing values that will be used to impute missing values
of the training/validation frame, use with conjunction missing_values_handling = PlugValues)non_negative - Restrict coefficients (not intercept) to be non-negativemax_iterations - Maximum number of iterationsbeta_epsilon - Converge if beta changes less (using L-infinity norm) than beta esilon, ONLY applies to
IRLSM solverobjective_epsilon - Converge if objective value changes less than this. Default indicates: If lambda_search
is set to True the value of objective_epsilon is set to .0001. If the lambda_search is
set to False and lambda is equal to zero, the value of objective_epsilon is set to
.000001, for any other value of lambda the default value of objective_epsilon is set to
.0001.gradient_epsilon - Converge if objective changes less (using L-infinity norm) than this, ONLY applies to
L-BFGS solver. Default indicates: If lambda_search is set to False and lambda is equal to
zero, the default value of gradient_epsilon is equal to .000001, otherwise the default
value is .0001. If lambda_search is set to True, the conditional values above are 1E-8
and 1E-6 respectively.obj_reg - Likelihood divider in objective value computation, default is 1/nobslink - Link function.rand_link - Link function array for random component in HGLM.startval - double array to initialize fixed and random coefficients for HGLM.random_columns - random columns indices for HGLM.calc_like - if true, will return likelihood function value for HGLM.intercept - Include constant term in the modelHGLM - If set to true, will return HGLM model. Otherwise, normal GLM model will be returnedprior - Prior probability for y==1. To be used only for logistic regression iff the data has been sampled
and the mean of response does not reflect reality.lambda_min_ratio - Minimum lambda used in lambda search, specified as a ratio of lambda_max (the smallest
lambda that drives all coefficients to zero). Default indicates: if the number of
observations is greater than the number of variables, then lambda_min_ratio is set to
0.0001; if the number of observations is less than the number of variables, then
lambda_min_ratio is set to 0.01.beta_constraints - Beta constraintsmax_active_predictors - Maximum number of active predictors during computation. Use as a stopping criterion
to prevent expensive model building with many predictors. Default indicates: If the
IRLSM solver is used, the value of max_active_predictors is set to 5000 otherwise it
is set to 100000000.interactions - A list of predictor column indices to interact. All pairwise combinations will be computed
for the list.interaction_pairs - A list of pairwise (first order) column interactions.balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logsmax_hit_ratio_k - Maximum number (top K) of predictions to use for hit ratio computation (for multi-class
only, 0 to disable)compute_p_values - Request p-values computation, p-values work only with IRLSM solver and no regularizationremove_collinear_columns - In case of linearly dependent columns, remove some of the dependent columnsmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/glm") retrofit2.Call<GLMV3> trainGlm()
@FormUrlEncoded @POST(value="/3/ModelBuilders/glm/parameters") retrofit2.Call<GLMV3> validate_parametersGlm(@Field(value="seed") long seed, @Field(value="family") GLMFamily family, @Field(value="rand_family") GLMFamily[] rand_family, @Field(value="tweedie_variance_power") double tweedie_variance_power, @Field(value="tweedie_link_power") double tweedie_link_power, @Field(value="theta") double theta, @Field(value="solver") GLMSolver solver, @Field(value="alpha") double[] alpha, @Field(value="lambda") double[] lambda, @Field(value="lambda_search") boolean lambda_search, @Field(value="early_stopping") boolean early_stopping, @Field(value="nlambdas") int nlambdas, @Field(value="standardize") boolean standardize, @Field(value="missing_values_handling") GLMMissingValuesHandling missing_values_handling, @Field(value="plug_values") java.lang.String plug_values, @Field(value="non_negative") boolean non_negative, @Field(value="max_iterations") int max_iterations, @Field(value="beta_epsilon") double beta_epsilon, @Field(value="objective_epsilon") double objective_epsilon, @Field(value="gradient_epsilon") double gradient_epsilon, @Field(value="obj_reg") double obj_reg, @Field(value="link") GLMLink link, @Field(value="rand_link") GLMLink[] rand_link, @Field(value="startval") double[] startval, @Field(value="random_columns") int[] random_columns, @Field(value="calc_like") boolean calc_like, @Field(value="intercept") boolean intercept, @Field(value="HGLM") boolean HGLM, @Field(value="prior") double prior, @Field(value="lambda_min_ratio") double lambda_min_ratio, @Field(value="beta_constraints") java.lang.String beta_constraints, @Field(value="max_active_predictors") int max_active_predictors, @Field(value="interactions") java.lang.String[] interactions, @Field(value="interaction_pairs") StringPairV3[] interaction_pairs, @Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="compute_p_values") boolean compute_p_values, @Field(value="remove_collinear_columns") boolean remove_collinear_columns, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
seed - Seed for pseudo random number generator (if applicable)family - Family. Use binomial for classification with logistic regression, others are for regression
problems.rand_family - Random Component Family array. One for each random component. Only support gaussian for now.tweedie_variance_power - Tweedie variance powertweedie_link_power - Tweedie link powertheta - Thetasolver - AUTO will set the solver based on given data and the other parameters. IRLSM is fast on on problems
with small number of predictors and for lambda-search with L1 penalty, L_BFGS scales better for
datasets with many columns.alpha - Distribution of regularization between the L1 (Lasso) and L2 (Ridge) penalties. A value of 1 for
alpha represents Lasso regression, a value of 0 produces Ridge regression, and anything in between
specifies the amount of mixing between the two. Default value of alpha is 0 when SOLVER = 'L-BFGS';
0.5 otherwise.lambda - Regularization strengthlambda_search - Use lambda search starting at lambda max, given lambda is then interpreted as lambda minearly_stopping - Stop early when there is no more relative improvement on train or validation (if provided)nlambdas - Number of lambdas to be used in a search. Default indicates: If alpha is zero, with lambda search
set to True, the value of nlamdas is set to 30 (fewer lambdas are needed for ridge regression)
otherwise it is set to 100.standardize - Standardize numeric columns to have zero mean and unit variancemissing_values_handling - Handling of missing values. Either MeanImputation, Skip or PlugValues.plug_values - Plug Values (a single row frame containing values that will be used to impute missing values
of the training/validation frame, use with conjunction missing_values_handling = PlugValues)non_negative - Restrict coefficients (not intercept) to be non-negativemax_iterations - Maximum number of iterationsbeta_epsilon - Converge if beta changes less (using L-infinity norm) than beta esilon, ONLY applies to
IRLSM solverobjective_epsilon - Converge if objective value changes less than this. Default indicates: If lambda_search
is set to True the value of objective_epsilon is set to .0001. If the lambda_search is
set to False and lambda is equal to zero, the value of objective_epsilon is set to
.000001, for any other value of lambda the default value of objective_epsilon is set to
.0001.gradient_epsilon - Converge if objective changes less (using L-infinity norm) than this, ONLY applies to
L-BFGS solver. Default indicates: If lambda_search is set to False and lambda is equal to
zero, the default value of gradient_epsilon is equal to .000001, otherwise the default
value is .0001. If lambda_search is set to True, the conditional values above are 1E-8
and 1E-6 respectively.obj_reg - Likelihood divider in objective value computation, default is 1/nobslink - Link function.rand_link - Link function array for random component in HGLM.startval - double array to initialize fixed and random coefficients for HGLM.random_columns - random columns indices for HGLM.calc_like - if true, will return likelihood function value for HGLM.intercept - Include constant term in the modelHGLM - If set to true, will return HGLM model. Otherwise, normal GLM model will be returnedprior - Prior probability for y==1. To be used only for logistic regression iff the data has been sampled
and the mean of response does not reflect reality.lambda_min_ratio - Minimum lambda used in lambda search, specified as a ratio of lambda_max (the smallest
lambda that drives all coefficients to zero). Default indicates: if the number of
observations is greater than the number of variables, then lambda_min_ratio is set to
0.0001; if the number of observations is less than the number of variables, then
lambda_min_ratio is set to 0.01.beta_constraints - Beta constraintsmax_active_predictors - Maximum number of active predictors during computation. Use as a stopping criterion
to prevent expensive model building with many predictors. Default indicates: If the
IRLSM solver is used, the value of max_active_predictors is set to 5000 otherwise it
is set to 100000000.interactions - A list of predictor column indices to interact. All pairwise combinations will be computed
for the list.interaction_pairs - A list of pairwise (first order) column interactions.balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logsmax_hit_ratio_k - Maximum number (top K) of predictions to use for hit ratio computation (for multi-class
only, 0 to disable)compute_p_values - Request p-values computation, p-values work only with IRLSM solver and no regularizationremove_collinear_columns - In case of linearly dependent columns, remove some of the dependent columnsmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/glm/parameters") retrofit2.Call<GLMV3> validate_parametersGlm()
@FormUrlEncoded @POST(value="/3/ModelBuilders/glrm") retrofit2.Call<GLRMV3> trainGlrm(@Field(value="transform") DataInfoTransformType transform, @Field(value="k") int k, @Field(value="loss") GenmodelalgosglrmGlrmLoss loss, @Field(value="multi_loss") GenmodelalgosglrmGlrmLoss multi_loss, @Field(value="loss_by_col") GenmodelalgosglrmGlrmLoss[] loss_by_col, @Field(value="loss_by_col_idx") int[] loss_by_col_idx, @Field(value="period") int period, @Field(value="regularization_x") GenmodelalgosglrmGlrmRegularizer regularization_x, @Field(value="regularization_y") GenmodelalgosglrmGlrmRegularizer regularization_y, @Field(value="gamma_x") double gamma_x, @Field(value="gamma_y") double gamma_y, @Field(value="max_iterations") int max_iterations, @Field(value="max_updates") int max_updates, @Field(value="init_step_size") double init_step_size, @Field(value="min_step_size") double min_step_size, @Field(value="seed") long seed, @Field(value="init") GenmodelalgosglrmGlrmInitialization init, @Field(value="svd_method") SVDMethod svd_method, @Field(value="user_y") java.lang.String user_y, @Field(value="user_x") java.lang.String user_x, @Field(value="loading_name") java.lang.String loading_name, @Field(value="expand_user_y") boolean expand_user_y, @Field(value="impute_original") boolean impute_original, @Field(value="recover_svd") boolean recover_svd, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
transform - Transformation of training datak - Rank of matrix approximationloss - Numeric loss functionmulti_loss - Categorical loss functionloss_by_col - Loss function by column (override)loss_by_col_idx - Loss function by column index (override)period - Length of period (only used with periodic loss function)regularization_x - Regularization function for X matrixregularization_y - Regularization function for Y matrixgamma_x - Regularization weight on X matrixgamma_y - Regularization weight on Y matrixmax_iterations - Maximum number of iterationsmax_updates - Maximum number of updates, defaults to 2*max_iterationsinit_step_size - Initial step sizemin_step_size - Minimum step sizeseed - RNG seed for initializationinit - Initialization modesvd_method - Method for computing SVD during initialization (Caution: Randomized is currently experimental
and unstable)user_y - User-specified initial Yuser_x - User-specified initial Xloading_name - Frame key to save resulting Xexpand_user_y - Expand categorical columns in user-specified initial Yimpute_original - Reconstruct original training data by reversing transformrecover_svd - Recover singular values and eigenvectors of XYmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/glrm") retrofit2.Call<GLRMV3> trainGlrm(@Field(value="k") int k)
@FormUrlEncoded @POST(value="/3/ModelBuilders/glrm/parameters") retrofit2.Call<GLRMV3> validate_parametersGlrm(@Field(value="transform") DataInfoTransformType transform, @Field(value="k") int k, @Field(value="loss") GenmodelalgosglrmGlrmLoss loss, @Field(value="multi_loss") GenmodelalgosglrmGlrmLoss multi_loss, @Field(value="loss_by_col") GenmodelalgosglrmGlrmLoss[] loss_by_col, @Field(value="loss_by_col_idx") int[] loss_by_col_idx, @Field(value="period") int period, @Field(value="regularization_x") GenmodelalgosglrmGlrmRegularizer regularization_x, @Field(value="regularization_y") GenmodelalgosglrmGlrmRegularizer regularization_y, @Field(value="gamma_x") double gamma_x, @Field(value="gamma_y") double gamma_y, @Field(value="max_iterations") int max_iterations, @Field(value="max_updates") int max_updates, @Field(value="init_step_size") double init_step_size, @Field(value="min_step_size") double min_step_size, @Field(value="seed") long seed, @Field(value="init") GenmodelalgosglrmGlrmInitialization init, @Field(value="svd_method") SVDMethod svd_method, @Field(value="user_y") java.lang.String user_y, @Field(value="user_x") java.lang.String user_x, @Field(value="loading_name") java.lang.String loading_name, @Field(value="expand_user_y") boolean expand_user_y, @Field(value="impute_original") boolean impute_original, @Field(value="recover_svd") boolean recover_svd, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
transform - Transformation of training datak - Rank of matrix approximationloss - Numeric loss functionmulti_loss - Categorical loss functionloss_by_col - Loss function by column (override)loss_by_col_idx - Loss function by column index (override)period - Length of period (only used with periodic loss function)regularization_x - Regularization function for X matrixregularization_y - Regularization function for Y matrixgamma_x - Regularization weight on X matrixgamma_y - Regularization weight on Y matrixmax_iterations - Maximum number of iterationsmax_updates - Maximum number of updates, defaults to 2*max_iterationsinit_step_size - Initial step sizemin_step_size - Minimum step sizeseed - RNG seed for initializationinit - Initialization modesvd_method - Method for computing SVD during initialization (Caution: Randomized is currently experimental
and unstable)user_y - User-specified initial Yuser_x - User-specified initial Xloading_name - Frame key to save resulting Xexpand_user_y - Expand categorical columns in user-specified initial Yimpute_original - Reconstruct original training data by reversing transformrecover_svd - Recover singular values and eigenvectors of XYmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/glrm/parameters") retrofit2.Call<GLRMV3> validate_parametersGlrm(@Field(value="k") int k)
@FormUrlEncoded @POST(value="/3/ModelBuilders/kmeans") retrofit2.Call<KMeansV3> trainKmeans(@Field(value="user_points") java.lang.String user_points, @Field(value="max_iterations") int max_iterations, @Field(value="standardize") boolean standardize, @Field(value="seed") long seed, @Field(value="init") KMeansInitialization init, @Field(value="estimate_k") boolean estimate_k, @Field(value="cluster_size_constraints") int[] cluster_size_constraints, @Field(value="k") int k, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
user_points - This option allows you to specify a dataframe, where each row represents an initial cluster
center. The user-specified points must have the same number of columns as the training
observations. The number of rows must equal the number of clustersmax_iterations - Maximum training iterations (if estimate_k is enabled, then this is for each inner Lloyds
iteration)standardize - Standardize columns before computing distancesseed - RNG Seedinit - Initialization modeestimate_k - Whether to estimate the number of clusters (<=k) iteratively and deterministically.cluster_size_constraints - An array specifying the minimum number of points that should be in each cluster.
The length of the constraints array has to be the same as the number of clusters.k - The max. number of clusters. If estimate_k is disabled, the model will find k centroids, otherwise it
will find up to k centroids.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/kmeans") retrofit2.Call<KMeansV3> trainKmeans()
@FormUrlEncoded @POST(value="/3/ModelBuilders/kmeans/parameters") retrofit2.Call<KMeansV3> validate_parametersKmeans(@Field(value="user_points") java.lang.String user_points, @Field(value="max_iterations") int max_iterations, @Field(value="standardize") boolean standardize, @Field(value="seed") long seed, @Field(value="init") KMeansInitialization init, @Field(value="estimate_k") boolean estimate_k, @Field(value="cluster_size_constraints") int[] cluster_size_constraints, @Field(value="k") int k, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
user_points - This option allows you to specify a dataframe, where each row represents an initial cluster
center. The user-specified points must have the same number of columns as the training
observations. The number of rows must equal the number of clustersmax_iterations - Maximum training iterations (if estimate_k is enabled, then this is for each inner Lloyds
iteration)standardize - Standardize columns before computing distancesseed - RNG Seedinit - Initialization modeestimate_k - Whether to estimate the number of clusters (<=k) iteratively and deterministically.cluster_size_constraints - An array specifying the minimum number of points that should be in each cluster.
The length of the constraints array has to be the same as the number of clusters.k - The max. number of clusters. If estimate_k is disabled, the model will find k centroids, otherwise it
will find up to k centroids.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/kmeans/parameters") retrofit2.Call<KMeansV3> validate_parametersKmeans()
@FormUrlEncoded @POST(value="/3/ModelBuilders/naivebayes") retrofit2.Call<NaiveBayesV3> trainNaivebayes(@Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="laplace") double laplace, @Field(value="min_sdev") double min_sdev, @Field(value="eps_sdev") double eps_sdev, @Field(value="min_prob") double min_prob, @Field(value="eps_prob") double eps_prob, @Field(value="compute_metrics") boolean compute_metrics, @Field(value="seed") long seed, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logsmax_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable)laplace - Laplace smoothing parametermin_sdev - Min. standard deviation to use for observations with not enough dataeps_sdev - Cutoff below which standard deviation is replaced with min_sdevmin_prob - Min. probability to use for observations with not enough dataeps_prob - Cutoff below which probability is replaced with min_probcompute_metrics - Compute metrics on training dataseed - Seed for pseudo random number generator (only used for cross-validation and fold_assignment="Random"
or "AUTO")model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/naivebayes") retrofit2.Call<NaiveBayesV3> trainNaivebayes()
@FormUrlEncoded @POST(value="/3/ModelBuilders/naivebayes/parameters") retrofit2.Call<NaiveBayesV3> validate_parametersNaivebayes(@Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="laplace") double laplace, @Field(value="min_sdev") double min_sdev, @Field(value="eps_sdev") double eps_sdev, @Field(value="min_prob") double min_prob, @Field(value="eps_prob") double eps_prob, @Field(value="compute_metrics") boolean compute_metrics, @Field(value="seed") long seed, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logsmax_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable)laplace - Laplace smoothing parametermin_sdev - Min. standard deviation to use for observations with not enough dataeps_sdev - Cutoff below which standard deviation is replaced with min_sdevmin_prob - Min. probability to use for observations with not enough dataeps_prob - Cutoff below which probability is replaced with min_probcompute_metrics - Compute metrics on training dataseed - Seed for pseudo random number generator (only used for cross-validation and fold_assignment="Random"
or "AUTO")model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/naivebayes/parameters") retrofit2.Call<NaiveBayesV3> validate_parametersNaivebayes()
@FormUrlEncoded @POST(value="/3/ModelBuilders/pca") retrofit2.Call<PCAV3> trainPca(@Field(value="transform") DataInfoTransformType transform, @Field(value="pca_method") PCAMethod pca_method, @Field(value="pca_impl") PCAImplementation pca_impl, @Field(value="k") int k, @Field(value="max_iterations") int max_iterations, @Field(value="seed") long seed, @Field(value="use_all_factor_levels") boolean use_all_factor_levels, @Field(value="compute_metrics") boolean compute_metrics, @Field(value="impute_missing") boolean impute_missing, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
transform - Transformation of training datapca_method - Specify the algorithm to use for computing the principal components: GramSVD - uses a
distributed computation of the Gram matrix, followed by a local SVD; Power - computes the SVD
using the power iteration method (experimental); Randomized - uses randomized subspace
iteration method; GLRM - fits a generalized low-rank model with L2 loss function and no
regularization and solves for the SVD using local matrix algebra (experimental)pca_impl - Specify the implementation to use for computing PCA (via SVD or EVD): MTJ_EVD_DENSEMATRIX -
eigenvalue decompositions for dense matrix using MTJ; MTJ_EVD_SYMMMATRIX - eigenvalue
decompositions for symmetric matrix using MTJ; MTJ_SVD_DENSEMATRIX - singular-value
decompositions for dense matrix using MTJ; JAMA - eigenvalue decompositions for dense matrix
using JAMA. References: JAMA - http://math.nist.gov/javanumerics/jama/; MTJ -
https://github.com/fommil/matrix-toolkits-java/k - Rank of matrix approximationmax_iterations - Maximum training iterationsseed - RNG seed for initializationuse_all_factor_levels - Whether first factor level is included in each categorical expansioncompute_metrics - Whether to compute metrics on the training dataimpute_missing - Whether to impute missing entries with the column meanmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/pca") retrofit2.Call<PCAV3> trainPca(@Field(value="k") int k)
@FormUrlEncoded @POST(value="/3/ModelBuilders/pca/parameters") retrofit2.Call<PCAV3> validate_parametersPca(@Field(value="transform") DataInfoTransformType transform, @Field(value="pca_method") PCAMethod pca_method, @Field(value="pca_impl") PCAImplementation pca_impl, @Field(value="k") int k, @Field(value="max_iterations") int max_iterations, @Field(value="seed") long seed, @Field(value="use_all_factor_levels") boolean use_all_factor_levels, @Field(value="compute_metrics") boolean compute_metrics, @Field(value="impute_missing") boolean impute_missing, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
transform - Transformation of training datapca_method - Specify the algorithm to use for computing the principal components: GramSVD - uses a
distributed computation of the Gram matrix, followed by a local SVD; Power - computes the SVD
using the power iteration method (experimental); Randomized - uses randomized subspace
iteration method; GLRM - fits a generalized low-rank model with L2 loss function and no
regularization and solves for the SVD using local matrix algebra (experimental)pca_impl - Specify the implementation to use for computing PCA (via SVD or EVD): MTJ_EVD_DENSEMATRIX -
eigenvalue decompositions for dense matrix using MTJ; MTJ_EVD_SYMMMATRIX - eigenvalue
decompositions for symmetric matrix using MTJ; MTJ_SVD_DENSEMATRIX - singular-value
decompositions for dense matrix using MTJ; JAMA - eigenvalue decompositions for dense matrix
using JAMA. References: JAMA - http://math.nist.gov/javanumerics/jama/; MTJ -
https://github.com/fommil/matrix-toolkits-java/k - Rank of matrix approximationmax_iterations - Maximum training iterationsseed - RNG seed for initializationuse_all_factor_levels - Whether first factor level is included in each categorical expansioncompute_metrics - Whether to compute metrics on the training dataimpute_missing - Whether to impute missing entries with the column meanmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/pca/parameters") retrofit2.Call<PCAV3> validate_parametersPca(@Field(value="k") int k)
@FormUrlEncoded @POST(value="/99/ModelBuilders/svd") retrofit2.Call<SVDV99> trainSvd(@Field(value="transform") DataInfoTransformType transform, @Field(value="svd_method") SVDMethod svd_method, @Field(value="nv") int nv, @Field(value="max_iterations") int max_iterations, @Field(value="seed") long seed, @Field(value="keep_u") boolean keep_u, @Field(value="u_name") java.lang.String u_name, @Field(value="use_all_factor_levels") boolean use_all_factor_levels, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
transform - Transformation of training datasvd_method - Method for computing SVD (Caution: Randomized is currently experimental and unstable)nv - Number of right singular vectorsmax_iterations - Maximum iterationsseed - RNG seed for k-means++ initializationkeep_u - Save left singular vectors?u_name - Frame key to save left singular vectorsuse_all_factor_levels - Whether first factor level is included in each categorical expansionmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/99/ModelBuilders/svd") retrofit2.Call<SVDV99> trainSvd()
@FormUrlEncoded @POST(value="/99/ModelBuilders/svd/parameters") retrofit2.Call<SVDV99> validate_parametersSvd(@Field(value="transform") DataInfoTransformType transform, @Field(value="svd_method") SVDMethod svd_method, @Field(value="nv") int nv, @Field(value="max_iterations") int max_iterations, @Field(value="seed") long seed, @Field(value="keep_u") boolean keep_u, @Field(value="u_name") java.lang.String u_name, @Field(value="use_all_factor_levels") boolean use_all_factor_levels, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
transform - Transformation of training datasvd_method - Method for computing SVD (Caution: Randomized is currently experimental and unstable)nv - Number of right singular vectorsmax_iterations - Maximum iterationsseed - RNG seed for k-means++ initializationkeep_u - Save left singular vectors?u_name - Frame key to save left singular vectorsuse_all_factor_levels - Whether first factor level is included in each categorical expansionmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/99/ModelBuilders/svd/parameters") retrofit2.Call<SVDV99> validate_parametersSvd()
@FormUrlEncoded @POST(value="/3/ModelBuilders/drf") retrofit2.Call<DRFV3> trainDrf(@Field(value="mtries") int mtries, @Field(value="binomial_double_trees") boolean binomial_double_trees, @Field(value="sample_rate") double sample_rate, @Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="ntrees") int ntrees, @Field(value="max_depth") int max_depth, @Field(value="min_rows") double min_rows, @Field(value="nbins") int nbins, @Field(value="nbins_top_level") int nbins_top_level, @Field(value="nbins_cats") int nbins_cats, @Field(value="r2_stopping") double r2_stopping, @Field(value="seed") long seed, @Field(value="build_tree_one_node") boolean build_tree_one_node, @Field(value="sample_rate_per_class") double[] sample_rate_per_class, @Field(value="col_sample_rate_per_tree") double col_sample_rate_per_tree, @Field(value="col_sample_rate_change_per_level") double col_sample_rate_change_per_level, @Field(value="score_tree_interval") int score_tree_interval, @Field(value="min_split_improvement") double min_split_improvement, @Field(value="histogram_type") TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type, @Field(value="calibrate_model") boolean calibrate_model, @Field(value="calibration_frame") java.lang.String calibration_frame, @Field(value="check_constant_response") boolean check_constant_response, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
mtries - Number of variables randomly sampled as candidates at each split. If set to -1, defaults to sqrt{p}
for classification and p/3 for regression (where p is the # of predictorsbinomial_double_trees - For binary classification: Build 2x as many trees (one per class) - can lead to
higher accuracy.sample_rate - Row sample rate per tree (from 0.0 to 1.0)balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logsmax_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable)ntrees - Number of trees.max_depth - Maximum tree depth.min_rows - Fewest allowed (weighted) observations in a leaf.nbins - For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the
best pointnbins_top_level - For numerical columns (real/int), build a histogram of (at most) this many bins at the
root level, then decrease by factor of two per levelnbins_cats - For categorical columns (factors), build a histogram of this many bins, then split at the best
point. Higher values can lead to more overfitting.r2_stopping - r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds,
stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making
trees when the R^2 metric equals or exceeds thisseed - Seed for pseudo random number generator (if applicable)build_tree_one_node - Run on one node only; no network overhead but fewer cpus used. Suitable for small
datasets.sample_rate_per_class - A list of row sample rates per class (relative fraction for each class, from 0.0 to
1.0), for each treecol_sample_rate_per_tree - Column sample rate per tree (from 0.0 to 1.0)col_sample_rate_change_per_level - Relative change of the column sampling rate for every level (must be >
0.0 and <= 2.0)score_tree_interval - Score the model after every so many trees. Disabled if set to 0.min_split_improvement - Minimum relative improvement in squared error reduction for a split to happenhistogram_type - What type of histogram to use for finding optimal split pointscalibrate_model - Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide
more accurate estimates of class probabilities.calibration_frame - Calibration frame for Platt Scalingcheck_constant_response - Check if response column is constant. If enabled, then an exception is thrown if
the response column is a constant value.If disabled, then model will train
regardless of the response column being a constant value or not.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/drf") retrofit2.Call<DRFV3> trainDrf()
@FormUrlEncoded @POST(value="/3/ModelBuilders/drf/parameters") retrofit2.Call<DRFV3> validate_parametersDrf(@Field(value="mtries") int mtries, @Field(value="binomial_double_trees") boolean binomial_double_trees, @Field(value="sample_rate") double sample_rate, @Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="ntrees") int ntrees, @Field(value="max_depth") int max_depth, @Field(value="min_rows") double min_rows, @Field(value="nbins") int nbins, @Field(value="nbins_top_level") int nbins_top_level, @Field(value="nbins_cats") int nbins_cats, @Field(value="r2_stopping") double r2_stopping, @Field(value="seed") long seed, @Field(value="build_tree_one_node") boolean build_tree_one_node, @Field(value="sample_rate_per_class") double[] sample_rate_per_class, @Field(value="col_sample_rate_per_tree") double col_sample_rate_per_tree, @Field(value="col_sample_rate_change_per_level") double col_sample_rate_change_per_level, @Field(value="score_tree_interval") int score_tree_interval, @Field(value="min_split_improvement") double min_split_improvement, @Field(value="histogram_type") TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type, @Field(value="calibrate_model") boolean calibrate_model, @Field(value="calibration_frame") java.lang.String calibration_frame, @Field(value="check_constant_response") boolean check_constant_response, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
mtries - Number of variables randomly sampled as candidates at each split. If set to -1, defaults to sqrt{p}
for classification and p/3 for regression (where p is the # of predictorsbinomial_double_trees - For binary classification: Build 2x as many trees (one per class) - can lead to
higher accuracy.sample_rate - Row sample rate per tree (from 0.0 to 1.0)balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logsmax_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable)ntrees - Number of trees.max_depth - Maximum tree depth.min_rows - Fewest allowed (weighted) observations in a leaf.nbins - For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the
best pointnbins_top_level - For numerical columns (real/int), build a histogram of (at most) this many bins at the
root level, then decrease by factor of two per levelnbins_cats - For categorical columns (factors), build a histogram of this many bins, then split at the best
point. Higher values can lead to more overfitting.r2_stopping - r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds,
stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making
trees when the R^2 metric equals or exceeds thisseed - Seed for pseudo random number generator (if applicable)build_tree_one_node - Run on one node only; no network overhead but fewer cpus used. Suitable for small
datasets.sample_rate_per_class - A list of row sample rates per class (relative fraction for each class, from 0.0 to
1.0), for each treecol_sample_rate_per_tree - Column sample rate per tree (from 0.0 to 1.0)col_sample_rate_change_per_level - Relative change of the column sampling rate for every level (must be >
0.0 and <= 2.0)score_tree_interval - Score the model after every so many trees. Disabled if set to 0.min_split_improvement - Minimum relative improvement in squared error reduction for a split to happenhistogram_type - What type of histogram to use for finding optimal split pointscalibrate_model - Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide
more accurate estimates of class probabilities.calibration_frame - Calibration frame for Platt Scalingcheck_constant_response - Check if response column is constant. If enabled, then an exception is thrown if
the response column is a constant value.If disabled, then model will train
regardless of the response column being a constant value or not.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/drf/parameters") retrofit2.Call<DRFV3> validate_parametersDrf()
@FormUrlEncoded @POST(value="/3/ModelBuilders/gbm") retrofit2.Call<GBMV3> trainGbm(@Field(value="learn_rate") double learn_rate, @Field(value="learn_rate_annealing") double learn_rate_annealing, @Field(value="sample_rate") double sample_rate, @Field(value="col_sample_rate") double col_sample_rate, @Field(value="monotone_constraints") KeyValueV3[] monotone_constraints, @Field(value="max_abs_leafnode_pred") double max_abs_leafnode_pred, @Field(value="pred_noise_bandwidth") double pred_noise_bandwidth, @Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="ntrees") int ntrees, @Field(value="max_depth") int max_depth, @Field(value="min_rows") double min_rows, @Field(value="nbins") int nbins, @Field(value="nbins_top_level") int nbins_top_level, @Field(value="nbins_cats") int nbins_cats, @Field(value="r2_stopping") double r2_stopping, @Field(value="seed") long seed, @Field(value="build_tree_one_node") boolean build_tree_one_node, @Field(value="sample_rate_per_class") double[] sample_rate_per_class, @Field(value="col_sample_rate_per_tree") double col_sample_rate_per_tree, @Field(value="col_sample_rate_change_per_level") double col_sample_rate_change_per_level, @Field(value="score_tree_interval") int score_tree_interval, @Field(value="min_split_improvement") double min_split_improvement, @Field(value="histogram_type") TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type, @Field(value="calibrate_model") boolean calibrate_model, @Field(value="calibration_frame") java.lang.String calibration_frame, @Field(value="check_constant_response") boolean check_constant_response, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
learn_rate - Learning rate (from 0.0 to 1.0)learn_rate_annealing - Scale the learning rate by this factor after each tree (e.g., 0.99 or 0.999)sample_rate - Row sample rate per tree (from 0.0 to 1.0)col_sample_rate - Column sample rate (from 0.0 to 1.0)monotone_constraints - A mapping representing monotonic constraints. Use +1 to enforce an increasing
constraint and -1 to specify a decreasing constraint.max_abs_leafnode_pred - Maximum absolute value of a leaf node predictionpred_noise_bandwidth - Bandwidth (sigma) of Gaussian multiplicative noise ~N(1,sigma) for tree node
predictionsbalance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logsmax_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable)ntrees - Number of trees.max_depth - Maximum tree depth.min_rows - Fewest allowed (weighted) observations in a leaf.nbins - For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the
best pointnbins_top_level - For numerical columns (real/int), build a histogram of (at most) this many bins at the
root level, then decrease by factor of two per levelnbins_cats - For categorical columns (factors), build a histogram of this many bins, then split at the best
point. Higher values can lead to more overfitting.r2_stopping - r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds,
stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making
trees when the R^2 metric equals or exceeds thisseed - Seed for pseudo random number generator (if applicable)build_tree_one_node - Run on one node only; no network overhead but fewer cpus used. Suitable for small
datasets.sample_rate_per_class - A list of row sample rates per class (relative fraction for each class, from 0.0 to
1.0), for each treecol_sample_rate_per_tree - Column sample rate per tree (from 0.0 to 1.0)col_sample_rate_change_per_level - Relative change of the column sampling rate for every level (must be >
0.0 and <= 2.0)score_tree_interval - Score the model after every so many trees. Disabled if set to 0.min_split_improvement - Minimum relative improvement in squared error reduction for a split to happenhistogram_type - What type of histogram to use for finding optimal split pointscalibrate_model - Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide
more accurate estimates of class probabilities.calibration_frame - Calibration frame for Platt Scalingcheck_constant_response - Check if response column is constant. If enabled, then an exception is thrown if
the response column is a constant value.If disabled, then model will train
regardless of the response column being a constant value or not.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/gbm") retrofit2.Call<GBMV3> trainGbm()
@FormUrlEncoded @POST(value="/3/ModelBuilders/gbm/parameters") retrofit2.Call<GBMV3> validate_parametersGbm(@Field(value="learn_rate") double learn_rate, @Field(value="learn_rate_annealing") double learn_rate_annealing, @Field(value="sample_rate") double sample_rate, @Field(value="col_sample_rate") double col_sample_rate, @Field(value="monotone_constraints") KeyValueV3[] monotone_constraints, @Field(value="max_abs_leafnode_pred") double max_abs_leafnode_pred, @Field(value="pred_noise_bandwidth") double pred_noise_bandwidth, @Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="ntrees") int ntrees, @Field(value="max_depth") int max_depth, @Field(value="min_rows") double min_rows, @Field(value="nbins") int nbins, @Field(value="nbins_top_level") int nbins_top_level, @Field(value="nbins_cats") int nbins_cats, @Field(value="r2_stopping") double r2_stopping, @Field(value="seed") long seed, @Field(value="build_tree_one_node") boolean build_tree_one_node, @Field(value="sample_rate_per_class") double[] sample_rate_per_class, @Field(value="col_sample_rate_per_tree") double col_sample_rate_per_tree, @Field(value="col_sample_rate_change_per_level") double col_sample_rate_change_per_level, @Field(value="score_tree_interval") int score_tree_interval, @Field(value="min_split_improvement") double min_split_improvement, @Field(value="histogram_type") TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type, @Field(value="calibrate_model") boolean calibrate_model, @Field(value="calibration_frame") java.lang.String calibration_frame, @Field(value="check_constant_response") boolean check_constant_response, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
learn_rate - Learning rate (from 0.0 to 1.0)learn_rate_annealing - Scale the learning rate by this factor after each tree (e.g., 0.99 or 0.999)sample_rate - Row sample rate per tree (from 0.0 to 1.0)col_sample_rate - Column sample rate (from 0.0 to 1.0)monotone_constraints - A mapping representing monotonic constraints. Use +1 to enforce an increasing
constraint and -1 to specify a decreasing constraint.max_abs_leafnode_pred - Maximum absolute value of a leaf node predictionpred_noise_bandwidth - Bandwidth (sigma) of Gaussian multiplicative noise ~N(1,sigma) for tree node
predictionsbalance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logsmax_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable)ntrees - Number of trees.max_depth - Maximum tree depth.min_rows - Fewest allowed (weighted) observations in a leaf.nbins - For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the
best pointnbins_top_level - For numerical columns (real/int), build a histogram of (at most) this many bins at the
root level, then decrease by factor of two per levelnbins_cats - For categorical columns (factors), build a histogram of this many bins, then split at the best
point. Higher values can lead to more overfitting.r2_stopping - r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds,
stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making
trees when the R^2 metric equals or exceeds thisseed - Seed for pseudo random number generator (if applicable)build_tree_one_node - Run on one node only; no network overhead but fewer cpus used. Suitable for small
datasets.sample_rate_per_class - A list of row sample rates per class (relative fraction for each class, from 0.0 to
1.0), for each treecol_sample_rate_per_tree - Column sample rate per tree (from 0.0 to 1.0)col_sample_rate_change_per_level - Relative change of the column sampling rate for every level (must be >
0.0 and <= 2.0)score_tree_interval - Score the model after every so many trees. Disabled if set to 0.min_split_improvement - Minimum relative improvement in squared error reduction for a split to happenhistogram_type - What type of histogram to use for finding optimal split pointscalibrate_model - Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide
more accurate estimates of class probabilities.calibration_frame - Calibration frame for Platt Scalingcheck_constant_response - Check if response column is constant. If enabled, then an exception is thrown if
the response column is a constant value.If disabled, then model will train
regardless of the response column being a constant value or not.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/gbm/parameters") retrofit2.Call<GBMV3> validate_parametersGbm()
@FormUrlEncoded @POST(value="/3/ModelBuilders/isolationforest") retrofit2.Call<IsolationForestV3> trainIsolationforest(@Field(value="sample_size") long sample_size, @Field(value="sample_rate") double sample_rate, @Field(value="mtries") int mtries, @Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="ntrees") int ntrees, @Field(value="max_depth") int max_depth, @Field(value="min_rows") double min_rows, @Field(value="nbins") int nbins, @Field(value="nbins_top_level") int nbins_top_level, @Field(value="nbins_cats") int nbins_cats, @Field(value="r2_stopping") double r2_stopping, @Field(value="seed") long seed, @Field(value="build_tree_one_node") boolean build_tree_one_node, @Field(value="sample_rate_per_class") double[] sample_rate_per_class, @Field(value="col_sample_rate_per_tree") double col_sample_rate_per_tree, @Field(value="col_sample_rate_change_per_level") double col_sample_rate_change_per_level, @Field(value="score_tree_interval") int score_tree_interval, @Field(value="min_split_improvement") double min_split_improvement, @Field(value="histogram_type") TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type, @Field(value="calibrate_model") boolean calibrate_model, @Field(value="calibration_frame") java.lang.String calibration_frame, @Field(value="check_constant_response") boolean check_constant_response, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
sample_size - Number of randomly sampled observations used to train each Isolation Forest tree. Only one of
parameters sample_size and sample_rate should be defined. If sample_rate is defined,
sample_size will be ignored.sample_rate - Rate of randomly sampled observations used to train each Isolation Forest tree. Needs to be in
range from 0.0 to 1.0. If set to -1, sample_rate is disabled and sample_size will be used
instead.mtries - Number of variables randomly sampled as candidates at each split. If set to -1, defaults (number of
predictors)/3.balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logsmax_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable)ntrees - Number of trees.max_depth - Maximum tree depth.min_rows - Fewest allowed (weighted) observations in a leaf.nbins - For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the
best pointnbins_top_level - For numerical columns (real/int), build a histogram of (at most) this many bins at the
root level, then decrease by factor of two per levelnbins_cats - For categorical columns (factors), build a histogram of this many bins, then split at the best
point. Higher values can lead to more overfitting.r2_stopping - r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds,
stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making
trees when the R^2 metric equals or exceeds thisseed - Seed for pseudo random number generator (if applicable)build_tree_one_node - Run on one node only; no network overhead but fewer cpus used. Suitable for small
datasets.sample_rate_per_class - A list of row sample rates per class (relative fraction for each class, from 0.0 to
1.0), for each treecol_sample_rate_per_tree - Column sample rate per tree (from 0.0 to 1.0)col_sample_rate_change_per_level - Relative change of the column sampling rate for every level (must be >
0.0 and <= 2.0)score_tree_interval - Score the model after every so many trees. Disabled if set to 0.min_split_improvement - Minimum relative improvement in squared error reduction for a split to happenhistogram_type - What type of histogram to use for finding optimal split pointscalibrate_model - Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide
more accurate estimates of class probabilities.calibration_frame - Calibration frame for Platt Scalingcheck_constant_response - Check if response column is constant. If enabled, then an exception is thrown if
the response column is a constant value.If disabled, then model will train
regardless of the response column being a constant value or not.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/isolationforest") retrofit2.Call<IsolationForestV3> trainIsolationforest()
@FormUrlEncoded @POST(value="/3/ModelBuilders/isolationforest/parameters") retrofit2.Call<IsolationForestV3> validate_parametersIsolationforest(@Field(value="sample_size") long sample_size, @Field(value="sample_rate") double sample_rate, @Field(value="mtries") int mtries, @Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="ntrees") int ntrees, @Field(value="max_depth") int max_depth, @Field(value="min_rows") double min_rows, @Field(value="nbins") int nbins, @Field(value="nbins_top_level") int nbins_top_level, @Field(value="nbins_cats") int nbins_cats, @Field(value="r2_stopping") double r2_stopping, @Field(value="seed") long seed, @Field(value="build_tree_one_node") boolean build_tree_one_node, @Field(value="sample_rate_per_class") double[] sample_rate_per_class, @Field(value="col_sample_rate_per_tree") double col_sample_rate_per_tree, @Field(value="col_sample_rate_change_per_level") double col_sample_rate_change_per_level, @Field(value="score_tree_interval") int score_tree_interval, @Field(value="min_split_improvement") double min_split_improvement, @Field(value="histogram_type") TreeSharedTreeModelSharedTreeParametersHistogramType histogram_type, @Field(value="calibrate_model") boolean calibrate_model, @Field(value="calibration_frame") java.lang.String calibration_frame, @Field(value="check_constant_response") boolean check_constant_response, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
sample_size - Number of randomly sampled observations used to train each Isolation Forest tree. Only one of
parameters sample_size and sample_rate should be defined. If sample_rate is defined,
sample_size will be ignored.sample_rate - Rate of randomly sampled observations used to train each Isolation Forest tree. Needs to be in
range from 0.0 to 1.0. If set to -1, sample_rate is disabled and sample_size will be used
instead.mtries - Number of variables randomly sampled as candidates at each split. If set to -1, defaults (number of
predictors)/3.balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logsmax_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable)ntrees - Number of trees.max_depth - Maximum tree depth.min_rows - Fewest allowed (weighted) observations in a leaf.nbins - For numerical columns (real/int), build a histogram of (at least) this many bins, then split at the
best pointnbins_top_level - For numerical columns (real/int), build a histogram of (at most) this many bins at the
root level, then decrease by factor of two per levelnbins_cats - For categorical columns (factors), build a histogram of this many bins, then split at the best
point. Higher values can lead to more overfitting.r2_stopping - r2_stopping is no longer supported and will be ignored if set - please use stopping_rounds,
stopping_metric and stopping_tolerance instead. Previous version of H2O would stop making
trees when the R^2 metric equals or exceeds thisseed - Seed for pseudo random number generator (if applicable)build_tree_one_node - Run on one node only; no network overhead but fewer cpus used. Suitable for small
datasets.sample_rate_per_class - A list of row sample rates per class (relative fraction for each class, from 0.0 to
1.0), for each treecol_sample_rate_per_tree - Column sample rate per tree (from 0.0 to 1.0)col_sample_rate_change_per_level - Relative change of the column sampling rate for every level (must be >
0.0 and <= 2.0)score_tree_interval - Score the model after every so many trees. Disabled if set to 0.min_split_improvement - Minimum relative improvement in squared error reduction for a split to happenhistogram_type - What type of histogram to use for finding optimal split pointscalibrate_model - Use Platt Scaling to calculate calibrated class probabilities. Calibration can provide
more accurate estimates of class probabilities.calibration_frame - Calibration frame for Platt Scalingcheck_constant_response - Check if response column is constant. If enabled, then an exception is thrown if
the response column is a constant value.If disabled, then model will train
regardless of the response column being a constant value or not.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/isolationforest/parameters") retrofit2.Call<IsolationForestV3> validate_parametersIsolationforest()
@FormUrlEncoded @POST(value="/99/ModelBuilders/aggregator") retrofit2.Call<AggregatorV99> trainAggregator(@Field(value="transform") DataInfoTransformType transform, @Field(value="pca_method") PCAMethod pca_method, @Field(value="k") int k, @Field(value="max_iterations") int max_iterations, @Field(value="target_num_exemplars") int target_num_exemplars, @Field(value="rel_tol_num_exemplars") double rel_tol_num_exemplars, @Field(value="seed") long seed, @Field(value="use_all_factor_levels") boolean use_all_factor_levels, @Field(value="save_mapping_frame") boolean save_mapping_frame, @Field(value="num_iteration_without_new_exemplar") int num_iteration_without_new_exemplar, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
transform - Transformation of training datapca_method - Method for computing PCA (Caution: GLRM is currently experimental and unstable)k - Rank of matrix approximationmax_iterations - Maximum number of iterations for PCAtarget_num_exemplars - Targeted number of exemplarsrel_tol_num_exemplars - Relative tolerance for number of exemplars (e.g, 0.5 is +/- 50 percents)seed - RNG seed for initializationuse_all_factor_levels - Whether first factor level is included in each categorical expansionsave_mapping_frame - Whether to export the mapping of the aggregated framenum_iteration_without_new_exemplar - The number of iterations to run before aggregator exits if the number
of exemplars collected didn't changemodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/99/ModelBuilders/aggregator") retrofit2.Call<AggregatorV99> trainAggregator()
@FormUrlEncoded @POST(value="/99/ModelBuilders/aggregator/parameters") retrofit2.Call<AggregatorV99> validate_parametersAggregator(@Field(value="transform") DataInfoTransformType transform, @Field(value="pca_method") PCAMethod pca_method, @Field(value="k") int k, @Field(value="max_iterations") int max_iterations, @Field(value="target_num_exemplars") int target_num_exemplars, @Field(value="rel_tol_num_exemplars") double rel_tol_num_exemplars, @Field(value="seed") long seed, @Field(value="use_all_factor_levels") boolean use_all_factor_levels, @Field(value="save_mapping_frame") boolean save_mapping_frame, @Field(value="num_iteration_without_new_exemplar") int num_iteration_without_new_exemplar, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
transform - Transformation of training datapca_method - Method for computing PCA (Caution: GLRM is currently experimental and unstable)k - Rank of matrix approximationmax_iterations - Maximum number of iterations for PCAtarget_num_exemplars - Targeted number of exemplarsrel_tol_num_exemplars - Relative tolerance for number of exemplars (e.g, 0.5 is +/- 50 percents)seed - RNG seed for initializationuse_all_factor_levels - Whether first factor level is included in each categorical expansionsave_mapping_frame - Whether to export the mapping of the aggregated framenum_iteration_without_new_exemplar - The number of iterations to run before aggregator exits if the number
of exemplars collected didn't changemodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/99/ModelBuilders/aggregator/parameters") retrofit2.Call<AggregatorV99> validate_parametersAggregator()
@FormUrlEncoded @POST(value="/3/ModelBuilders/deepwater") retrofit2.Call<DeepWaterV3> trainDeepwater(@Field(value="problem_type") DeepWaterParametersProblemType problem_type, @Field(value="activation") DeepWaterParametersActivation activation, @Field(value="hidden") int[] hidden, @Field(value="input_dropout_ratio") double input_dropout_ratio, @Field(value="hidden_dropout_ratios") double[] hidden_dropout_ratios, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="sparse") boolean sparse, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="epochs") double epochs, @Field(value="train_samples_per_iteration") long train_samples_per_iteration, @Field(value="target_ratio_comm_to_comp") double target_ratio_comm_to_comp, @Field(value="seed") long seed, @Field(value="learning_rate") double learning_rate, @Field(value="learning_rate_annealing") double learning_rate_annealing, @Field(value="momentum_start") double momentum_start, @Field(value="momentum_ramp") double momentum_ramp, @Field(value="momentum_stable") double momentum_stable, @Field(value="score_interval") double score_interval, @Field(value="score_training_samples") long score_training_samples, @Field(value="score_validation_samples") long score_validation_samples, @Field(value="score_duty_cycle") double score_duty_cycle, @Field(value="classification_stop") double classification_stop, @Field(value="regression_stop") double regression_stop, @Field(value="quiet_mode") boolean quiet_mode, @Field(value="overwrite_with_best_model") boolean overwrite_with_best_model, @Field(value="autoencoder") boolean autoencoder, @Field(value="diagnostics") boolean diagnostics, @Field(value="variable_importances") boolean variable_importances, @Field(value="replicate_training_data") boolean replicate_training_data, @Field(value="single_node_mode") boolean single_node_mode, @Field(value="shuffle_training_data") boolean shuffle_training_data, @Field(value="mini_batch_size") int mini_batch_size, @Field(value="clip_gradient") double clip_gradient, @Field(value="network") DeepWaterParametersNetwork network, @Field(value="backend") DeepWaterParametersBackend backend, @Field(value="image_shape") int[] image_shape, @Field(value="channels") int channels, @Field(value="gpu") boolean gpu, @Field(value="device_id") int[] device_id, @Field(value="cache_data") boolean cache_data, @Field(value="network_definition_file") java.lang.String network_definition_file, @Field(value="network_parameters_file") java.lang.String network_parameters_file, @Field(value="mean_image_file") java.lang.String mean_image_file, @Field(value="export_native_parameters_prefix") java.lang.String export_native_parameters_prefix, @Field(value="standardize") boolean standardize, @Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
problem_type - Problem type, auto-detected by default. If set to image, the H2OFrame must contain a string
column containing the path (URI or URL) to the images in the first column. If set to text,
the H2OFrame must contain a string column containing the text in the first column. If set to
dataset, Deep Water behaves just like any other H2O Model and builds a model on the provided
H2OFrame (non-String columns).activation - Activation function. Only used if no user-defined network architecture file is provided, and
only for problem_type=dataset.hidden - Hidden layer sizes (e.g. [200, 200]). Only used if no user-defined network architecture file is
provided, and only for problem_type=dataset.input_dropout_ratio - Input layer dropout ratio (can improve generalization, try 0.1 or 0.2).hidden_dropout_ratios - Hidden layer dropout ratios (can improve generalization), specify one value per
hidden layer, defaults to 0.5.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logs.sparse - Sparse data handling (more efficient for data with lots of 0 values).max_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable).epochs - How many times the dataset should be iterated (streamed), can be fractional.train_samples_per_iteration - Number of training samples (globally) per MapReduce iteration. Special values
are 0: one epoch, -1: all available data (e.g., replicated training data), -2:
automatic.target_ratio_comm_to_comp - Target ratio of communication overhead to computation. Only for multi-node
operation and train_samples_per_iteration = -2 (auto-tuning).seed - Seed for random numbers (affects sampling) - Note: only reproducible when running single threaded.learning_rate - Learning rate (higher => less stable, lower => slower convergence).learning_rate_annealing - Learning rate annealing: rate / (1 + rate_annealing * samples).momentum_start - Initial momentum at the beginning of training (try 0.5).momentum_ramp - Number of training samples for which momentum increases.momentum_stable - Final momentum after the ramp is over (try 0.99).score_interval - Shortest time interval (in seconds) between model scoring.score_training_samples - Number of training set samples for scoring (0 for all).score_validation_samples - Number of validation set samples for scoring (0 for all).score_duty_cycle - Maximum duty cycle fraction for scoring (lower: more training, higher: more scoring).classification_stop - Stopping criterion for classification error fraction on training data (-1 to disable).regression_stop - Stopping criterion for regression error (MSE) on training data (-1 to disable).quiet_mode - Enable quiet mode for less output to standard output.overwrite_with_best_model - If enabled, override the final model with the best model found during training.autoencoder - Auto-Encoder.diagnostics - Enable diagnostics for hidden layers.variable_importances - Compute variable importances for input features (Gedeon method) - can be slow for
large networks.replicate_training_data - Replicate the entire training dataset onto every node for faster training on small
datasets.single_node_mode - Run on a single node for fine-tuning of model parameters.shuffle_training_data - Enable global shuffling of training data.mini_batch_size - Mini-batch size (smaller leads to better fit, larger can speed up and generalize better).clip_gradient - Clip gradients once their absolute value is larger than this value.network - Network architecture.backend - Deep Learning Backend.image_shape - Width and height of image.channels - Number of (color) channels.gpu - Whether to use a GPU (if available).device_id - Device IDs (which GPUs to use).cache_data - Whether to cache the data in memory (automatically disabled if data size is too large).network_definition_file - Path of file containing network definition (graph, architecture).network_parameters_file - Path of file containing network (initial) parameters (weights, biases).mean_image_file - Path of file containing the mean image data for data normalization.export_native_parameters_prefix - Path (prefix) where to export the native model parameters after every
iteration.standardize - If enabled, automatically standardize the data. If disabled, the user must provide properly
scaled input data.balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/deepwater") retrofit2.Call<DeepWaterV3> trainDeepwater()
@FormUrlEncoded @POST(value="/3/ModelBuilders/deepwater/parameters") retrofit2.Call<DeepWaterV3> validate_parametersDeepwater(@Field(value="problem_type") DeepWaterParametersProblemType problem_type, @Field(value="activation") DeepWaterParametersActivation activation, @Field(value="hidden") int[] hidden, @Field(value="input_dropout_ratio") double input_dropout_ratio, @Field(value="hidden_dropout_ratios") double[] hidden_dropout_ratios, @Field(value="max_confusion_matrix_size") int max_confusion_matrix_size, @Field(value="sparse") boolean sparse, @Field(value="max_hit_ratio_k") int max_hit_ratio_k, @Field(value="epochs") double epochs, @Field(value="train_samples_per_iteration") long train_samples_per_iteration, @Field(value="target_ratio_comm_to_comp") double target_ratio_comm_to_comp, @Field(value="seed") long seed, @Field(value="learning_rate") double learning_rate, @Field(value="learning_rate_annealing") double learning_rate_annealing, @Field(value="momentum_start") double momentum_start, @Field(value="momentum_ramp") double momentum_ramp, @Field(value="momentum_stable") double momentum_stable, @Field(value="score_interval") double score_interval, @Field(value="score_training_samples") long score_training_samples, @Field(value="score_validation_samples") long score_validation_samples, @Field(value="score_duty_cycle") double score_duty_cycle, @Field(value="classification_stop") double classification_stop, @Field(value="regression_stop") double regression_stop, @Field(value="quiet_mode") boolean quiet_mode, @Field(value="overwrite_with_best_model") boolean overwrite_with_best_model, @Field(value="autoencoder") boolean autoencoder, @Field(value="diagnostics") boolean diagnostics, @Field(value="variable_importances") boolean variable_importances, @Field(value="replicate_training_data") boolean replicate_training_data, @Field(value="single_node_mode") boolean single_node_mode, @Field(value="shuffle_training_data") boolean shuffle_training_data, @Field(value="mini_batch_size") int mini_batch_size, @Field(value="clip_gradient") double clip_gradient, @Field(value="network") DeepWaterParametersNetwork network, @Field(value="backend") DeepWaterParametersBackend backend, @Field(value="image_shape") int[] image_shape, @Field(value="channels") int channels, @Field(value="gpu") boolean gpu, @Field(value="device_id") int[] device_id, @Field(value="cache_data") boolean cache_data, @Field(value="network_definition_file") java.lang.String network_definition_file, @Field(value="network_parameters_file") java.lang.String network_parameters_file, @Field(value="mean_image_file") java.lang.String mean_image_file, @Field(value="export_native_parameters_prefix") java.lang.String export_native_parameters_prefix, @Field(value="standardize") boolean standardize, @Field(value="balance_classes") boolean balance_classes, @Field(value="class_sampling_factors") float[] class_sampling_factors, @Field(value="max_after_balance_size") float max_after_balance_size, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
problem_type - Problem type, auto-detected by default. If set to image, the H2OFrame must contain a string
column containing the path (URI or URL) to the images in the first column. If set to text,
the H2OFrame must contain a string column containing the text in the first column. If set to
dataset, Deep Water behaves just like any other H2O Model and builds a model on the provided
H2OFrame (non-String columns).activation - Activation function. Only used if no user-defined network architecture file is provided, and
only for problem_type=dataset.hidden - Hidden layer sizes (e.g. [200, 200]). Only used if no user-defined network architecture file is
provided, and only for problem_type=dataset.input_dropout_ratio - Input layer dropout ratio (can improve generalization, try 0.1 or 0.2).hidden_dropout_ratios - Hidden layer dropout ratios (can improve generalization), specify one value per
hidden layer, defaults to 0.5.max_confusion_matrix_size - [Deprecated] Maximum size (# classes) for confusion matrices to be printed in
the Logs.sparse - Sparse data handling (more efficient for data with lots of 0 values).max_hit_ratio_k - Max. number (top K) of predictions to use for hit ratio computation (for multi-class only,
0 to disable).epochs - How many times the dataset should be iterated (streamed), can be fractional.train_samples_per_iteration - Number of training samples (globally) per MapReduce iteration. Special values
are 0: one epoch, -1: all available data (e.g., replicated training data), -2:
automatic.target_ratio_comm_to_comp - Target ratio of communication overhead to computation. Only for multi-node
operation and train_samples_per_iteration = -2 (auto-tuning).seed - Seed for random numbers (affects sampling) - Note: only reproducible when running single threaded.learning_rate - Learning rate (higher => less stable, lower => slower convergence).learning_rate_annealing - Learning rate annealing: rate / (1 + rate_annealing * samples).momentum_start - Initial momentum at the beginning of training (try 0.5).momentum_ramp - Number of training samples for which momentum increases.momentum_stable - Final momentum after the ramp is over (try 0.99).score_interval - Shortest time interval (in seconds) between model scoring.score_training_samples - Number of training set samples for scoring (0 for all).score_validation_samples - Number of validation set samples for scoring (0 for all).score_duty_cycle - Maximum duty cycle fraction for scoring (lower: more training, higher: more scoring).classification_stop - Stopping criterion for classification error fraction on training data (-1 to disable).regression_stop - Stopping criterion for regression error (MSE) on training data (-1 to disable).quiet_mode - Enable quiet mode for less output to standard output.overwrite_with_best_model - If enabled, override the final model with the best model found during training.autoencoder - Auto-Encoder.diagnostics - Enable diagnostics for hidden layers.variable_importances - Compute variable importances for input features (Gedeon method) - can be slow for
large networks.replicate_training_data - Replicate the entire training dataset onto every node for faster training on small
datasets.single_node_mode - Run on a single node for fine-tuning of model parameters.shuffle_training_data - Enable global shuffling of training data.mini_batch_size - Mini-batch size (smaller leads to better fit, larger can speed up and generalize better).clip_gradient - Clip gradients once their absolute value is larger than this value.network - Network architecture.backend - Deep Learning Backend.image_shape - Width and height of image.channels - Number of (color) channels.gpu - Whether to use a GPU (if available).device_id - Device IDs (which GPUs to use).cache_data - Whether to cache the data in memory (automatically disabled if data size is too large).network_definition_file - Path of file containing network definition (graph, architecture).network_parameters_file - Path of file containing network (initial) parameters (weights, biases).mean_image_file - Path of file containing the mean image data for data normalization.export_native_parameters_prefix - Path (prefix) where to export the native model parameters after every
iteration.standardize - If enabled, automatically standardize the data. If disabled, the user must provide properly
scaled input data.balance_classes - Balance training data class counts via over/under-sampling (for imbalanced data).class_sampling_factors - Desired over/under-sampling ratios per class (in lexicographic order). If not
specified, sampling factors will be automatically computed to obtain class balance
during training. Requires balance_classes.max_after_balance_size - Maximum relative size of the training data after balancing class counts (can be
less than 1.0). Requires balance_classes.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/deepwater/parameters") retrofit2.Call<DeepWaterV3> validate_parametersDeepwater()
@FormUrlEncoded @POST(value="/3/ModelBuilders/word2vec") retrofit2.Call<Word2VecV3> trainWord2vec(@Field(value="vec_size") int vec_size, @Field(value="window_size") int window_size, @Field(value="sent_sample_rate") float sent_sample_rate, @Field(value="norm_model") Word2VecNormModel norm_model, @Field(value="epochs") int epochs, @Field(value="min_word_freq") int min_word_freq, @Field(value="init_learning_rate") float init_learning_rate, @Field(value="word_model") Word2VecWordModel word_model, @Field(value="pre_trained") java.lang.String pre_trained, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
vec_size - Set size of word vectorswindow_size - Set max skip length between wordssent_sample_rate - Set threshold for occurrence of words. Those that appear with higher frequency in the
training data will be randomly down-sampled; useful range is (0, 1e-5)norm_model - Use Hierarchical Softmaxepochs - Number of training iterations to runmin_word_freq - This will discard words that appear less than init_learning_rate - Set the starting learning rateword_model - Use the Skip-Gram modelpre_trained - Id of a data frame that contains a pre-trained (external) word2vec modelmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/word2vec") retrofit2.Call<Word2VecV3> trainWord2vec()
@FormUrlEncoded @POST(value="/3/ModelBuilders/word2vec/parameters") retrofit2.Call<Word2VecV3> validate_parametersWord2vec(@Field(value="vec_size") int vec_size, @Field(value="window_size") int window_size, @Field(value="sent_sample_rate") float sent_sample_rate, @Field(value="norm_model") Word2VecNormModel norm_model, @Field(value="epochs") int epochs, @Field(value="min_word_freq") int min_word_freq, @Field(value="init_learning_rate") float init_learning_rate, @Field(value="word_model") Word2VecWordModel word_model, @Field(value="pre_trained") java.lang.String pre_trained, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
vec_size - Set size of word vectorswindow_size - Set max skip length between wordssent_sample_rate - Set threshold for occurrence of words. Those that appear with higher frequency in the
training data will be randomly down-sampled; useful range is (0, 1e-5)norm_model - Use Hierarchical Softmaxepochs - Number of training iterations to runmin_word_freq - This will discard words that appear less than init_learning_rate - Set the starting learning rateword_model - Use the Skip-Gram modelpre_trained - Id of a data frame that contains a pre-trained (external) word2vec modelmodel_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/word2vec/parameters") retrofit2.Call<Word2VecV3> validate_parametersWord2vec()
@FormUrlEncoded @POST(value="/99/ModelBuilders/stackedensemble") retrofit2.Call<StackedEnsembleV99> trainStackedensemble(@Field(value="base_models") java.lang.String[] base_models, @Field(value="metalearner_algorithm") EnsembleMetalearnerAlgorithm metalearner_algorithm, @Field(value="metalearner_nfolds") int metalearner_nfolds, @Field(value="metalearner_fold_assignment") ModelParametersFoldAssignmentScheme metalearner_fold_assignment, @Field(value="metalearner_fold_column") java.lang.String metalearner_fold_column, @Field(value="keep_levelone_frame") boolean keep_levelone_frame, @Field(value="metalearner_params") java.lang.String metalearner_params, @Field(value="blending_frame") java.lang.String blending_frame, @Field(value="seed") long seed, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
base_models - List of models or grids (or their ids) to ensemble/stack together. Grids are expanded to
individual models. If not using blending frame, then models must have been cross-validated
using nfolds > 1, and folds must be identical across models.metalearner_algorithm - Type of algorithm to use as the metalearner. Options include 'AUTO' (GLM with non
negative weights; if validation_frame is present, a lambda search is performed),
'deeplearning' (Deep Learning with default parameters), 'drf' (Random Forest with
default parameters), 'gbm' (GBM with default parameters), 'glm' (GLM with default
parameters), 'naivebayes' (NaiveBayes with default parameters), or 'xgboost' (if
available, XGBoost with default parameters).metalearner_nfolds - Number of folds for K-fold cross-validation of the metalearner algorithm (0 to disable
or >= 2).metalearner_fold_assignment - Cross-validation fold assignment scheme for metalearner cross-validation.
Defaults to AUTO (which is currently set to Random). The 'Stratified' option
will stratify the folds based on the response variable, for classification
problems.metalearner_fold_column - Column with cross-validation fold index assignment per observation for cross-
validation of the metalearner.keep_levelone_frame - Keep level one frame used for metalearner training.metalearner_params - Parameters for metalearner algorithmblending_frame - Frame used to compute the predictions that serve as the training frame for the metalearner
(triggers blending mode if provided)seed - Seed for random numbers; passed through to the metalearner algorithm. Defaults to -1 (time-based
random number)model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/99/ModelBuilders/stackedensemble") retrofit2.Call<StackedEnsembleV99> trainStackedensemble(@Field(value="base_models") java.lang.String[] base_models)
@FormUrlEncoded @POST(value="/99/ModelBuilders/stackedensemble/parameters") retrofit2.Call<StackedEnsembleV99> validate_parametersStackedensemble(@Field(value="base_models") java.lang.String[] base_models, @Field(value="metalearner_algorithm") EnsembleMetalearnerAlgorithm metalearner_algorithm, @Field(value="metalearner_nfolds") int metalearner_nfolds, @Field(value="metalearner_fold_assignment") ModelParametersFoldAssignmentScheme metalearner_fold_assignment, @Field(value="metalearner_fold_column") java.lang.String metalearner_fold_column, @Field(value="keep_levelone_frame") boolean keep_levelone_frame, @Field(value="metalearner_params") java.lang.String metalearner_params, @Field(value="blending_frame") java.lang.String blending_frame, @Field(value="seed") long seed, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
base_models - List of models or grids (or their ids) to ensemble/stack together. Grids are expanded to
individual models. If not using blending frame, then models must have been cross-validated
using nfolds > 1, and folds must be identical across models.metalearner_algorithm - Type of algorithm to use as the metalearner. Options include 'AUTO' (GLM with non
negative weights; if validation_frame is present, a lambda search is performed),
'deeplearning' (Deep Learning with default parameters), 'drf' (Random Forest with
default parameters), 'gbm' (GBM with default parameters), 'glm' (GLM with default
parameters), 'naivebayes' (NaiveBayes with default parameters), or 'xgboost' (if
available, XGBoost with default parameters).metalearner_nfolds - Number of folds for K-fold cross-validation of the metalearner algorithm (0 to disable
or >= 2).metalearner_fold_assignment - Cross-validation fold assignment scheme for metalearner cross-validation.
Defaults to AUTO (which is currently set to Random). The 'Stratified' option
will stratify the folds based on the response variable, for classification
problems.metalearner_fold_column - Column with cross-validation fold index assignment per observation for cross-
validation of the metalearner.keep_levelone_frame - Keep level one frame used for metalearner training.metalearner_params - Parameters for metalearner algorithmblending_frame - Frame used to compute the predictions that serve as the training frame for the metalearner
(triggers blending mode if provided)seed - Seed for random numbers; passed through to the metalearner algorithm. Defaults to -1 (time-based
random number)model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/99/ModelBuilders/stackedensemble/parameters") retrofit2.Call<StackedEnsembleV99> validate_parametersStackedensemble(@Field(value="base_models") java.lang.String[] base_models)
@FormUrlEncoded @POST(value="/3/ModelBuilders/coxph") retrofit2.Call<CoxPHV3> trainCoxph(@Field(value="start_column") java.lang.String start_column, @Field(value="stop_column") java.lang.String stop_column, @Field(value="stratify_by") java.lang.String[] stratify_by, @Field(value="ties") CoxPHTies ties, @Field(value="init") double init, @Field(value="lre_min") double lre_min, @Field(value="max_iterations") int max_iterations, @Field(value="interactions_only") java.lang.String[] interactions_only, @Field(value="interactions") java.lang.String[] interactions, @Field(value="interaction_pairs") StringPairV3[] interaction_pairs, @Field(value="use_all_factor_levels") boolean use_all_factor_levels, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
start_column - Start Time Column.stop_column - Stop Time Column.stratify_by - List of columns to use for stratification.ties - Method for Handling Ties.init - Coefficient starting value.lre_min - Minimum log-relative error.max_iterations - Maximum number of iterations.interactions_only - A list of columns that should only be used to create interactions but should not itself
participate in model training.interactions - A list of predictor column indices to interact. All pairwise combinations will be computed
for the list.interaction_pairs - A list of pairwise (first order) column interactions.use_all_factor_levels - (Internal. For development only!) Indicates whether to use all factor levels.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/coxph") retrofit2.Call<CoxPHV3> trainCoxph()
@FormUrlEncoded @POST(value="/3/ModelBuilders/coxph/parameters") retrofit2.Call<CoxPHV3> validate_parametersCoxph(@Field(value="start_column") java.lang.String start_column, @Field(value="stop_column") java.lang.String stop_column, @Field(value="stratify_by") java.lang.String[] stratify_by, @Field(value="ties") CoxPHTies ties, @Field(value="init") double init, @Field(value="lre_min") double lre_min, @Field(value="max_iterations") int max_iterations, @Field(value="interactions_only") java.lang.String[] interactions_only, @Field(value="interactions") java.lang.String[] interactions, @Field(value="interaction_pairs") StringPairV3[] interaction_pairs, @Field(value="use_all_factor_levels") boolean use_all_factor_levels, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
start_column - Start Time Column.stop_column - Stop Time Column.stratify_by - List of columns to use for stratification.ties - Method for Handling Ties.init - Coefficient starting value.lre_min - Minimum log-relative error.max_iterations - Maximum number of iterations.interactions_only - A list of columns that should only be used to create interactions but should not itself
participate in model training.interactions - A list of predictor column indices to interact. All pairwise combinations will be computed
for the list.interaction_pairs - A list of pairwise (first order) column interactions.use_all_factor_levels - (Internal. For development only!) Indicates whether to use all factor levels.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/coxph/parameters") retrofit2.Call<CoxPHV3> validate_parametersCoxph()
@FormUrlEncoded @POST(value="/3/ModelBuilders/generic") retrofit2.Call<GenericV3> trainGeneric(@Field(value="path") java.lang.String path, @Field(value="model_key") java.lang.String model_key, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
path - Path to file with self-contained model archive.model_key - Key to the self-contained model archive already uploaded to H2O.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/generic") retrofit2.Call<GenericV3> trainGeneric()
@FormUrlEncoded @POST(value="/3/ModelBuilders/generic/parameters") retrofit2.Call<GenericV3> validate_parametersGeneric(@Field(value="path") java.lang.String path, @Field(value="model_key") java.lang.String model_key, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
path - Path to file with self-contained model archive.model_key - Key to the self-contained model archive already uploaded to H2O.model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/generic/parameters") retrofit2.Call<GenericV3> validate_parametersGeneric()
@FormUrlEncoded @POST(value="/3/ModelBuilders/psvm") retrofit2.Call<PSVMV3> trainPsvm(@Field(value="hyper_param") double hyper_param, @Field(value="kernel_type") GenmodelalgospsvmKernelType kernel_type, @Field(value="gamma") double gamma, @Field(value="rank_ratio") double rank_ratio, @Field(value="positive_weight") double positive_weight, @Field(value="negative_weight") double negative_weight, @Field(value="disable_training_metrics") boolean disable_training_metrics, @Field(value="sv_threshold") double sv_threshold, @Field(value="max_iterations") int max_iterations, @Field(value="fact_threshold") double fact_threshold, @Field(value="feasible_threshold") double feasible_threshold, @Field(value="surrogate_gap_threshold") double surrogate_gap_threshold, @Field(value="mu_factor") double mu_factor, @Field(value="seed") long seed, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
hyper_param - Penalty parameter C of the error termkernel_type - Type of used kernelgamma - Coefficient of the kernel (currently RBF gamma for gaussian kernel, -1 means 1/#features)rank_ratio - Desired rank of the ICF matrix expressed as an ration of number of input rows (-1 means use
sqrt(#rows)).positive_weight - Weight of positive (+1) class of observationsnegative_weight - Weight of positive (-1) class of observationsdisable_training_metrics - Disable calculating training metrics (expensive on large datasets)sv_threshold - Threshold for accepting a candidate observation into the set of support vectorsmax_iterations - Maximum number of iteration of the algorithmfact_threshold - Convergence threshold of the Incomplete Cholesky Factorization (ICF)feasible_threshold - Convergence threshold for primal-dual residuals in the IPM iterationsurrogate_gap_threshold - Feasibility criterion of the surrogate duality gap (eta)mu_factor - Increasing factor museed - Seed for pseudo random number generator (if applicable)model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/psvm") retrofit2.Call<PSVMV3> trainPsvm()
@FormUrlEncoded @POST(value="/3/ModelBuilders/psvm/parameters") retrofit2.Call<PSVMV3> validate_parametersPsvm(@Field(value="hyper_param") double hyper_param, @Field(value="kernel_type") GenmodelalgospsvmKernelType kernel_type, @Field(value="gamma") double gamma, @Field(value="rank_ratio") double rank_ratio, @Field(value="positive_weight") double positive_weight, @Field(value="negative_weight") double negative_weight, @Field(value="disable_training_metrics") boolean disable_training_metrics, @Field(value="sv_threshold") double sv_threshold, @Field(value="max_iterations") int max_iterations, @Field(value="fact_threshold") double fact_threshold, @Field(value="feasible_threshold") double feasible_threshold, @Field(value="surrogate_gap_threshold") double surrogate_gap_threshold, @Field(value="mu_factor") double mu_factor, @Field(value="seed") long seed, @Field(value="model_id") java.lang.String model_id, @Field(value="training_frame") java.lang.String training_frame, @Field(value="validation_frame") java.lang.String validation_frame, @Field(value="nfolds") int nfolds, @Field(value="keep_cross_validation_models") boolean keep_cross_validation_models, @Field(value="keep_cross_validation_predictions") boolean keep_cross_validation_predictions, @Field(value="keep_cross_validation_fold_assignment") boolean keep_cross_validation_fold_assignment, @Field(value="parallelize_cross_validation") boolean parallelize_cross_validation, @Field(value="distribution") GenmodelutilsDistributionFamily distribution, @Field(value="tweedie_power") double tweedie_power, @Field(value="quantile_alpha") double quantile_alpha, @Field(value="huber_alpha") double huber_alpha, @Field(value="response_column") java.lang.String response_column, @Field(value="weights_column") java.lang.String weights_column, @Field(value="offset_column") java.lang.String offset_column, @Field(value="fold_column") java.lang.String fold_column, @Field(value="fold_assignment") ModelParametersFoldAssignmentScheme fold_assignment, @Field(value="categorical_encoding") ModelParametersCategoricalEncodingScheme categorical_encoding, @Field(value="max_categorical_levels") int max_categorical_levels, @Field(value="ignored_columns") java.lang.String[] ignored_columns, @Field(value="ignore_const_cols") boolean ignore_const_cols, @Field(value="score_each_iteration") boolean score_each_iteration, @Field(value="checkpoint") java.lang.String checkpoint, @Field(value="stopping_rounds") int stopping_rounds, @Field(value="max_runtime_secs") double max_runtime_secs, @Field(value="stopping_metric") ScoreKeeperStoppingMetric stopping_metric, @Field(value="stopping_tolerance") double stopping_tolerance, @Field(value="custom_metric_func") java.lang.String custom_metric_func, @Field(value="custom_distribution_func") java.lang.String custom_distribution_func, @Field(value="export_checkpoints_dir") java.lang.String export_checkpoints_dir)
hyper_param - Penalty parameter C of the error termkernel_type - Type of used kernelgamma - Coefficient of the kernel (currently RBF gamma for gaussian kernel, -1 means 1/#features)rank_ratio - Desired rank of the ICF matrix expressed as an ration of number of input rows (-1 means use
sqrt(#rows)).positive_weight - Weight of positive (+1) class of observationsnegative_weight - Weight of positive (-1) class of observationsdisable_training_metrics - Disable calculating training metrics (expensive on large datasets)sv_threshold - Threshold for accepting a candidate observation into the set of support vectorsmax_iterations - Maximum number of iteration of the algorithmfact_threshold - Convergence threshold of the Incomplete Cholesky Factorization (ICF)feasible_threshold - Convergence threshold for primal-dual residuals in the IPM iterationsurrogate_gap_threshold - Feasibility criterion of the surrogate duality gap (eta)mu_factor - Increasing factor museed - Seed for pseudo random number generator (if applicable)model_id - Destination id for this model; auto-generated if not specified.training_frame - Id of the training data frame.validation_frame - Id of the validation data frame.nfolds - Number of folds for K-fold cross-validation (0 to disable or >= 2).keep_cross_validation_models - Whether to keep the cross-validation models.keep_cross_validation_predictions - Whether to keep the predictions of the cross-validation models.keep_cross_validation_fold_assignment - Whether to keep the cross-validation fold assignment.parallelize_cross_validation - Allow parallel training of cross-validation modelsdistribution - Distribution functiontweedie_power - Tweedie power for Tweedie regression, must be between 1 and 2.quantile_alpha - Desired quantile for Quantile regression, must be between 0 and 1.huber_alpha - Desired quantile for Huber/M-regression (threshold between quadratic and linear loss, must be
between 0 and 1).response_column - Response variable column.weights_column - Column with observation weights. Giving some observation a weight of zero is equivalent to
excluding it from the dataset; giving an observation a relative weight of 2 is equivalent
to repeating that row twice. Negative weights are not allowed. Note: Weights are per-row
observation weights and do not increase the size of the data frame. This is typically the
number of times a row is repeated, but non-integer values are supported as well. During
training, rows with higher weights matter more, due to the larger loss function pre-factor.offset_column - Offset column. This will be added to the combination of columns before applying the link
function.fold_column - Column with cross-validation fold index assignment per observation.fold_assignment - Cross-validation fold assignment scheme, if fold_column is not specified. The 'Stratified'
option will stratify the folds based on the response variable, for classification
problems.categorical_encoding - Encoding scheme for categorical featuresmax_categorical_levels - For every categorical feature, only use this many most frequent categorical levels
for model training. Only used for categorical_encoding == EnumLimited.ignored_columns - Names of columns to ignore for training.ignore_const_cols - Ignore constant columns.score_each_iteration - Whether to score during each iteration of model training.checkpoint - Model checkpoint to resume training with.stopping_rounds - Early stopping based on convergence of stopping_metric. Stop if simple moving average of
length k of the stopping_metric does not improve for k:=stopping_rounds scoring events (0
to disable)max_runtime_secs - Maximum allowed runtime in seconds for model training. Use 0 to disable.stopping_metric - Metric to use for early stopping (AUTO: logloss for classification, deviance for
regression and anonomaly_score for Isolation Forest). Note that custom and
custom_increasing can only be used in GBM and DRF with the Python client.stopping_tolerance - Relative tolerance for metric-based stopping criterion (stop if relative improvement is
not at least this much)custom_metric_func - Reference to custom evaluation function, format: `language:keyName=funcName`custom_distribution_func - Reference to custom distribution, format: `language:keyName=funcName`export_checkpoints_dir - Automatically export generated models to this directory.@FormUrlEncoded @POST(value="/3/ModelBuilders/psvm/parameters") retrofit2.Call<PSVMV3> validate_parametersPsvm()
@FormUrlEncoded
@POST(value="/3/ModelBuilders/{algo}/model_id")
retrofit2.Call<ModelIdV3> calcModelId(@Path(value="algo")
java.lang.String algo,
@Field(value="_exclude_fields")
java.lang.String _exclude_fields)
algo - Algo of ModelBuilder of interest_exclude_fields - Comma-separated list of JSON field paths to exclude from the result, used like:
"/3/Frames?_exclude_fields=frames/frame_id/URL,__meta"@FormUrlEncoded
@POST(value="/3/ModelBuilders/{algo}/model_id")
retrofit2.Call<ModelIdV3> calcModelId(@Path(value="algo")
java.lang.String algo)
@GET(value="/3/ModelBuilders/{algo}")
retrofit2.Call<ModelBuildersV3> fetch(@Path(value="algo")
java.lang.String algo,
@Query(value="_exclude_fields")
java.lang.String _exclude_fields)
algo - Algo of ModelBuilder of interest_exclude_fields - Comma-separated list of JSON field paths to exclude from the result, used like:
"/3/Frames?_exclude_fields=frames/frame_id/URL,__meta"@GET(value="/3/ModelBuilders/{algo}")
retrofit2.Call<ModelBuildersV3> fetch(@Path(value="algo")
java.lang.String algo)
@GET(value="/3/ModelBuilders") retrofit2.Call<ModelBuildersV3> list(@Query(value="algo") java.lang.String algo, @Query(value="_exclude_fields") java.lang.String _exclude_fields)
algo - Algo of ModelBuilder of interest_exclude_fields - Comma-separated list of JSON field paths to exclude from the result, used like:
"/3/Frames?_exclude_fields=frames/frame_id/URL,__meta"@GET(value="/3/ModelBuilders") retrofit2.Call<ModelBuildersV3> list()