Class: Google::Apis::BigqueryV2::TrainingOptions

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/bigquery_v2/classes.rb,
lib/google/apis/bigquery_v2/representations.rb,
lib/google/apis/bigquery_v2/representations.rb

Overview

Options used in model training.

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ TrainingOptions

Returns a new instance of TrainingOptions.



8614
8615
8616
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8614

def initialize(**args)
   update!(**args)
end

Instance Attribute Details

#adjust_step_changes ⇒ Boolean Also known as: adjust_step_changes?

If true, detect step changes and make data adjustment in the input time series. Corresponds to the JSON property adjustStepChanges

Returns:

  • (Boolean) 


8246
8247
8248
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8246

def adjust_step_changes
  @adjust_step_changes
end

#auto_arima ⇒ Boolean Also known as: auto_arima?

Whether to enable auto ARIMA or not. Corresponds to the JSON property autoArima

Returns:

  • (Boolean) 


8252
8253
8254
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8252

def auto_arima
  @auto_arima
end

#auto_arima_max_order ⇒ Fixnum

The max value of non-seasonal p and q. Corresponds to the JSON property autoArimaMaxOrder

Returns:

  • (Fixnum) 


8258
8259
8260
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8258

def auto_arima_max_order
  @auto_arima_max_order
end

#batch_size ⇒ Fixnum

Batch size for dnn models. Corresponds to the JSON property batchSize

Returns:

  • (Fixnum) 


8263
8264
8265
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8263

def batch_size
  @batch_size
end

#booster_type ⇒ String

Booster type for boosted tree models. Corresponds to the JSON property boosterType

Returns:

  • (String) 


8268
8269
8270
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8268

def booster_type
  @booster_type
end

#calculate_p_values ⇒ Boolean Also known as: calculate_p_values?

Whether or not p-value test should be computed for this model. Only available for linear and logistic regression models. Corresponds to the JSON property calculatePValues

Returns:

  • (Boolean) 


8274
8275
8276
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8274

def calculate_p_values
  @calculate_p_values
end

#clean_spikes_and_dips ⇒ Boolean Also known as: clean_spikes_and_dips?

If true, clean spikes and dips in the input time series. Corresponds to the JSON property cleanSpikesAndDips

Returns:

  • (Boolean) 


8280
8281
8282
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8280

def clean_spikes_and_dips
  @clean_spikes_and_dips
end

#color_space ⇒ String

Enums for color space, used for processing images in Object Table. See more details at https://www.tensorflow.org/io/tutorials/colorspace. Corresponds to the JSON property colorSpace

Returns:

  • (String) 


8287
8288
8289
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8287

def color_space
  @color_space
end

#colsample_bylevel ⇒ Float

Subsample ratio of columns for each level for boosted tree models. Corresponds to the JSON property colsampleBylevel

Returns:

  • (Float) 


8292
8293
8294
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8292

def colsample_bylevel
  @colsample_bylevel
end

#colsample_bynode ⇒ Float

Subsample ratio of columns for each node(split) for boosted tree models. Corresponds to the JSON property colsampleBynode

Returns:

  • (Float) 


8297
8298
8299
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8297

def colsample_bynode
  @colsample_bynode
end

#colsample_bytree ⇒ Float

Subsample ratio of columns when constructing each tree for boosted tree models. Corresponds to the JSON property colsampleBytree

Returns:

  • (Float) 


8302
8303
8304
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8302

def colsample_bytree
  @colsample_bytree
end

#dart_normalize_type ⇒ String

Type of normalization algorithm for boosted tree models using dart booster. Corresponds to the JSON property dartNormalizeType

Returns:

  • (String) 


8307
8308
8309
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8307

def dart_normalize_type
  @dart_normalize_type
end

#data_frequency ⇒ String

The data frequency of a time series. Corresponds to the JSON property dataFrequency

Returns:

  • (String) 


8312
8313
8314
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8312

def data_frequency
  @data_frequency
end

#data_split_column ⇒ String

The column to split data with. This column won't be used as a feature. 1. When data_split_method is CUSTOM, the corresponding column should be boolean. The rows with true value tag are eval data, and the false are training data. 2. When data_split_method is SEQ, the first DATA_SPLIT_EVAL_FRACTION rows (from smallest to largest) in the corresponding column are used as training data, and the rest are eval data. It respects the order in Orderable data types: https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types#data- type-properties Corresponds to the JSON property dataSplitColumn

Returns:

  • (String) 


8324
8325
8326
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8324

def data_split_column
  @data_split_column
end

#data_split_eval_fraction ⇒ Float

The fraction of evaluation data over the whole input data. The rest of data will be used as training data. The format should be double. Accurate to two decimal places. Default value is 0.2. Corresponds to the JSON property dataSplitEvalFraction

Returns:

  • (Float) 


8331
8332
8333
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8331

def data_split_eval_fraction
  @data_split_eval_fraction
end

#data_split_method ⇒ String

The data split type for training and evaluation, e.g. RANDOM. Corresponds to the JSON property dataSplitMethod

Returns:

  • (String) 


8336
8337
8338
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8336

def data_split_method
  @data_split_method
end

#decompose_time_series ⇒ Boolean Also known as: decompose_time_series?

If true, perform decompose time series and save the results. Corresponds to the JSON property decomposeTimeSeries

Returns:

  • (Boolean) 


8341
8342
8343
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8341

def decompose_time_series
  @decompose_time_series
end

#distance_type ⇒ String

Distance type for clustering models. Corresponds to the JSON property distanceType

Returns:

  • (String) 


8347
8348
8349
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8347

def distance_type
  @distance_type
end

#dropout ⇒ Float

Dropout probability for dnn models. Corresponds to the JSON property dropout

Returns:

  • (Float) 


8352
8353
8354
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8352

def dropout
  @dropout
end

#early_stop ⇒ Boolean Also known as: early_stop?

Whether to stop early when the loss doesn't improve significantly any more ( compared to min_relative_progress). Used only for iterative training algorithms. Corresponds to the JSON property earlyStop

Returns:

  • (Boolean) 


8359
8360
8361
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8359

def early_stop
  @early_stop
end

#enable_global_explain ⇒ Boolean Also known as: enable_global_explain?

If true, enable global explanation during training. Corresponds to the JSON property enableGlobalExplain

Returns:

  • (Boolean) 


8365
8366
8367
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8365

def enable_global_explain
  @enable_global_explain
end

#feedback_type ⇒ String

Feedback type that specifies which algorithm to run for matrix factorization. Corresponds to the JSON property feedbackType

Returns:

  • (String) 


8371
8372
8373
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8371

def feedback_type
  @feedback_type
end

#hidden_units ⇒ Array<Fixnum>

Hidden units for dnn models. Corresponds to the JSON property hiddenUnits

Returns:

  • (Array<Fixnum>) 


8376
8377
8378
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8376

def hidden_units
  @hidden_units
end

#holiday_region ⇒ String

The geographical region based on which the holidays are considered in time series modeling. If a valid value is specified, then holiday effects modeling is enabled. Corresponds to the JSON property holidayRegion

Returns:

  • (String) 


8383
8384
8385
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8383

def holiday_region
  @holiday_region
end

#horizon ⇒ Fixnum

The number of periods ahead that need to be forecasted. Corresponds to the JSON property horizon

Returns:

  • (Fixnum) 


8388
8389
8390
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8388

def horizon
  @horizon
end

#hparam_tuning_objectives ⇒ Array<String>

The target evaluation metrics to optimize the hyperparameters for. Corresponds to the JSON property hparamTuningObjectives

Returns:

  • (Array<String>) 


8393
8394
8395
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8393

def hparam_tuning_objectives
  @hparam_tuning_objectives
end

#include_drift ⇒ Boolean Also known as: include_drift?

Include drift when fitting an ARIMA model. Corresponds to the JSON property includeDrift

Returns:

  • (Boolean) 


8398
8399
8400
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8398

def include_drift
  @include_drift
end

#initial_learn_rate ⇒ Float

Specifies the initial learning rate for the line search learn rate strategy. Corresponds to the JSON property initialLearnRate

Returns:

  • (Float) 


8404
8405
8406
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8404

def initial_learn_rate
  @initial_learn_rate
end

#input_label_columns ⇒ Array<String>

Name of input label columns in training data. Corresponds to the JSON property inputLabelColumns

Returns:

  • (Array<String>) 


8409
8410
8411
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8409

def input_label_columns
  @input_label_columns
end

#integrated_gradients_num_steps ⇒ Fixnum

Number of integral steps for the integrated gradients explain method. Corresponds to the JSON property integratedGradientsNumSteps

Returns:

  • (Fixnum) 


8414
8415
8416
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8414

def integrated_gradients_num_steps
  @integrated_gradients_num_steps
end

#item_column ⇒ String

Item column specified for matrix factorization models. Corresponds to the JSON property itemColumn

Returns:

  • (String) 


8419
8420
8421
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8419

def item_column
  @item_column
end

#kmeans_initialization_column ⇒ String

The column used to provide the initial centroids for kmeans algorithm when kmeans_initialization_method is CUSTOM. Corresponds to the JSON property kmeansInitializationColumn

Returns:

  • (String) 


8425
8426
8427
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8425

def kmeans_initialization_column
  @kmeans_initialization_column
end

#kmeans_initialization_method ⇒ String

The method used to initialize the centroids for kmeans algorithm. Corresponds to the JSON property kmeansInitializationMethod

Returns:

  • (String) 


8430
8431
8432
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8430

def kmeans_initialization_method
  @kmeans_initialization_method
end

#l1_regularization ⇒ Float

L1 regularization coefficient. Corresponds to the JSON property l1Regularization

Returns:

  • (Float) 


8435
8436
8437
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8435

def l1_regularization
  @l1_regularization
end

#l2_regularization ⇒ Float

L2 regularization coefficient. Corresponds to the JSON property l2Regularization

Returns:

  • (Float) 


8440
8441
8442
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8440

def l2_regularization
  @l2_regularization
end

#label_class_weights ⇒ Hash<String,Float>

Weights associated with each label class, for rebalancing the training data. Only applicable for classification models. Corresponds to the JSON property labelClassWeights

Returns:

  • (Hash<String,Float>) 


8446
8447
8448
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8446

def label_class_weights
  @label_class_weights
end

#learn_rate ⇒ Float

Learning rate in training. Used only for iterative training algorithms. Corresponds to the JSON property learnRate

Returns:

  • (Float) 


8451
8452
8453
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8451

def learn_rate
  @learn_rate
end

#learn_rate_strategy ⇒ String

The strategy to determine learn rate for the current iteration. Corresponds to the JSON property learnRateStrategy

Returns:

  • (String) 


8456
8457
8458
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8456

def learn_rate_strategy
  @learn_rate_strategy
end

#loss_type ⇒ String

Type of loss function used during training run. Corresponds to the JSON property lossType

Returns:

  • (String) 


8461
8462
8463
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8461

def loss_type
  @loss_type
end

#max_iterations ⇒ Fixnum

The maximum number of iterations in training. Used only for iterative training algorithms. Corresponds to the JSON property maxIterations

Returns:

  • (Fixnum) 


8467
8468
8469
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8467

def max_iterations
  @max_iterations
end

#max_parallel_trials ⇒ Fixnum

Maximum number of trials to run in parallel. Corresponds to the JSON property maxParallelTrials

Returns:

  • (Fixnum) 


8472
8473
8474
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8472

def max_parallel_trials
  @max_parallel_trials
end

#max_time_series_length ⇒ Fixnum

Get truncated length by last n points in time series. Use separately from time_series_length_fraction and min_time_series_length. Corresponds to the JSON property maxTimeSeriesLength

Returns:

  • (Fixnum) 


8478
8479
8480
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8478

def max_time_series_length
  @max_time_series_length
end

#max_tree_depth ⇒ Fixnum

Maximum depth of a tree for boosted tree models. Corresponds to the JSON property maxTreeDepth

Returns:

  • (Fixnum) 


8483
8484
8485
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8483

def max_tree_depth
  @max_tree_depth
end

#min_relative_progress ⇒ Float

When early_stop is true, stops training when accuracy improvement is less than 'min_relative_progress'. Used only for iterative training algorithms. Corresponds to the JSON property minRelativeProgress

Returns:

  • (Float) 


8489
8490
8491
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8489

def min_relative_progress
  @min_relative_progress
end

#min_split_loss ⇒ Float

Minimum split loss for boosted tree models. Corresponds to the JSON property minSplitLoss

Returns:

  • (Float) 


8494
8495
8496
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8494

def min_split_loss
  @min_split_loss
end

#min_time_series_length ⇒ Fixnum

Set fast trend ARIMA_PLUS model minimum training length. Use in pair with time_series_length_fraction. Corresponds to the JSON property minTimeSeriesLength

Returns:

  • (Fixnum) 


8500
8501
8502
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8500

def min_time_series_length
  @min_time_series_length
end

#min_tree_child_weight ⇒ Fixnum

Minimum sum of instance weight needed in a child for boosted tree models. Corresponds to the JSON property minTreeChildWeight

Returns:

  • (Fixnum) 


8505
8506
8507
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8505

def min_tree_child_weight
  @min_tree_child_weight
end

#model_uri ⇒ String

Google Cloud Storage URI from which the model was imported. Only applicable for imported models. Corresponds to the JSON property modelUri

Returns:

  • (String) 


8511
8512
8513
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8511

def model_uri
  @model_uri
end

#non_seasonal_order ⇒ Google::Apis::BigqueryV2::ArimaOrder

Arima order, can be used for both non-seasonal and seasonal parts. Corresponds to the JSON property nonSeasonalOrder

Returns:



8516
8517
8518
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8516

def non_seasonal_order
  @non_seasonal_order
end

#num_clusters ⇒ Fixnum

Number of clusters for clustering models. Corresponds to the JSON property numClusters

Returns:

  • (Fixnum) 


8521
8522
8523
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8521

def num_clusters
  @num_clusters
end

#num_factors ⇒ Fixnum

Num factors specified for matrix factorization models. Corresponds to the JSON property numFactors

Returns:

  • (Fixnum) 


8526
8527
8528
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8526

def num_factors
  @num_factors
end

#num_parallel_tree ⇒ Fixnum

Number of parallel trees constructed during each iteration for boosted tree models. Corresponds to the JSON property numParallelTree

Returns:

  • (Fixnum) 


8532
8533
8534
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8532

def num_parallel_tree
  @num_parallel_tree
end

#num_trials ⇒ Fixnum

Number of trials to run this hyperparameter tuning job. Corresponds to the JSON property numTrials

Returns:

  • (Fixnum) 


8537
8538
8539
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8537

def num_trials
  @num_trials
end

#optimization_strategy ⇒ String

Optimization strategy for training linear regression models. Corresponds to the JSON property optimizationStrategy

Returns:

  • (String) 


8542
8543
8544
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8542

def optimization_strategy
  @optimization_strategy
end

#preserve_input_structs ⇒ Boolean Also known as: preserve_input_structs?

Whether to preserve the input structs in output feature names. Suppose there is a struct A with field b. When false (default), the output feature name is A_b. When true, the output feature name is A.b. Corresponds to the JSON property preserveInputStructs

Returns:

  • (Boolean) 


8549
8550
8551
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8549

def preserve_input_structs
  @preserve_input_structs
end

#sampled_shapley_num_paths ⇒ Fixnum

Number of paths for the sampled Shapley explain method. Corresponds to the JSON property sampledShapleyNumPaths

Returns:

  • (Fixnum) 


8555
8556
8557
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8555

def sampled_shapley_num_paths
  @sampled_shapley_num_paths
end

#subsample ⇒ Float

Subsample fraction of the training data to grow tree to prevent overfitting for boosted tree models. Corresponds to the JSON property subsample

Returns:

  • (Float) 


8561
8562
8563
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8561

def subsample
  @subsample
end

#time_series_data_column ⇒ String

Column to be designated as time series data for ARIMA model. Corresponds to the JSON property timeSeriesDataColumn

Returns:

  • (String) 


8566
8567
8568
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8566

def time_series_data_column
  @time_series_data_column
end

#time_series_id_column ⇒ String

The time series id column that was used during ARIMA model training. Corresponds to the JSON property timeSeriesIdColumn

Returns:

  • (String) 


8571
8572
8573
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8571

def time_series_id_column
  @time_series_id_column
end

#time_series_id_columns ⇒ Array<String>

The time series id columns that were used during ARIMA model training. Corresponds to the JSON property timeSeriesIdColumns

Returns:

  • (Array<String>) 


8576
8577
8578
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8576

def time_series_id_columns
  @time_series_id_columns
end

#time_series_length_fraction ⇒ Float

Get truncated length by fraction in time series. Corresponds to the JSON property timeSeriesLengthFraction

Returns:

  • (Float) 


8581
8582
8583
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8581

def time_series_length_fraction
  @time_series_length_fraction
end

#time_series_timestamp_column ⇒ String

Column to be designated as time series timestamp for ARIMA model. Corresponds to the JSON property timeSeriesTimestampColumn

Returns:

  • (String) 


8586
8587
8588
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8586

def time_series_timestamp_column
  @time_series_timestamp_column
end

#tree_method ⇒ String

Tree construction algorithm for boosted tree models. Corresponds to the JSON property treeMethod

Returns:

  • (String) 


8591
8592
8593
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8591

def tree_method
  @tree_method
end

#trend_smoothing_window_size ⇒ Fixnum

The smoothing window size for the trend component of the time series. Corresponds to the JSON property trendSmoothingWindowSize

Returns:

  • (Fixnum) 


8596
8597
8598
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8596

def trend_smoothing_window_size
  @trend_smoothing_window_size
end

#user_column ⇒ String

User column specified for matrix factorization models. Corresponds to the JSON property userColumn

Returns:

  • (String) 


8601
8602
8603
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8601

def user_column
  @user_column
end

#wals_alpha ⇒ Float

Hyperparameter for matrix factoration when implicit feedback type is specified. Corresponds to the JSON property walsAlpha

Returns:

  • (Float) 


8606
8607
8608
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8606

def wals_alpha
  @wals_alpha
end

#warm_start ⇒ Boolean Also known as: warm_start?

Whether to train a model from the last checkpoint. Corresponds to the JSON property warmStart

Returns:

  • (Boolean) 


8611
8612
8613
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8611

def warm_start
  @warm_start
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 8619

def update!(**args)
  @adjust_step_changes = args[:adjust_step_changes] if args.key?(:adjust_step_changes)
  @auto_arima = args[:auto_arima] if args.key?(:auto_arima)
  @auto_arima_max_order = args[:auto_arima_max_order] if args.key?(:auto_arima_max_order)
  @batch_size = args[:batch_size] if args.key?(:batch_size)
  @booster_type = args[:booster_type] if args.key?(:booster_type)
  @calculate_p_values = args[:calculate_p_values] if args.key?(:calculate_p_values)
  @clean_spikes_and_dips = args[:clean_spikes_and_dips] if args.key?(:clean_spikes_and_dips)
  @color_space = args[:color_space] if args.key?(:color_space)
  @colsample_bylevel = args[:colsample_bylevel] if args.key?(:colsample_bylevel)
  @colsample_bynode = args[:colsample_bynode] if args.key?(:colsample_bynode)
  @colsample_bytree = args[:colsample_bytree] if args.key?(:colsample_bytree)
  @dart_normalize_type = args[:dart_normalize_type] if args.key?(:dart_normalize_type)
  @data_frequency = args[:data_frequency] if args.key?(:data_frequency)
  @data_split_column = args[:data_split_column] if args.key?(:data_split_column)
  @data_split_eval_fraction = args[:data_split_eval_fraction] if args.key?(:data_split_eval_fraction)
  @data_split_method = args[:data_split_method] if args.key?(:data_split_method)
  @decompose_time_series = args[:decompose_time_series] if args.key?(:decompose_time_series)
  @distance_type = args[:distance_type] if args.key?(:distance_type)
  @dropout = args[:dropout] if args.key?(:dropout)
  @early_stop = args[:early_stop] if args.key?(:early_stop)
  @enable_global_explain = args[:enable_global_explain] if args.key?(:enable_global_explain)
  @feedback_type = args[:feedback_type] if args.key?(:feedback_type)
  @hidden_units = args[:hidden_units] if args.key?(:hidden_units)
  @holiday_region = args[:holiday_region] if args.key?(:holiday_region)
  @horizon = args[:horizon] if args.key?(:horizon)
  @hparam_tuning_objectives = args[:hparam_tuning_objectives] if args.key?(:hparam_tuning_objectives)
  @include_drift = args[:include_drift] if args.key?(:include_drift)
  @initial_learn_rate = args[:initial_learn_rate] if args.key?(:initial_learn_rate)
  @input_label_columns = args[:input_label_columns] if args.key?(:input_label_columns)
  @integrated_gradients_num_steps = args[:integrated_gradients_num_steps] if args.key?(:integrated_gradients_num_steps)
  @item_column = args[:item_column] if args.key?(:item_column)
  @kmeans_initialization_column = args[:kmeans_initialization_column] if args.key?(:kmeans_initialization_column)
  @kmeans_initialization_method = args[:kmeans_initialization_method] if args.key?(:kmeans_initialization_method)
  @l1_regularization = args[:l1_regularization] if args.key?(:l1_regularization)
  @l2_regularization = args[:l2_regularization] if args.key?(:l2_regularization)
  @label_class_weights = args[:label_class_weights] if args.key?(:label_class_weights)
  @learn_rate = args[:learn_rate] if args.key?(:learn_rate)
  @learn_rate_strategy = args[:learn_rate_strategy] if args.key?(:learn_rate_strategy)
  @loss_type = args[:loss_type] if args.key?(:loss_type)
  @max_iterations = args[:max_iterations] if args.key?(:max_iterations)
  @max_parallel_trials = args[:max_parallel_trials] if args.key?(:max_parallel_trials)
  @max_time_series_length = args[:max_time_series_length] if args.key?(:max_time_series_length)
  @max_tree_depth = args[:max_tree_depth] if args.key?(:max_tree_depth)
  @min_relative_progress = args[:min_relative_progress] if args.key?(:min_relative_progress)
  @min_split_loss = args[:min_split_loss] if args.key?(:min_split_loss)
  @min_time_series_length = args[:min_time_series_length] if args.key?(:min_time_series_length)
  @min_tree_child_weight = args[:min_tree_child_weight] if args.key?(:min_tree_child_weight)
  @model_uri = args[:model_uri] if args.key?(:model_uri)
  @non_seasonal_order = args[:non_seasonal_order] if args.key?(:non_seasonal_order)
  @num_clusters = args[:num_clusters] if args.key?(:num_clusters)
  @num_factors = args[:num_factors] if args.key?(:num_factors)
  @num_parallel_tree = args[:num_parallel_tree] if args.key?(:num_parallel_tree)
  @num_trials = args[:num_trials] if args.key?(:num_trials)
  @optimization_strategy = args[:optimization_strategy] if args.key?(:optimization_strategy)
  @preserve_input_structs = args[:preserve_input_structs] if args.key?(:preserve_input_structs)
  @sampled_shapley_num_paths = args[:sampled_shapley_num_paths] if args.key?(:sampled_shapley_num_paths)
  @subsample = args[:subsample] if args.key?(:subsample)
  @time_series_data_column = args[:time_series_data_column] if args.key?(:time_series_data_column)
  @time_series_id_column = args[:time_series_id_column] if args.key?(:time_series_id_column)
  @time_series_id_columns = args[:time_series_id_columns] if args.key?(:time_series_id_columns)
  @time_series_length_fraction = args[:time_series_length_fraction] if args.key?(:time_series_length_fraction)
  @time_series_timestamp_column = args[:time_series_timestamp_column] if args.key?(:time_series_timestamp_column)
  @tree_method = args[:tree_method] if args.key?(:tree_method)
  @trend_smoothing_window_size = args[:trend_smoothing_window_size] if args.key?(:trend_smoothing_window_size)
  @user_column = args[:user_column] if args.key?(:user_column)
  @wals_alpha = args[:wals_alpha] if args.key?(:wals_alpha)
  @warm_start = args[:warm_start] if args.key?(:warm_start)
end