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.



11035
11036
11037
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 11035

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

Instance Attribute Details

#activation_fn ⇒ String

Activation function of the neural nets. Corresponds to the JSON property activationFn

Returns:

  • (String) 


10546
10547
10548
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10546

def activation_fn
  @activation_fn
end

#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) 


10551
10552
10553
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10551

def adjust_step_changes
  @adjust_step_changes
end

#approx_global_feature_contrib ⇒ Boolean Also known as: approx_global_feature_contrib?

Whether to use approximate feature contribution method in XGBoost model explanation for global explain. Corresponds to the JSON property approxGlobalFeatureContrib

Returns:

  • (Boolean) 


10558
10559
10560
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10558

def approx_global_feature_contrib
  @approx_global_feature_contrib
end

#auto_arima ⇒ Boolean Also known as: auto_arima?

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

Returns:

  • (Boolean) 


10564
10565
10566
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10564

def auto_arima
  @auto_arima
end

#auto_arima_max_order ⇒ Fixnum

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

Returns:

  • (Fixnum) 


10570
10571
10572
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10570

def auto_arima_max_order
  @auto_arima_max_order
end

#auto_arima_min_order ⇒ Fixnum

The min value of the sum of non-seasonal p and q. Corresponds to the JSON property autoArimaMinOrder

Returns:

  • (Fixnum) 


10575
10576
10577
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10575

def auto_arima_min_order
  @auto_arima_min_order
end

#auto_class_weights ⇒ Boolean Also known as: auto_class_weights?

Whether to calculate class weights automatically based on the popularity of each label. Corresponds to the JSON property autoClassWeights

Returns:

  • (Boolean) 


10581
10582
10583
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10581

def auto_class_weights
  @auto_class_weights
end

#batch_size ⇒ Fixnum

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

Returns:

  • (Fixnum) 


10587
10588
10589
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10587

def batch_size
  @batch_size
end

#booster_type ⇒ String

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

Returns:

  • (String) 


10592
10593
10594
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10592

def booster_type
  @booster_type
end

#budget_hours ⇒ Float

Budget in hours for AutoML training. Corresponds to the JSON property budgetHours

Returns:

  • (Float) 


10597
10598
10599
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10597

def budget_hours
  @budget_hours
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) 


10603
10604
10605
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10603

def calculate_p_values
  @calculate_p_values
end

#category_encoding_method ⇒ String

Categorical feature encoding method. Corresponds to the JSON property categoryEncodingMethod

Returns:

  • (String) 


10609
10610
10611
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10609

def category_encoding_method
  @category_encoding_method
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) 


10614
10615
10616
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10614

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) 


10621
10622
10623
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10621

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) 


10626
10627
10628
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10626

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) 


10631
10632
10633
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10631

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) 


10636
10637
10638
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10636

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) 


10641
10642
10643
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10641

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) 


10646
10647
10648
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10646

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) 


10658
10659
10660
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10658

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) 


10665
10666
10667
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10665

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) 


10670
10671
10672
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10670

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) 


10675
10676
10677
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10675

def decompose_time_series
  @decompose_time_series
end

#distance_type ⇒ String

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

Returns:

  • (String) 


10681
10682
10683
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10681

def distance_type
  @distance_type
end

#dropout ⇒ Float

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

Returns:

  • (Float) 


10686
10687
10688
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10686

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) 


10693
10694
10695
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10693

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) 


10699
10700
10701
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10699

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) 


10705
10706
10707
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10705

def feedback_type
  @feedback_type
end

#fit_intercept ⇒ Boolean Also known as: fit_intercept?

Whether the model should include intercept during model training. Corresponds to the JSON property fitIntercept

Returns:

  • (Boolean) 


10710
10711
10712
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10710

def fit_intercept
  @fit_intercept
end

#hidden_units ⇒ Array<Fixnum>

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

Returns:

  • (Array<Fixnum>) 


10716
10717
10718
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10716

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) 


10723
10724
10725
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10723

def holiday_region
  @holiday_region
end

#holiday_regions ⇒ Array<String>

A list of geographical regions that are used for time series modeling. Corresponds to the JSON property holidayRegions

Returns:

  • (Array<String>) 


10728
10729
10730
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10728

def holiday_regions
  @holiday_regions
end

#horizon ⇒ Fixnum

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

Returns:

  • (Fixnum) 


10733
10734
10735
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10733

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>) 


10738
10739
10740
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10738

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) 


10743
10744
10745
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10743

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) 


10749
10750
10751
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10749

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>) 


10754
10755
10756
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10754

def input_label_columns
  @input_label_columns
end

#instance_weight_column ⇒ String

Name of the instance weight column for training data. This column isn't be used as a feature. Corresponds to the JSON property instanceWeightColumn

Returns:

  • (String) 


10760
10761
10762
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10760

def instance_weight_column
  @instance_weight_column
end

#integrated_gradients_num_steps ⇒ Fixnum

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

Returns:

  • (Fixnum) 


10765
10766
10767
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10765

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) 


10770
10771
10772
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10770

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) 


10776
10777
10778
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10776

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) 


10781
10782
10783
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10781

def kmeans_initialization_method
  @kmeans_initialization_method
end

#l1_reg_activation ⇒ Float

L1 regularization coefficient to activations. Corresponds to the JSON property l1RegActivation

Returns:

  • (Float) 


10786
10787
10788
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10786

def l1_reg_activation
  @l1_reg_activation
end

#l1_regularization ⇒ Float

L1 regularization coefficient. Corresponds to the JSON property l1Regularization

Returns:

  • (Float) 


10791
10792
10793
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10791

def l1_regularization
  @l1_regularization
end

#l2_regularization ⇒ Float

L2 regularization coefficient. Corresponds to the JSON property l2Regularization

Returns:

  • (Float) 


10796
10797
10798
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10796

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>) 


10802
10803
10804
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10802

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) 


10807
10808
10809
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10807

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) 


10812
10813
10814
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10812

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) 


10817
10818
10819
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10817

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) 


10823
10824
10825
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10823

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) 


10828
10829
10830
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10828

def max_parallel_trials
  @max_parallel_trials
end

#max_time_series_length ⇒ Fixnum

The maximum number of time points in a time series that can be used in modeling the trend component of the time series. Don't use this option with the timeSeriesLengthFraction or minTimeSeriesLength options. Corresponds to the JSON property maxTimeSeriesLength

Returns:

  • (Fixnum) 


10835
10836
10837
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10835

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) 


10840
10841
10842
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10840

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) 


10846
10847
10848
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10846

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) 


10851
10852
10853
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10851

def min_split_loss
  @min_split_loss
end

#min_time_series_length ⇒ Fixnum

The minimum number of time points in a time series that are used in modeling the trend component of the time series. If you use this option you must also set the timeSeriesLengthFraction option. This training option ensures that enough time points are available when you use timeSeriesLengthFraction in trend modeling. This is particularly important when forecasting multiple time series in a single query using timeSeriesIdColumn. If the total number of time points is less than the minTimeSeriesLength value, then the query uses all available time points. Corresponds to the JSON property minTimeSeriesLength

Returns:

  • (Fixnum) 


10863
10864
10865
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10863

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) 


10868
10869
10870
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10868

def min_tree_child_weight
  @min_tree_child_weight
end

#model_registry ⇒ String

The model registry. Corresponds to the JSON property modelRegistry

Returns:

  • (String) 


10873
10874
10875
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10873

def model_registry
  @model_registry
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) 


10879
10880
10881
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10879

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:



10884
10885
10886
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10884

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) 


10889
10890
10891
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10889

def num_clusters
  @num_clusters
end

#num_factors ⇒ Fixnum

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

Returns:

  • (Fixnum) 


10894
10895
10896
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10894

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) 


10900
10901
10902
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10900

def num_parallel_tree
  @num_parallel_tree
end

#num_principal_components ⇒ Fixnum

Number of principal components to keep in the PCA model. Must be <= the number of features. Corresponds to the JSON property numPrincipalComponents

Returns:

  • (Fixnum) 


10906
10907
10908
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10906

def num_principal_components
  @num_principal_components
end

#num_trials ⇒ Fixnum

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

Returns:

  • (Fixnum) 


10911
10912
10913
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10911

def num_trials
  @num_trials
end

#optimization_strategy ⇒ String

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

Returns:

  • (String) 


10916
10917
10918
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10916

def optimization_strategy
  @optimization_strategy
end

#optimizer ⇒ String

Optimizer used for training the neural nets. Corresponds to the JSON property optimizer

Returns:

  • (String) 


10921
10922
10923
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10921

def optimizer
  @optimizer
end

#pca_explained_variance_ratio ⇒ Float

The minimum ratio of cumulative explained variance that needs to be given by the PCA model. Corresponds to the JSON property pcaExplainedVarianceRatio

Returns:

  • (Float) 


10927
10928
10929
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10927

def pca_explained_variance_ratio
  @pca_explained_variance_ratio
end

#pca_solver ⇒ String

The solver for PCA. Corresponds to the JSON property pcaSolver

Returns:

  • (String) 


10932
10933
10934
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10932

def pca_solver
  @pca_solver
end

#sampled_shapley_num_paths ⇒ Fixnum

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

Returns:

  • (Fixnum) 


10937
10938
10939
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10937

def sampled_shapley_num_paths
  @sampled_shapley_num_paths
end

#scale_features ⇒ Boolean Also known as: scale_features?

If true, scale the feature values by dividing the feature standard deviation. Currently only apply to PCA. Corresponds to the JSON property scaleFeatures

Returns:

  • (Boolean) 


10943
10944
10945
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10943

def scale_features
  @scale_features
end

#standardize_features ⇒ Boolean Also known as: standardize_features?

Whether to standardize numerical features. Default to true. Corresponds to the JSON property standardizeFeatures

Returns:

  • (Boolean) 


10949
10950
10951
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10949

def standardize_features
  @standardize_features
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) 


10956
10957
10958
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10956

def subsample
  @subsample
end

#tf_version ⇒ String

Based on the selected TF version, the corresponding docker image is used to train external models. Corresponds to the JSON property tfVersion

Returns:

  • (String) 


10962
10963
10964
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10962

def tf_version
  @tf_version
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) 


10967
10968
10969
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10967

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) 


10972
10973
10974
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10972

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>) 


10977
10978
10979
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10977

def time_series_id_columns
  @time_series_id_columns
end

#time_series_length_fraction ⇒ Float

The fraction of the interpolated length of the time series that's used to model the time series trend component. All of the time points of the time series are used to model the non-trend component. This training option accelerates modeling training without sacrificing much forecasting accuracy. You can use this option with minTimeSeriesLength but not with maxTimeSeriesLength. Corresponds to the JSON property timeSeriesLengthFraction

Returns:

  • (Float) 


10987
10988
10989
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10987

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) 


10992
10993
10994
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10992

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) 


10997
10998
10999
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 10997

def tree_method
  @tree_method
end

#trend_smoothing_window_size ⇒ Fixnum

Smoothing window size for the trend component. When a positive value is specified, a center moving average smoothing is applied on the history trend. When the smoothing window is out of the boundary at the beginning or the end of the trend, the first element or the last element is padded to fill the smoothing window before the average is applied. Corresponds to the JSON property trendSmoothingWindowSize

Returns:

  • (Fixnum) 


11006
11007
11008
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 11006

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) 


11011
11012
11013
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 11011

def user_column
  @user_column
end

#vertex_ai_model_version_aliases ⇒ Array<String>

The version aliases to apply in Vertex AI model registry. Always overwrite if the version aliases exists in a existing model. Corresponds to the JSON property vertexAiModelVersionAliases

Returns:

  • (Array<String>) 


11017
11018
11019
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 11017

def vertex_ai_model_version_aliases
  @vertex_ai_model_version_aliases
end

#wals_alpha ⇒ Float

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

Returns:

  • (Float) 


11022
11023
11024
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 11022

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) 


11027
11028
11029
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 11027

def warm_start
  @warm_start
end

#xgboost_version ⇒ String

User-selected XGBoost versions for training of XGBoost models. Corresponds to the JSON property xgboostVersion

Returns:

  • (String) 


11033
11034
11035
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 11033

def xgboost_version
  @xgboost_version
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



11040
11041
11042
11043
11044
11045
11046
11047
11048
11049
11050
11051
11052
11053
11054
11055
11056
11057
11058
11059
11060
11061
11062
11063
11064
11065
11066
11067
11068
11069
11070
11071
11072
11073
11074
11075
11076
11077
11078
11079
11080
11081
11082
11083
11084
11085
11086
11087
11088
11089
11090
11091
11092
11093
11094
11095
11096
11097
11098
11099
11100
11101
11102
11103
11104
11105
11106
11107
11108
11109
11110
11111
11112
11113
11114
11115
11116
11117
11118
11119
11120
11121
11122
11123
11124
11125
11126
11127
 
# File 'lib/google/apis/bigquery_v2/classes.rb', line 11040

def update!(**args)
  @activation_fn = args[:activation_fn] if args.key?(:activation_fn)
  @adjust_step_changes = args[:adjust_step_changes] if args.key?(:adjust_step_changes)
  @approx_global_feature_contrib = args[:approx_global_feature_contrib] if args.key?(:approx_global_feature_contrib)
  @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)
  @auto_arima_min_order = args[:auto_arima_min_order] if args.key?(:auto_arima_min_order)
  @auto_class_weights = args[:auto_class_weights] if args.key?(:auto_class_weights)
  @batch_size = args[:batch_size] if args.key?(:batch_size)
  @booster_type = args[:booster_type] if args.key?(:booster_type)
  @budget_hours = args[:budget_hours] if args.key?(:budget_hours)
  @calculate_p_values = args[:calculate_p_values] if args.key?(:calculate_p_values)
  @category_encoding_method = args[:category_encoding_method] if args.key?(:category_encoding_method)
  @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)
  @fit_intercept = args[:fit_intercept] if args.key?(:fit_intercept)
  @hidden_units = args[:hidden_units] if args.key?(:hidden_units)
  @holiday_region = args[:holiday_region] if args.key?(:holiday_region)
  @holiday_regions = args[:holiday_regions] if args.key?(:holiday_regions)
  @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)
  @instance_weight_column = args[:instance_weight_column] if args.key?(:instance_weight_column)
  @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_reg_activation = args[:l1_reg_activation] if args.key?(:l1_reg_activation)
  @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_registry = args[:model_registry] if args.key?(:model_registry)
  @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_principal_components = args[:num_principal_components] if args.key?(:num_principal_components)
  @num_trials = args[:num_trials] if args.key?(:num_trials)
  @optimization_strategy = args[:optimization_strategy] if args.key?(:optimization_strategy)
  @optimizer = args[:optimizer] if args.key?(:optimizer)
  @pca_explained_variance_ratio = args[:pca_explained_variance_ratio] if args.key?(:pca_explained_variance_ratio)
  @pca_solver = args[:pca_solver] if args.key?(:pca_solver)
  @sampled_shapley_num_paths = args[:sampled_shapley_num_paths] if args.key?(:sampled_shapley_num_paths)
  @scale_features = args[:scale_features] if args.key?(:scale_features)
  @standardize_features = args[:standardize_features] if args.key?(:standardize_features)
  @subsample = args[:subsample] if args.key?(:subsample)
  @tf_version = args[:tf_version] if args.key?(:tf_version)
  @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)
  @vertex_ai_model_version_aliases = args[:vertex_ai_model_version_aliases] if args.key?(:vertex_ai_model_version_aliases)
  @wals_alpha = args[:wals_alpha] if args.key?(:wals_alpha)
  @warm_start = args[:warm_start] if args.key?(:warm_start)
  @xgboost_version = args[:xgboost_version] if args.key?(:xgboost_version)
end