Class: Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionAutoMlForecastingInputs

Inherits:
Object
  • Object
show all
Includes:
Core::Hashable, Core::JsonObjectSupport
Defined in:
lib/google/apis/aiplatform_v1/classes.rb,
lib/google/apis/aiplatform_v1/representations.rb,
lib/google/apis/aiplatform_v1/representations.rb

Instance Attribute Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize(**args) ⇒ GoogleCloudAiplatformV1SchemaTrainingjobDefinitionAutoMlForecastingInputs

Returns a new instance of GoogleCloudAiplatformV1SchemaTrainingjobDefinitionAutoMlForecastingInputs.



22746
22747
22748
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22746

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

Instance Attribute Details

#additional_experiments ⇒ Array<String>

Additional experiment flags for the time series forcasting training. Corresponds to the JSON property additionalExperiments

Returns:

  • (Array<String>) 


22582
22583
22584
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22582

def additional_experiments
  @additional_experiments
end

#available_at_forecast_columns ⇒ Array<String>

Names of columns that are available and provided when a forecast is requested. These columns contain information for the given entity (identified by the time_series_identifier_column column) that is known at forecast. For example, predicted weather for a specific day. Corresponds to the JSON property availableAtForecastColumns

Returns:

  • (Array<String>) 


22590
22591
22592
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22590

def available_at_forecast_columns
  @available_at_forecast_columns
end

#context_window ⇒ Fixnum

The amount of time into the past training and prediction data is used for model training and prediction respectively. Expressed in number of units defined by the data_granularity field. Corresponds to the JSON property contextWindow

Returns:

  • (Fixnum) 


22597
22598
22599
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22597

def context_window
  @context_window
end

#data_granularity ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionAutoMlForecastingInputsGranularity

A duration of time expressed in time granularity units. Corresponds to the JSON property dataGranularity

Returns:



22602
22603
22604
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22602

def data_granularity
  @data_granularity
end

#enable_probabilistic_inference ⇒ Boolean Also known as: enable_probabilistic_inference?

If probabilistic inference is enabled, the model will fit a distribution that captures the uncertainty of a prediction. At inference time, the predictive distribution is used to make a point prediction that minimizes the optimization objective. For example, the mean of a predictive distribution is the point prediction that minimizes RMSE loss. If quantiles are specified, then the quantiles of the distribution are also returned. The optimization objective cannot be minimize-quantile-loss. Corresponds to the JSON property enableProbabilisticInference

Returns:

  • (Boolean) 


22613
22614
22615
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22613

def enable_probabilistic_inference
  @enable_probabilistic_inference
end

#export_evaluated_data_items_config ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionExportEvaluatedDataItemsConfig

Configuration for exporting test set predictions to a BigQuery table. Corresponds to the JSON property exportEvaluatedDataItemsConfig

Returns:



22619
22620
22621
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22619

def export_evaluated_data_items_config
  @export_evaluated_data_items_config
end

#forecast_horizon ⇒ Fixnum

The amount of time into the future for which forecasted values for the target are returned. Expressed in number of units defined by the data_granularity field. Corresponds to the JSON property forecastHorizon

Returns:

  • (Fixnum) 


22626
22627
22628
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22626

def forecast_horizon
  @forecast_horizon
end

#hierarchy_config ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionHierarchyConfig

Configuration that defines the hierarchical relationship of time series and parameters for hierarchical forecasting strategies. Corresponds to the JSON property hierarchyConfig

Returns:



22632
22633
22634
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22632

def hierarchy_config
  @hierarchy_config
end

#holiday_regions ⇒ Array<String>

The geographical region based on which the holiday effect is applied in modeling by adding holiday categorical array feature that include all holidays matching the date. This option only allowed when data_granularity is day. By default, holiday effect modeling is disabled. To turn it on, specify the holiday region using this option. Corresponds to the JSON property holidayRegions

Returns:

  • (Array<String>) 


22641
22642
22643
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22641

def holiday_regions
  @holiday_regions
end

#optimization_objective ⇒ String

Objective function the model is optimizing towards. The training process creates a model that optimizes the value of the objective function over the validation set. The supported optimization objectives: * "minimize-rmse" ( default) - Minimize root-mean-squared error (RMSE). * "minimize-mae" - Minimize mean-absolute error (MAE). * "minimize-rmsle" - Minimize root-mean- squared log error (RMSLE). * "minimize-rmspe" - Minimize root-mean-squared percentage error (RMSPE). * "minimize-wape-mae" - Minimize the combination of weighted absolute percentage error (WAPE) and mean-absolute-error (MAE). * " minimize-quantile-loss" - Minimize the quantile loss at the quantiles defined in quantiles. * "minimize-mape" - Minimize the mean absolute percentage error. Corresponds to the JSON property optimizationObjective

Returns:

  • (String) 


22656
22657
22658
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22656

def optimization_objective
  @optimization_objective
end

#quantiles ⇒ Array<Float>

Quantiles to use for minimize-quantile-loss optimization_objective, or for probabilistic inference. Up to 5 quantiles are allowed of values between 0 and 1, exclusive. Required if the value of optimization_objective is minimize- quantile-loss. Represents the percent quantiles to use for that objective. Quantiles must be unique. Corresponds to the JSON property quantiles

Returns:

  • (Array<Float>) 


22665
22666
22667
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22665

def quantiles
  @quantiles
end

#target_column ⇒ String

The name of the column that the Model is to predict values for. This column must be unavailable at forecast. Corresponds to the JSON property targetColumn

Returns:

  • (String) 


22671
22672
22673
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22671

def target_column
  @target_column
end

#time_column ⇒ String

The name of the column that identifies time order in the time series. This column must be available at forecast. Corresponds to the JSON property timeColumn

Returns:

  • (String) 


22677
22678
22679
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22677

def time_column
  @time_column
end

#time_series_attribute_columns ⇒ Array<String>

Column names that should be used as attribute columns. The value of these columns does not vary as a function of time. For example, store ID or item color. Corresponds to the JSON property timeSeriesAttributeColumns

Returns:

  • (Array<String>) 


22684
22685
22686
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22684

def time_series_attribute_columns
  @time_series_attribute_columns
end

#time_series_identifier_column ⇒ String

The name of the column that identifies the time series. Corresponds to the JSON property timeSeriesIdentifierColumn

Returns:

  • (String) 


22689
22690
22691
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22689

def time_series_identifier_column
  @time_series_identifier_column
end

#train_budget_milli_node_hours ⇒ Fixnum

Required. The train budget of creating this model, expressed in milli node hours i.e. 1,000 value in this field means 1 node hour. The training cost of the model will not exceed this budget. The final cost will be attempted to be close to the budget, though may end up being (even) noticeably smaller - at the backend's discretion. This especially may happen when further model training ceases to provide any improvements. If the budget is set to a value known to be insufficient to train a model for the given dataset, the training won't be attempted and will error. The train budget must be between 1,000 and 72,000 milli node hours, inclusive. Corresponds to the JSON property trainBudgetMilliNodeHours

Returns:

  • (Fixnum) 


22702
22703
22704
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22702

def train_budget_milli_node_hours
  @train_budget_milli_node_hours
end

#transformations ⇒ Array<Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionAutoMlForecastingInputsTransformation>

Each transformation will apply transform function to given input column. And the result will be used for training. When creating transformation for BigQuery Struct column, the column should be flattened using "." as the delimiter. Corresponds to the JSON property transformations

Returns:



22710
22711
22712
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22710

def transformations
  @transformations
end

#unavailable_at_forecast_columns ⇒ Array<String>

Names of columns that are unavailable when a forecast is requested. This column contains information for the given entity (identified by the time_series_identifier_column) that is unknown before the forecast For example, actual weather on a given day. Corresponds to the JSON property unavailableAtForecastColumns

Returns:

  • (Array<String>) 


22718
22719
22720
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22718

def unavailable_at_forecast_columns
  @unavailable_at_forecast_columns
end

#validation_options ⇒ String

Validation options for the data validation component. The available options are: * "fail-pipeline" - default, will validate against the validation and fail the pipeline if it fails. * "ignore-validation" - ignore the results of the validation and continue Corresponds to the JSON property validationOptions

Returns:

  • (String) 


22726
22727
22728
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22726

def validation_options
  @validation_options
end

#weight_column ⇒ String

Column name that should be used as the weight column. Higher values in this column give more importance to the row during model training. The column must have numeric values between 0 and 10000 inclusively; 0 means the row is ignored for training. If weight column field is not set, then all rows are assumed to have equal weight of 1. Corresponds to the JSON property weightColumn

Returns:

  • (String) 


22735
22736
22737
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22735

def weight_column
  @weight_column
end

#window_config ⇒ Google::Apis::AiplatformV1::GoogleCloudAiplatformV1SchemaTrainingjobDefinitionWindowConfig

Config that contains the strategy used to generate sliding windows in time series training. A window is a series of rows that comprise the context up to the time of prediction, and the horizon following. The corresponding row for each window marks the start of the forecast horizon. Each window is used as an input example for training/evaluation. Corresponds to the JSON property windowConfig

Returns:



22744
22745
22746
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22744

def window_config
  @window_config
end

Instance Method Details

#update!(**args) ⇒ Object

Update properties of this object



22751
22752
22753
22754
22755
22756
22757
22758
22759
22760
22761
22762
22763
22764
22765
22766
22767
22768
22769
22770
22771
22772
22773
 
# File 'lib/google/apis/aiplatform_v1/classes.rb', line 22751

def update!(**args)
  @additional_experiments = args[:additional_experiments] if args.key?(:additional_experiments)
  @available_at_forecast_columns = args[:available_at_forecast_columns] if args.key?(:available_at_forecast_columns)
  @context_window = args[:context_window] if args.key?(:context_window)
  @data_granularity = args[:data_granularity] if args.key?(:data_granularity)
  @enable_probabilistic_inference = args[:enable_probabilistic_inference] if args.key?(:enable_probabilistic_inference)
  @export_evaluated_data_items_config = args[:export_evaluated_data_items_config] if args.key?(:export_evaluated_data_items_config)
  @forecast_horizon = args[:forecast_horizon] if args.key?(:forecast_horizon)
  @hierarchy_config = args[:hierarchy_config] if args.key?(:hierarchy_config)
  @holiday_regions = args[:holiday_regions] if args.key?(:holiday_regions)
  @optimization_objective = args[:optimization_objective] if args.key?(:optimization_objective)
  @quantiles = args[:quantiles] if args.key?(:quantiles)
  @target_column = args[:target_column] if args.key?(:target_column)
  @time_column = args[:time_column] if args.key?(:time_column)
  @time_series_attribute_columns = args[:time_series_attribute_columns] if args.key?(:time_series_attribute_columns)
  @time_series_identifier_column = args[:time_series_identifier_column] if args.key?(:time_series_identifier_column)
  @train_budget_milli_node_hours = args[:train_budget_milli_node_hours] if args.key?(:train_budget_milli_node_hours)
  @transformations = args[:transformations] if args.key?(:transformations)
  @unavailable_at_forecast_columns = args[:unavailable_at_forecast_columns] if args.key?(:unavailable_at_forecast_columns)
  @validation_options = args[:validation_options] if args.key?(:validation_options)
  @weight_column = args[:weight_column] if args.key?(:weight_column)
  @window_config = args[:window_config] if args.key?(:window_config)
end