Interface AutoMlForecastingInputsOrBuilder (3.42.0)

public interface AutoMlForecastingInputsOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getAdditionalExperiments(int index)

public abstract String getAdditionalExperiments(int index)

Additional experiment flags for the time series forcasting training.

repeated string additional_experiments = 25;

Parameter
Name	Description
`index`	`int` The index of the element to return.

Returns
Type	Description
`String`	The additionalExperiments at the given index.

getAdditionalExperimentsBytes(int index)

public abstract ByteString getAdditionalExperimentsBytes(int index)

Additional experiment flags for the time series forcasting training.

repeated string additional_experiments = 25;

Parameter
Name	Description
`index`	`int` The index of the value to return.

Returns
Type	Description
`ByteString`	The bytes of the additionalExperiments at the given index.

getAdditionalExperimentsCount()

public abstract int getAdditionalExperimentsCount()

Additional experiment flags for the time series forcasting training.

repeated string additional_experiments = 25;

Returns
Type	Description
`int`	The count of additionalExperiments.

getAdditionalExperimentsList()

public abstract List<String> getAdditionalExperimentsList()

Additional experiment flags for the time series forcasting training.

repeated string additional_experiments = 25;

Returns
Type	Description
`List<String>`	A list containing the additionalExperiments.

getAvailableAtForecastColumns(int index)

public abstract String getAvailableAtForecastColumns(int index)

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.

repeated string available_at_forecast_columns = 21;

Parameter
Name	Description
`index`	`int` The index of the element to return.

Returns
Type	Description
`String`	The availableAtForecastColumns at the given index.

getAvailableAtForecastColumnsBytes(int index)

public abstract ByteString getAvailableAtForecastColumnsBytes(int index)

repeated string available_at_forecast_columns = 21;

Parameter
Name	Description
`index`	`int` The index of the value to return.

Returns
Type	Description
`ByteString`	The bytes of the availableAtForecastColumns at the given index.

getAvailableAtForecastColumnsCount()

public abstract int getAvailableAtForecastColumnsCount()

repeated string available_at_forecast_columns = 21;

Returns
Type	Description
`int`	The count of availableAtForecastColumns.

getAvailableAtForecastColumnsList()

public abstract List<String> getAvailableAtForecastColumnsList()

repeated string available_at_forecast_columns = 21;

Returns
Type	Description
`List<String>`	A list containing the availableAtForecastColumns.

getContextWindow()

public abstract long getContextWindow()

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.

int64 context_window = 24;

Returns
Type	Description
`long`	The contextWindow.

getDataGranularity()

public abstract AutoMlForecastingInputs.Granularity getDataGranularity()

Expected difference in time granularity between rows in the data.

.google.cloud.aiplatform.v1beta1.schema.trainingjob.definition.AutoMlForecastingInputs.Granularity data_granularity = 22;

Returns
Type	Description
`AutoMlForecastingInputs.Granularity`	The dataGranularity.

getDataGranularityOrBuilder()

public abstract AutoMlForecastingInputs.GranularityOrBuilder getDataGranularityOrBuilder()

Expected difference in time granularity between rows in the data.

.google.cloud.aiplatform.v1beta1.schema.trainingjob.definition.AutoMlForecastingInputs.Granularity data_granularity = 22;

Returns
Type	Description
`AutoMlForecastingInputs.GranularityOrBuilder`

getExportEvaluatedDataItemsConfig()

public abstract ExportEvaluatedDataItemsConfig getExportEvaluatedDataItemsConfig()

Configuration for exporting test set predictions to a BigQuery table. If this configuration is absent, then the export is not performed.

.google.cloud.aiplatform.v1beta1.schema.trainingjob.definition.ExportEvaluatedDataItemsConfig export_evaluated_data_items_config = 15;

Returns
Type	Description
`ExportEvaluatedDataItemsConfig`	The exportEvaluatedDataItemsConfig.

getExportEvaluatedDataItemsConfigOrBuilder()

public abstract ExportEvaluatedDataItemsConfigOrBuilder getExportEvaluatedDataItemsConfigOrBuilder()

Configuration for exporting test set predictions to a BigQuery table. If this configuration is absent, then the export is not performed.

.google.cloud.aiplatform.v1beta1.schema.trainingjob.definition.ExportEvaluatedDataItemsConfig export_evaluated_data_items_config = 15;

Returns
Type	Description
`ExportEvaluatedDataItemsConfigOrBuilder`

getForecastHorizon()

public abstract long getForecastHorizon()

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.

int64 forecast_horizon = 23;

Returns
Type	Description
`long`	The forecastHorizon.

getOptimizationObjective()

public abstract String getOptimizationObjective()

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.

string optimization_objective = 5;

Returns
Type	Description
`String`	The optimizationObjective.

getOptimizationObjectiveBytes()

public abstract ByteString getOptimizationObjectiveBytes()

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.

string optimization_objective = 5;

Returns
Type	Description
`ByteString`	The bytes for optimizationObjective.

getQuantiles(int index)

public abstract double getQuantiles(int index)

Quantiles to use for minimize-quantile-loss optimization_objective. 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.

repeated double quantiles = 16;

Parameter
Name	Description
`index`	`int` The index of the element to return.

Returns
Type	Description
`double`	The quantiles at the given index.

getQuantilesCount()

public abstract int getQuantilesCount()

repeated double quantiles = 16;

Returns
Type	Description
`int`	The count of quantiles.

getQuantilesList()

public abstract List<Double> getQuantilesList()

repeated double quantiles = 16;

Returns
Type	Description
`List<Double>`	A list containing the quantiles.

getTargetColumn()

public abstract String getTargetColumn()

The name of the column that the model is to predict.

string target_column = 1;

Returns
Type	Description
`String`	The targetColumn.

getTargetColumnBytes()

public abstract ByteString getTargetColumnBytes()

The name of the column that the model is to predict.

string target_column = 1;

Returns
Type	Description
`ByteString`	The bytes for targetColumn.

getTimeColumn()

public abstract String getTimeColumn()

The name of the column that identifies time order in the time series.

string time_column = 3;

Returns
Type	Description
`String`	The timeColumn.

getTimeColumnBytes()

public abstract ByteString getTimeColumnBytes()

The name of the column that identifies time order in the time series.

string time_column = 3;

Returns
Type	Description
`ByteString`	The bytes for timeColumn.

getTimeSeriesAttributeColumns(int index)

public abstract String getTimeSeriesAttributeColumns(int index)

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.

repeated string time_series_attribute_columns = 19;

Parameter
Name	Description
`index`	`int` The index of the element to return.

Returns
Type	Description
`String`	The timeSeriesAttributeColumns at the given index.

getTimeSeriesAttributeColumnsBytes(int index)

public abstract ByteString getTimeSeriesAttributeColumnsBytes(int index)

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.

repeated string time_series_attribute_columns = 19;

Parameter
Name	Description
`index`	`int` The index of the value to return.

Returns
Type	Description
`ByteString`	The bytes of the timeSeriesAttributeColumns at the given index.

getTimeSeriesAttributeColumnsCount()

public abstract int getTimeSeriesAttributeColumnsCount()

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.

repeated string time_series_attribute_columns = 19;

Returns
Type	Description
`int`	The count of timeSeriesAttributeColumns.

getTimeSeriesAttributeColumnsList()

public abstract List<String> getTimeSeriesAttributeColumnsList()

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.

repeated string time_series_attribute_columns = 19;

Returns
Type	Description
`List<String>`	A list containing the timeSeriesAttributeColumns.

getTimeSeriesIdentifierColumn()

public abstract String getTimeSeriesIdentifierColumn()

The name of the column that identifies the time series.

string time_series_identifier_column = 2;

Returns
Type	Description
`String`	The timeSeriesIdentifierColumn.

getTimeSeriesIdentifierColumnBytes()

public abstract ByteString getTimeSeriesIdentifierColumnBytes()

The name of the column that identifies the time series.

string time_series_identifier_column = 2;

Returns
Type	Description
`ByteString`	The bytes for timeSeriesIdentifierColumn.

getTrainBudgetMilliNodeHours()

public abstract long getTrainBudgetMilliNodeHours()

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.

int64 train_budget_milli_node_hours = 6;

Returns
Type	Description
`long`	The trainBudgetMilliNodeHours.

getTransformations(int index)

public abstract AutoMlForecastingInputs.Transformation getTransformations(int index)

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.