definition

type AutoMlForecasting struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlForecastingInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// The metadata information.
	Metadata *AutoMlForecastingMetadata `protobuf:"bytes,2,opt,name=metadata,proto3" json:"metadata,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs struct {

	// The name of the column that the model is to predict.
	TargetColumn string `protobuf:"bytes,1,opt,name=target_column,json=targetColumn,proto3" json:"target_column,omitempty"`
	// The name of the column that identifies the time series.
	TimeSeriesIdentifierColumn string `` /* 143-byte string literal not displayed */
	// The name of the column that identifies time order in the time series.
	TimeColumn string `protobuf:"bytes,3,opt,name=time_column,json=timeColumn,proto3" json:"time_column,omitempty"`
	// 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.
	Transformations []*AutoMlForecastingInputs_Transformation `protobuf:"bytes,4,rep,name=transformations,proto3" json:"transformations,omitempty"`
	// 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`.
	OptimizationObjective string `protobuf:"bytes,5,opt,name=optimization_objective,json=optimizationObjective,proto3" json:"optimization_objective,omitempty"`
	// 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.
	TrainBudgetMilliNodeHours int64 `` /* 143-byte string literal not displayed */
	// 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.
	WeightColumn string `protobuf:"bytes,7,opt,name=weight_column,json=weightColumn,proto3" json:"weight_column,omitempty"`
	// Column names that should be used as static columns.
	// The value of these columns are static per time series.
	StaticColumns []string `protobuf:"bytes,8,rep,name=static_columns,json=staticColumns,proto3" json:"static_columns,omitempty"`
	// Column names that should be used as time variant past only columns.
	// This column contains information for the given entity (identified by the
	// time_series_identifier_column) that is known for the past but not the
	// future (e.g. population of a city in a given year, or weather on a given
	// day).
	TimeVariantPastOnlyColumns []string `` /* 145-byte string literal not displayed */
	// Column names that should be used as time variant past and future columns.
	// This column contains information for the given entity (identified by the
	// key column) that is known for the past and the future
	TimeVariantPastAndFutureColumns []string `` /* 163-byte string literal not displayed */
	// Expected difference in time granularity between rows in the data. If it is
	// not set, the period is inferred from data.
	Period *AutoMlForecastingInputs_Period `protobuf:"bytes,11,opt,name=period,proto3" json:"period,omitempty"`
	// The number of periods offset into the future as the start of the forecast
	// window (the window of future values to predict, relative to the present.),
	// where each period is one unit of granularity as defined by the `period`
	// field above. Default to 0. Inclusive.
	ForecastWindowStart int64 `protobuf:"varint,12,opt,name=forecast_window_start,json=forecastWindowStart,proto3" json:"forecast_window_start,omitempty"`
	// The number of periods offset into the future as the end of the forecast
	// window (the window of future values to predict, relative to the present.),
	// where each period is one unit of granularity as defined by the `period`
	// field above. Inclusive.
	ForecastWindowEnd int64 `protobuf:"varint,13,opt,name=forecast_window_end,json=forecastWindowEnd,proto3" json:"forecast_window_end,omitempty"`
	// The number of periods offset into the past to restrict past sequence, where
	// each period is one unit of granularity as defined by the `period`. Default
	// value 0 means that it lets algorithm to define the value. Inclusive.
	PastHorizon int64 `protobuf:"varint,14,opt,name=past_horizon,json=pastHorizon,proto3" json:"past_horizon,omitempty"`
	// Configuration for exporting test set predictions to a BigQuery table. If
	// this configuration is absent, then the export is not performed.
	ExportEvaluatedDataItemsConfig *ExportEvaluatedDataItemsConfig `` /* 158-byte string literal not displayed */
	// 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.
	Quantiles []float64 `protobuf:"fixed64,16,rep,packed,name=quantiles,proto3" json:"quantiles,omitempty"`
	// 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
	ValidationOptions string `protobuf:"bytes,17,opt,name=validation_options,json=validationOptions,proto3" json:"validation_options,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs_Period struct {

	// The time granularity unit of this time period.
	// The supported unit are:
	//  "minute"
	//  "hour"
	//  "day"
	//  "week"
	//  "month"
	//  "year"
	Unit string `protobuf:"bytes,1,opt,name=unit,proto3" json:"unit,omitempty"`
	// The number of units per period, e.g. 3 weeks or 2 months.
	Quantity int64 `protobuf:"varint,2,opt,name=quantity,proto3" json:"quantity,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs_Transformation struct {

	// The transformation that the training pipeline will apply to the input
	// columns.
	//
	// Types that are assignable to TransformationDetail:
	//	*AutoMlForecastingInputs_Transformation_Auto
	//	*AutoMlForecastingInputs_Transformation_Numeric
	//	*AutoMlForecastingInputs_Transformation_Categorical
	//	*AutoMlForecastingInputs_Transformation_Timestamp
	//	*AutoMlForecastingInputs_Transformation_Text
	//	*AutoMlForecastingInputs_Transformation_RepeatedNumeric
	//	*AutoMlForecastingInputs_Transformation_RepeatedCategorical
	//	*AutoMlForecastingInputs_Transformation_RepeatedText
	TransformationDetail isAutoMlForecastingInputs_Transformation_TransformationDetail `protobuf_oneof:"transformation_detail"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs_Transformation_Auto struct {
	Auto *AutoMlForecastingInputs_Transformation_AutoTransformation `protobuf:"bytes,1,opt,name=auto,proto3,oneof"`
}

type AutoMlForecastingInputs_Transformation_AutoTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs_Transformation_Categorical struct {
	Categorical *AutoMlForecastingInputs_Transformation_CategoricalTransformation `protobuf:"bytes,3,opt,name=categorical,proto3,oneof"`
}

type AutoMlForecastingInputs_Transformation_CategoricalArrayTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs_Transformation_CategoricalTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs_Transformation_Numeric struct {
	Numeric *AutoMlForecastingInputs_Transformation_NumericTransformation `protobuf:"bytes,2,opt,name=numeric,proto3,oneof"`
}

type AutoMlForecastingInputs_Transformation_NumericArrayTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// If invalid values is allowed, the training pipeline will create a
	// boolean feature that indicated whether the value is valid.
	// Otherwise, the training pipeline will discard the input row from
	// trainining data.
	InvalidValuesAllowed bool `protobuf:"varint,2,opt,name=invalid_values_allowed,json=invalidValuesAllowed,proto3" json:"invalid_values_allowed,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs_Transformation_NumericTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// If invalid values is allowed, the training pipeline will create a
	// boolean feature that indicated whether the value is valid.
	// Otherwise, the training pipeline will discard the input row from
	// trainining data.
	InvalidValuesAllowed bool `protobuf:"varint,2,opt,name=invalid_values_allowed,json=invalidValuesAllowed,proto3" json:"invalid_values_allowed,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs_Transformation_RepeatedCategorical struct {
	RepeatedCategorical *AutoMlForecastingInputs_Transformation_CategoricalArrayTransformation `protobuf:"bytes,7,opt,name=repeated_categorical,json=repeatedCategorical,proto3,oneof"`
}

type AutoMlForecastingInputs_Transformation_RepeatedNumeric struct {
	RepeatedNumeric *AutoMlForecastingInputs_Transformation_NumericArrayTransformation `protobuf:"bytes,6,opt,name=repeated_numeric,json=repeatedNumeric,proto3,oneof"`
}

type AutoMlForecastingInputs_Transformation_RepeatedText struct {
	RepeatedText *AutoMlForecastingInputs_Transformation_TextArrayTransformation `protobuf:"bytes,8,opt,name=repeated_text,json=repeatedText,proto3,oneof"`
}

type AutoMlForecastingInputs_Transformation_Text struct {
	Text *AutoMlForecastingInputs_Transformation_TextTransformation `protobuf:"bytes,5,opt,name=text,proto3,oneof"`
}

type AutoMlForecastingInputs_Transformation_TextArrayTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs_Transformation_TextTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingInputs_Transformation_Timestamp struct {
	Timestamp *AutoMlForecastingInputs_Transformation_TimestampTransformation `protobuf:"bytes,4,opt,name=timestamp,proto3,oneof"`
}

type AutoMlForecastingInputs_Transformation_TimestampTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// The format in which that time field is expressed. The time_format must
	// either be one of:
	// * `unix-seconds`
	// * `unix-milliseconds`
	// * `unix-microseconds`
	// * `unix-nanoseconds`
	// (for respectively number of seconds, milliseconds, microseconds and
	// nanoseconds since start of the Unix epoch);
	// or be written in `strftime` syntax. If time_format is not set, then the
	// default format is RFC 3339 `date-time` format, where
	// `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
	TimeFormat string `protobuf:"bytes,2,opt,name=time_format,json=timeFormat,proto3" json:"time_format,omitempty"`
	// If invalid values is allowed, the training pipeline will create a
	// boolean feature that indicated whether the value is valid.
	// Otherwise, the training pipeline will discard the input row from
	// trainining data.
	InvalidValuesAllowed bool `protobuf:"varint,3,opt,name=invalid_values_allowed,json=invalidValuesAllowed,proto3" json:"invalid_values_allowed,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlForecastingMetadata struct {

	// Output only. The actual training cost of the model, expressed in milli
	// node hours, i.e. 1,000 value in this field means 1 node hour. Guaranteed
	// to not exceed the train budget.
	TrainCostMilliNodeHours int64 `` /* 137-byte string literal not displayed */
	// contains filtered or unexported fields
}

type AutoMlImageClassification struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlImageClassificationInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// The metadata information.
	Metadata *AutoMlImageClassificationMetadata `protobuf:"bytes,2,opt,name=metadata,proto3" json:"metadata,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlImageClassificationInputs struct {
	ModelType AutoMlImageClassificationInputs_ModelType `` /* 193-byte string literal not displayed */
	// The ID of the `base` model. If it is specified, the new model will be
	// trained based on the `base` model. Otherwise, the new model will be
	// trained from scratch. The `base` model must be in the same
	// Project and Location as the new Model to train, and have the same
	// modelType.
	BaseModelId string `protobuf:"bytes,2,opt,name=base_model_id,json=baseModelId,proto3" json:"base_model_id,omitempty"`
	// The training budget of creating this model, expressed in milli node
	// hours i.e. 1,000 value in this field means 1 node hour. The actual
	// metadata.costMilliNodeHours will be equal or less than this value.
	// If further model training ceases to provide any improvements, it will
	// stop without using the full budget and the metadata.successfulStopReason
	// will be `model-converged`.
	// Note, node_hour  = actual_hour * number_of_nodes_involved.
	// For modelType `cloud`(default), the budget must be between 8,000
	// and 800,000 milli node hours, inclusive. The default value is 192,000
	// which represents one day in wall time, considering 8 nodes are used.
	// For model types `mobile-tf-low-latency-1`, `mobile-tf-versatile-1`,
	// `mobile-tf-high-accuracy-1`, the training budget must be between
	// 1,000 and 100,000 milli node hours, inclusive.
	// The default value is 24,000 which represents one day in wall time on a
	// single node that is used.
	BudgetMilliNodeHours int64 `` /* 126-byte string literal not displayed */
	// Use the entire training budget. This disables the early stopping feature.
	// When false the early stopping feature is enabled, which means that
	// AutoML Image Classification might stop training before the entire
	// training budget has been used.
	DisableEarlyStopping bool `protobuf:"varint,4,opt,name=disable_early_stopping,json=disableEarlyStopping,proto3" json:"disable_early_stopping,omitempty"`
	// If false, a single-label (multi-class) Model will be trained (i.e.
	// assuming that for each image just up to one annotation may be
	// applicable). If true, a multi-label Model will be trained (i.e.
	// assuming that for each image multiple annotations may be applicable).
	MultiLabel bool `protobuf:"varint,5,opt,name=multi_label,json=multiLabel,proto3" json:"multi_label,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlImageClassificationInputs_ModelType int32

type AutoMlImageClassificationMetadata struct {

	// The actual training cost of creating this model, expressed in
	// milli node hours, i.e. 1,000 value in this field means 1 node hour.
	// Guaranteed to not exceed inputs.budgetMilliNodeHours.
	CostMilliNodeHours int64 `protobuf:"varint,1,opt,name=cost_milli_node_hours,json=costMilliNodeHours,proto3" json:"cost_milli_node_hours,omitempty"`
	// For successful job completions, this is the reason why the job has
	// finished.
	SuccessfulStopReason AutoMlImageClassificationMetadata_SuccessfulStopReason `` /* 241-byte string literal not displayed */
	// contains filtered or unexported fields
}

type AutoMlImageClassificationMetadata_SuccessfulStopReason int32

type AutoMlImageObjectDetection struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlImageObjectDetectionInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// The metadata information
	Metadata *AutoMlImageObjectDetectionMetadata `protobuf:"bytes,2,opt,name=metadata,proto3" json:"metadata,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlImageObjectDetectionInputs struct {
	ModelType AutoMlImageObjectDetectionInputs_ModelType `` /* 194-byte string literal not displayed */
	// The training budget of creating this model, expressed in milli node
	// hours i.e. 1,000 value in this field means 1 node hour. The actual
	// metadata.costMilliNodeHours will be equal or less than this value.
	// If further model training ceases to provide any improvements, it will
	// stop without using the full budget and the metadata.successfulStopReason
	// will be `model-converged`.
	// Note, node_hour  = actual_hour * number_of_nodes_involved.
	// For modelType `cloud`(default), the budget must be between 20,000
	// and 900,000 milli node hours, inclusive. The default value is 216,000
	// which represents one day in wall time, considering 9 nodes are used.
	// For model types `mobile-tf-low-latency-1`, `mobile-tf-versatile-1`,
	// `mobile-tf-high-accuracy-1`
	// the training budget must be between 1,000 and 100,000 milli node hours,
	// inclusive. The default value is 24,000 which represents one day in
	// wall time on a single node that is used.
	BudgetMilliNodeHours int64 `` /* 126-byte string literal not displayed */
	// Use the entire training budget. This disables the early stopping feature.
	// When false the early stopping feature is enabled, which means that AutoML
	// Image Object Detection might stop training before the entire training
	// budget has been used.
	DisableEarlyStopping bool `protobuf:"varint,3,opt,name=disable_early_stopping,json=disableEarlyStopping,proto3" json:"disable_early_stopping,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlImageObjectDetectionInputs_ModelType int32

type AutoMlImageObjectDetectionMetadata struct {

	// The actual training cost of creating this model, expressed in
	// milli node hours, i.e. 1,000 value in this field means 1 node hour.
	// Guaranteed to not exceed inputs.budgetMilliNodeHours.
	CostMilliNodeHours int64 `protobuf:"varint,1,opt,name=cost_milli_node_hours,json=costMilliNodeHours,proto3" json:"cost_milli_node_hours,omitempty"`
	// For successful job completions, this is the reason why the job has
	// finished.
	SuccessfulStopReason AutoMlImageObjectDetectionMetadata_SuccessfulStopReason `` /* 242-byte string literal not displayed */
	// contains filtered or unexported fields
}

type AutoMlImageObjectDetectionMetadata_SuccessfulStopReason int32

type AutoMlImageSegmentation struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlImageSegmentationInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// The metadata information.
	Metadata *AutoMlImageSegmentationMetadata `protobuf:"bytes,2,opt,name=metadata,proto3" json:"metadata,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlImageSegmentationInputs struct {
	ModelType AutoMlImageSegmentationInputs_ModelType `` /* 191-byte string literal not displayed */
	// The training budget of creating this model, expressed in milli node
	// hours i.e. 1,000 value in this field means 1 node hour. The actual
	// metadata.costMilliNodeHours will be equal or less than this value.
	// If further model training ceases to provide any improvements, it will
	// stop without using the full budget and the metadata.successfulStopReason
	// will be `model-converged`.
	// Note, node_hour  = actual_hour * number_of_nodes_involved. Or
	// actaul_wall_clock_hours = train_budget_milli_node_hours /
	//                           (number_of_nodes_involved * 1000)
	// For modelType `cloud-high-accuracy-1`(default), the budget must be between
	// 20,000 and 2,000,000 milli node hours, inclusive. The default value is
	// 192,000 which represents one day in wall time
	// (1000 milli * 24 hours * 8 nodes).
	BudgetMilliNodeHours int64 `` /* 126-byte string literal not displayed */
	// The ID of the `base` model. If it is specified, the new model will be
	// trained based on the `base` model. Otherwise, the new model will be
	// trained from scratch. The `base` model must be in the same
	// Project and Location as the new Model to train, and have the same
	// modelType.
	BaseModelId string `protobuf:"bytes,3,opt,name=base_model_id,json=baseModelId,proto3" json:"base_model_id,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlImageSegmentationInputs_ModelType int32

type AutoMlImageSegmentationMetadata struct {

	// The actual training cost of creating this model, expressed in
	// milli node hours, i.e. 1,000 value in this field means 1 node hour.
	// Guaranteed to not exceed inputs.budgetMilliNodeHours.
	CostMilliNodeHours int64 `protobuf:"varint,1,opt,name=cost_milli_node_hours,json=costMilliNodeHours,proto3" json:"cost_milli_node_hours,omitempty"`
	// For successful job completions, this is the reason why the job has
	// finished.
	SuccessfulStopReason AutoMlImageSegmentationMetadata_SuccessfulStopReason `` /* 239-byte string literal not displayed */
	// contains filtered or unexported fields
}

type AutoMlImageSegmentationMetadata_SuccessfulStopReason int32

type AutoMlTables struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlTablesInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// The metadata information.
	Metadata *AutoMlTablesMetadata `protobuf:"bytes,2,opt,name=metadata,proto3" json:"metadata,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTablesInputs struct {

	// Additional optimization objective configuration. Required for
	// `maximize-precision-at-recall` and `maximize-recall-at-precision`,
	// otherwise unused.
	//
	// Types that are assignable to AdditionalOptimizationObjectiveConfig:
	//	*AutoMlTablesInputs_OptimizationObjectiveRecallValue
	//	*AutoMlTablesInputs_OptimizationObjectivePrecisionValue
	AdditionalOptimizationObjectiveConfig isAutoMlTablesInputs_AdditionalOptimizationObjectiveConfig `protobuf_oneof:"additional_optimization_objective_config"`
	// The type of prediction the Model is to produce.
	//   "classification" - Predict one out of multiple target values is
	//                      picked for each row.
	//   "regression" - Predict a value based on its relation to other values.
	//                  This type is available only to columns that contain
	//                  semantically numeric values, i.e. integers or floating
	//                  point number, even if stored as e.g. strings.
	PredictionType string `protobuf:"bytes,1,opt,name=prediction_type,json=predictionType,proto3" json:"prediction_type,omitempty"`
	// The column name of the target column that the model is to predict.
	TargetColumn string `protobuf:"bytes,2,opt,name=target_column,json=targetColumn,proto3" json:"target_column,omitempty"`
	// 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.
	Transformations []*AutoMlTablesInputs_Transformation `protobuf:"bytes,3,rep,name=transformations,proto3" json:"transformations,omitempty"`
	// Objective function the model is optimizing towards. The training process
	// creates a model that maximizes/minimizes the value of the objective
	// function over the validation set.
	//
	// The supported optimization objectives depend on the prediction type.
	// If the field is not set, a default objective function is used.
	//
	// classification (binary):
	//   "maximize-au-roc" (default) - Maximize the area under the receiver
	//                                 operating characteristic (ROC) curve.
	//   "minimize-log-loss" - Minimize log loss.
	//   "maximize-au-prc" - Maximize the area under the precision-recall curve.
	//   "maximize-precision-at-recall" - Maximize precision for a specified
	//                                   recall value.
	//   "maximize-recall-at-precision" - Maximize recall for a specified
	//                                    precision value.
	//
	// classification (multi-class):
	//   "minimize-log-loss" (default) - Minimize log loss.
	//
	// regression:
	//   "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).
	OptimizationObjective string `protobuf:"bytes,4,opt,name=optimization_objective,json=optimizationObjective,proto3" json:"optimization_objective,omitempty"`
	// 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.
	TrainBudgetMilliNodeHours int64 `` /* 143-byte string literal not displayed */
	// Use the entire training budget. This disables the early stopping feature.
	// By default, the early stopping feature is enabled, which means that AutoML
	// Tables might stop training before the entire training budget has been used.
	DisableEarlyStopping bool `protobuf:"varint,8,opt,name=disable_early_stopping,json=disableEarlyStopping,proto3" json:"disable_early_stopping,omitempty"`
	// 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.
	WeightColumnName string `protobuf:"bytes,9,opt,name=weight_column_name,json=weightColumnName,proto3" json:"weight_column_name,omitempty"`
	// Configuration for exporting test set predictions to a BigQuery table. If
	// this configuration is absent, then the export is not performed.
	ExportEvaluatedDataItemsConfig *ExportEvaluatedDataItemsConfig `` /* 158-byte string literal not displayed */
	// contains filtered or unexported fields
}

type AutoMlTablesInputs_OptimizationObjectivePrecisionValue struct {
	// Required when optimization_objective is "maximize-recall-at-precision".
	// Must be between 0 and 1, inclusive.
	OptimizationObjectivePrecisionValue float32 `protobuf:"fixed32,6,opt,name=optimization_objective_precision_value,json=optimizationObjectivePrecisionValue,proto3,oneof"`
}

type AutoMlTablesInputs_OptimizationObjectiveRecallValue struct {
	// Required when optimization_objective is "maximize-precision-at-recall".
	// Must be between 0 and 1, inclusive.
	OptimizationObjectiveRecallValue float32 `protobuf:"fixed32,5,opt,name=optimization_objective_recall_value,json=optimizationObjectiveRecallValue,proto3,oneof"`
}

type AutoMlTablesInputs_Transformation struct {

	// The transformation that the training pipeline will apply to the input
	// columns.
	//
	// Types that are assignable to TransformationDetail:
	//	*AutoMlTablesInputs_Transformation_Auto
	//	*AutoMlTablesInputs_Transformation_Numeric
	//	*AutoMlTablesInputs_Transformation_Categorical
	//	*AutoMlTablesInputs_Transformation_Timestamp
	//	*AutoMlTablesInputs_Transformation_Text
	//	*AutoMlTablesInputs_Transformation_RepeatedNumeric
	//	*AutoMlTablesInputs_Transformation_RepeatedCategorical
	//	*AutoMlTablesInputs_Transformation_RepeatedText
	TransformationDetail isAutoMlTablesInputs_Transformation_TransformationDetail `protobuf_oneof:"transformation_detail"`
	// contains filtered or unexported fields
}

type AutoMlTablesInputs_Transformation_Auto struct {
	Auto *AutoMlTablesInputs_Transformation_AutoTransformation `protobuf:"bytes,1,opt,name=auto,proto3,oneof"`
}

type AutoMlTablesInputs_Transformation_AutoTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTablesInputs_Transformation_Categorical struct {
	Categorical *AutoMlTablesInputs_Transformation_CategoricalTransformation `protobuf:"bytes,3,opt,name=categorical,proto3,oneof"`
}

type AutoMlTablesInputs_Transformation_CategoricalArrayTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTablesInputs_Transformation_CategoricalTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTablesInputs_Transformation_Numeric struct {
	Numeric *AutoMlTablesInputs_Transformation_NumericTransformation `protobuf:"bytes,2,opt,name=numeric,proto3,oneof"`
}

type AutoMlTablesInputs_Transformation_NumericArrayTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// If invalid values is allowed, the training pipeline will create a
	// boolean feature that indicated whether the value is valid.
	// Otherwise, the training pipeline will discard the input row from
	// trainining data.
	InvalidValuesAllowed bool `protobuf:"varint,2,opt,name=invalid_values_allowed,json=invalidValuesAllowed,proto3" json:"invalid_values_allowed,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTablesInputs_Transformation_NumericTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// If invalid values is allowed, the training pipeline will create a
	// boolean feature that indicated whether the value is valid.
	// Otherwise, the training pipeline will discard the input row from
	// trainining data.
	InvalidValuesAllowed bool `protobuf:"varint,2,opt,name=invalid_values_allowed,json=invalidValuesAllowed,proto3" json:"invalid_values_allowed,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTablesInputs_Transformation_RepeatedCategorical struct {
	RepeatedCategorical *AutoMlTablesInputs_Transformation_CategoricalArrayTransformation `protobuf:"bytes,7,opt,name=repeated_categorical,json=repeatedCategorical,proto3,oneof"`
}

type AutoMlTablesInputs_Transformation_RepeatedNumeric struct {
	RepeatedNumeric *AutoMlTablesInputs_Transformation_NumericArrayTransformation `protobuf:"bytes,6,opt,name=repeated_numeric,json=repeatedNumeric,proto3,oneof"`
}

type AutoMlTablesInputs_Transformation_RepeatedText struct {
	RepeatedText *AutoMlTablesInputs_Transformation_TextArrayTransformation `protobuf:"bytes,8,opt,name=repeated_text,json=repeatedText,proto3,oneof"`
}

type AutoMlTablesInputs_Transformation_Text struct {
	Text *AutoMlTablesInputs_Transformation_TextTransformation `protobuf:"bytes,5,opt,name=text,proto3,oneof"`
}

type AutoMlTablesInputs_Transformation_TextArrayTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTablesInputs_Transformation_TextTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTablesInputs_Transformation_Timestamp struct {
	Timestamp *AutoMlTablesInputs_Transformation_TimestampTransformation `protobuf:"bytes,4,opt,name=timestamp,proto3,oneof"`
}

type AutoMlTablesInputs_Transformation_TimestampTransformation struct {
	ColumnName string `protobuf:"bytes,1,opt,name=column_name,json=columnName,proto3" json:"column_name,omitempty"`
	// The format in which that time field is expressed. The time_format must
	// either be one of:
	// * `unix-seconds`
	// * `unix-milliseconds`
	// * `unix-microseconds`
	// * `unix-nanoseconds`
	// (for respectively number of seconds, milliseconds, microseconds and
	// nanoseconds since start of the Unix epoch);
	// or be written in `strftime` syntax. If time_format is not set, then the
	// default format is RFC 3339 `date-time` format, where
	// `time-offset` = `"Z"` (e.g. 1985-04-12T23:20:50.52Z)
	TimeFormat string `protobuf:"bytes,2,opt,name=time_format,json=timeFormat,proto3" json:"time_format,omitempty"`
	// If invalid values is allowed, the training pipeline will create a
	// boolean feature that indicated whether the value is valid.
	// Otherwise, the training pipeline will discard the input row from
	// trainining data.
	InvalidValuesAllowed bool `protobuf:"varint,3,opt,name=invalid_values_allowed,json=invalidValuesAllowed,proto3" json:"invalid_values_allowed,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTablesMetadata struct {

	// Output only. The actual training cost of the model, expressed in milli
	// node hours, i.e. 1,000 value in this field means 1 node hour. Guaranteed
	// to not exceed the train budget.
	TrainCostMilliNodeHours int64 `` /* 137-byte string literal not displayed */
	// contains filtered or unexported fields
}

type AutoMlTextClassification struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlTextClassificationInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTextClassificationInputs struct {
	MultiLabel bool `protobuf:"varint,1,opt,name=multi_label,json=multiLabel,proto3" json:"multi_label,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTextExtraction struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlTextExtractionInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTextExtractionInputs struct {
	// contains filtered or unexported fields
}

type AutoMlTextSentiment struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlTextSentimentInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlTextSentimentInputs struct {

	// A sentiment is expressed as an integer ordinal, where higher value
	// means a more positive sentiment. The range of sentiments that will be used
	// is between 0 and sentimentMax (inclusive on both ends), and all the values
	// in the range must be represented in the dataset before a model can be
	// created.
	// Only the Annotations with this sentimentMax will be used for training.
	// sentimentMax value must be between 1 and 10 (inclusive).
	SentimentMax int32 `protobuf:"varint,1,opt,name=sentiment_max,json=sentimentMax,proto3" json:"sentiment_max,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlVideoActionRecognition struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlVideoActionRecognitionInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlVideoActionRecognitionInputs struct {
	ModelType AutoMlVideoActionRecognitionInputs_ModelType `` /* 196-byte string literal not displayed */
	// contains filtered or unexported fields
}

type AutoMlVideoActionRecognitionInputs_ModelType int32

type AutoMlVideoClassification struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlVideoClassificationInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlVideoClassificationInputs struct {
	ModelType AutoMlVideoClassificationInputs_ModelType `` /* 193-byte string literal not displayed */
	// contains filtered or unexported fields
}

type AutoMlVideoClassificationInputs_ModelType int32

type AutoMlVideoObjectTracking struct {

	// The input parameters of this TrainingJob.
	Inputs *AutoMlVideoObjectTrackingInputs `protobuf:"bytes,1,opt,name=inputs,proto3" json:"inputs,omitempty"`
	// contains filtered or unexported fields
}

type AutoMlVideoObjectTrackingInputs struct {
	ModelType AutoMlVideoObjectTrackingInputs_ModelType `` /* 193-byte string literal not displayed */
	// contains filtered or unexported fields
}

type AutoMlVideoObjectTrackingInputs_ModelType int32

type ExportEvaluatedDataItemsConfig struct {

	// URI of desired destination BigQuery table. Expected format:
	// bq://<project_id>:<dataset_id>:<table>
	//
	// If not specified, then results are exported to the following auto-created
	// BigQuery table:
	//
	// <project_id>:export_evaluated_examples_<model_name>_<yyyy_MM_dd'T'HH_mm_ss_SSS'Z'>.evaluated_examples
	DestinationBigqueryUri string `` /* 129-byte string literal not displayed */
	// If true and an export destination is specified, then the contents of the
	// destination are overwritten. Otherwise, if the export destination already
	// exists, then the export operation fails.
	OverrideExistingTable bool `` /* 127-byte string literal not displayed */
	// contains filtered or unexported fields
}