Class AutoMlTablesInputs.Builder (3.43.0)

public static final class AutoMlTablesInputs.Builder extends GeneratedMessageV3.Builder<AutoMlTablesInputs.Builder> implements AutoMlTablesInputsOrBuilder

Protobuf type google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs

Static Methods

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
Type Description
Descriptor

Methods

addAdditionalExperiments(String value)

public AutoMlTablesInputs.Builder addAdditionalExperiments(String value)

Additional experiment flags for the Tables training pipeline.

repeated string additional_experiments = 11;

Parameter
Name Description
value String

The additionalExperiments to add.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

addAdditionalExperimentsBytes(ByteString value)

public AutoMlTablesInputs.Builder addAdditionalExperimentsBytes(ByteString value)

Additional experiment flags for the Tables training pipeline.

repeated string additional_experiments = 11;

Parameter
Name Description
value ByteString

The bytes of the additionalExperiments to add.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

addAllAdditionalExperiments(Iterable<String> values)

public AutoMlTablesInputs.Builder addAllAdditionalExperiments(Iterable<String> values)

Additional experiment flags for the Tables training pipeline.

repeated string additional_experiments = 11;

Parameter
Name Description
values Iterable<String>

The additionalExperiments to add.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

addAllTransformations(Iterable<? extends AutoMlTablesInputs.Transformation> values)

public AutoMlTablesInputs.Builder addAllTransformations(Iterable<? extends AutoMlTablesInputs.Transformation> values)

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameter
Name Description
values Iterable<? extends com.google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation>
Returns
Type Description
AutoMlTablesInputs.Builder

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public AutoMlTablesInputs.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
Name Description
field FieldDescriptor
value Object
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides

addTransformations(AutoMlTablesInputs.Transformation value)

public AutoMlTablesInputs.Builder addTransformations(AutoMlTablesInputs.Transformation value)

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameter
Name Description
value AutoMlTablesInputs.Transformation
Returns
Type Description
AutoMlTablesInputs.Builder

addTransformations(AutoMlTablesInputs.Transformation.Builder builderForValue)

public AutoMlTablesInputs.Builder addTransformations(AutoMlTablesInputs.Transformation.Builder builderForValue)

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameter
Name Description
builderForValue AutoMlTablesInputs.Transformation.Builder
Returns
Type Description
AutoMlTablesInputs.Builder

addTransformations(int index, AutoMlTablesInputs.Transformation value)

public AutoMlTablesInputs.Builder addTransformations(int index, AutoMlTablesInputs.Transformation value)

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameters
Name Description
index int
value AutoMlTablesInputs.Transformation
Returns
Type Description
AutoMlTablesInputs.Builder

addTransformations(int index, AutoMlTablesInputs.Transformation.Builder builderForValue)

public AutoMlTablesInputs.Builder addTransformations(int index, AutoMlTablesInputs.Transformation.Builder builderForValue)

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameters
Name Description
index int
builderForValue AutoMlTablesInputs.Transformation.Builder
Returns
Type Description
AutoMlTablesInputs.Builder

addTransformationsBuilder()

public AutoMlTablesInputs.Transformation.Builder addTransformationsBuilder()

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Returns
Type Description
AutoMlTablesInputs.Transformation.Builder

addTransformationsBuilder(int index)

public AutoMlTablesInputs.Transformation.Builder addTransformationsBuilder(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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameter
Name Description
index int
Returns
Type Description
AutoMlTablesInputs.Transformation.Builder

build()

public AutoMlTablesInputs build()
Returns
Type Description
AutoMlTablesInputs

buildPartial()

public AutoMlTablesInputs buildPartial()
Returns
Type Description
AutoMlTablesInputs

clear()

public AutoMlTablesInputs.Builder clear()
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides

clearAdditionalExperiments()

public AutoMlTablesInputs.Builder clearAdditionalExperiments()

Additional experiment flags for the Tables training pipeline.

repeated string additional_experiments = 11;

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

clearAdditionalOptimizationObjectiveConfig()

public AutoMlTablesInputs.Builder clearAdditionalOptimizationObjectiveConfig()
Returns
Type Description
AutoMlTablesInputs.Builder

clearDisableEarlyStopping()

public AutoMlTablesInputs.Builder clearDisableEarlyStopping()

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.

bool disable_early_stopping = 8;

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

clearExportEvaluatedDataItemsConfig()

public AutoMlTablesInputs.Builder clearExportEvaluatedDataItemsConfig()

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

.google.cloud.aiplatform.v1.schema.trainingjob.definition.ExportEvaluatedDataItemsConfig export_evaluated_data_items_config = 10;

Returns
Type Description
AutoMlTablesInputs.Builder

clearField(Descriptors.FieldDescriptor field)

public AutoMlTablesInputs.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
Name Description
field FieldDescriptor
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides

clearOneof(Descriptors.OneofDescriptor oneof)

public AutoMlTablesInputs.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
Name Description
oneof OneofDescriptor
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides

clearOptimizationObjective()

public AutoMlTablesInputs.Builder clearOptimizationObjective()

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).

string optimization_objective = 4;

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

clearOptimizationObjectivePrecisionValue()

public AutoMlTablesInputs.Builder clearOptimizationObjectivePrecisionValue()

Required when optimization_objective is "maximize-recall-at-precision". Must be between 0 and 1, inclusive.

float optimization_objective_precision_value = 6;

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

clearOptimizationObjectiveRecallValue()

public AutoMlTablesInputs.Builder clearOptimizationObjectiveRecallValue()

Required when optimization_objective is "maximize-precision-at-recall". Must be between 0 and 1, inclusive.

float optimization_objective_recall_value = 5;

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

clearPredictionType()

public AutoMlTablesInputs.Builder clearPredictionType()

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.

string prediction_type = 1;

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

clearTargetColumn()

public AutoMlTablesInputs.Builder clearTargetColumn()

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

string target_column = 2;

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

clearTrainBudgetMilliNodeHours()

public AutoMlTablesInputs.Builder clearTrainBudgetMilliNodeHours()

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 = 7;

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

clearTransformations()

public AutoMlTablesInputs.Builder clearTransformations()

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Returns
Type Description
AutoMlTablesInputs.Builder

clearWeightColumnName()

public AutoMlTablesInputs.Builder clearWeightColumnName()

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.

string weight_column_name = 9;

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

clone()

public AutoMlTablesInputs.Builder clone()
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides

getAdditionalExperiments(int index)

public String getAdditionalExperiments(int index)

Additional experiment flags for the Tables training pipeline.

repeated string additional_experiments = 11;

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 ByteString getAdditionalExperimentsBytes(int index)

Additional experiment flags for the Tables training pipeline.

repeated string additional_experiments = 11;

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 int getAdditionalExperimentsCount()

Additional experiment flags for the Tables training pipeline.

repeated string additional_experiments = 11;

Returns
Type Description
int

The count of additionalExperiments.

getAdditionalExperimentsList()

public ProtocolStringList getAdditionalExperimentsList()

Additional experiment flags for the Tables training pipeline.

repeated string additional_experiments = 11;

Returns
Type Description
ProtocolStringList

A list containing the additionalExperiments.

getAdditionalOptimizationObjectiveConfigCase()

public AutoMlTablesInputs.AdditionalOptimizationObjectiveConfigCase getAdditionalOptimizationObjectiveConfigCase()
Returns
Type Description
AutoMlTablesInputs.AdditionalOptimizationObjectiveConfigCase

getDefaultInstanceForType()

public AutoMlTablesInputs getDefaultInstanceForType()
Returns
Type Description
AutoMlTablesInputs

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
Type Description
Descriptor
Overrides

getDisableEarlyStopping()

public boolean getDisableEarlyStopping()

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.

bool disable_early_stopping = 8;

Returns
Type Description
boolean

The disableEarlyStopping.

getExportEvaluatedDataItemsConfig()

public 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.v1.schema.trainingjob.definition.ExportEvaluatedDataItemsConfig export_evaluated_data_items_config = 10;

Returns
Type Description
ExportEvaluatedDataItemsConfig

The exportEvaluatedDataItemsConfig.

getExportEvaluatedDataItemsConfigBuilder()

public ExportEvaluatedDataItemsConfig.Builder getExportEvaluatedDataItemsConfigBuilder()

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

.google.cloud.aiplatform.v1.schema.trainingjob.definition.ExportEvaluatedDataItemsConfig export_evaluated_data_items_config = 10;

Returns
Type Description
ExportEvaluatedDataItemsConfig.Builder

getExportEvaluatedDataItemsConfigOrBuilder()

public 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.v1.schema.trainingjob.definition.ExportEvaluatedDataItemsConfig export_evaluated_data_items_config = 10;

Returns
Type Description
ExportEvaluatedDataItemsConfigOrBuilder

getOptimizationObjective()

public String getOptimizationObjective()

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).

string optimization_objective = 4;

Returns
Type Description
String

The optimizationObjective.

getOptimizationObjectiveBytes()

public ByteString getOptimizationObjectiveBytes()

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).

string optimization_objective = 4;

Returns
Type Description
ByteString

The bytes for optimizationObjective.

getOptimizationObjectivePrecisionValue()

public float getOptimizationObjectivePrecisionValue()

Required when optimization_objective is "maximize-recall-at-precision". Must be between 0 and 1, inclusive.

float optimization_objective_precision_value = 6;

Returns
Type Description
float

The optimizationObjectivePrecisionValue.

getOptimizationObjectiveRecallValue()

public float getOptimizationObjectiveRecallValue()

Required when optimization_objective is "maximize-precision-at-recall". Must be between 0 and 1, inclusive.

float optimization_objective_recall_value = 5;

Returns
Type Description
float

The optimizationObjectiveRecallValue.

getPredictionType()

public String getPredictionType()

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.

string prediction_type = 1;

Returns
Type Description
String

The predictionType.

getPredictionTypeBytes()

public ByteString getPredictionTypeBytes()

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.

string prediction_type = 1;

Returns
Type Description
ByteString

The bytes for predictionType.

getTargetColumn()

public String getTargetColumn()

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

string target_column = 2;

Returns
Type Description
String

The targetColumn.

getTargetColumnBytes()

public ByteString getTargetColumnBytes()

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

string target_column = 2;

Returns
Type Description
ByteString

The bytes for targetColumn.

getTrainBudgetMilliNodeHours()

public 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 = 7;

Returns
Type Description
long

The trainBudgetMilliNodeHours.

getTransformations(int index)

public AutoMlTablesInputs.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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameter
Name Description
index int
Returns
Type Description
AutoMlTablesInputs.Transformation

getTransformationsBuilder(int index)

public AutoMlTablesInputs.Transformation.Builder getTransformationsBuilder(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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameter
Name Description
index int
Returns
Type Description
AutoMlTablesInputs.Transformation.Builder

getTransformationsBuilderList()

public List<AutoMlTablesInputs.Transformation.Builder> getTransformationsBuilderList()

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Returns
Type Description
List<Builder>

getTransformationsCount()

public int getTransformationsCount()

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Returns
Type Description
int

getTransformationsList()

public List<AutoMlTablesInputs.Transformation> getTransformationsList()

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Returns
Type Description
List<Transformation>

getTransformationsOrBuilder(int index)

public AutoMlTablesInputs.TransformationOrBuilder getTransformationsOrBuilder(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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameter
Name Description
index int
Returns
Type Description
AutoMlTablesInputs.TransformationOrBuilder

getTransformationsOrBuilderList()

public List<? extends AutoMlTablesInputs.TransformationOrBuilder> getTransformationsOrBuilderList()

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Returns
Type Description
List<? extends com.google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.TransformationOrBuilder>

getWeightColumnName()

public String getWeightColumnName()

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.

string weight_column_name = 9;

Returns
Type Description
String

The weightColumnName.

getWeightColumnNameBytes()

public ByteString getWeightColumnNameBytes()

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.

string weight_column_name = 9;

Returns
Type Description
ByteString

The bytes for weightColumnName.

hasExportEvaluatedDataItemsConfig()

public boolean hasExportEvaluatedDataItemsConfig()

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

.google.cloud.aiplatform.v1.schema.trainingjob.definition.ExportEvaluatedDataItemsConfig export_evaluated_data_items_config = 10;

Returns
Type Description
boolean

Whether the exportEvaluatedDataItemsConfig field is set.

hasOptimizationObjectivePrecisionValue()

public boolean hasOptimizationObjectivePrecisionValue()

Required when optimization_objective is "maximize-recall-at-precision". Must be between 0 and 1, inclusive.

float optimization_objective_precision_value = 6;

Returns
Type Description
boolean

Whether the optimizationObjectivePrecisionValue field is set.

hasOptimizationObjectiveRecallValue()

public boolean hasOptimizationObjectiveRecallValue()

Required when optimization_objective is "maximize-precision-at-recall". Must be between 0 and 1, inclusive.

float optimization_objective_recall_value = 5;

Returns
Type Description
boolean

Whether the optimizationObjectiveRecallValue field is set.

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Type Description
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

mergeExportEvaluatedDataItemsConfig(ExportEvaluatedDataItemsConfig value)

public AutoMlTablesInputs.Builder mergeExportEvaluatedDataItemsConfig(ExportEvaluatedDataItemsConfig value)

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

.google.cloud.aiplatform.v1.schema.trainingjob.definition.ExportEvaluatedDataItemsConfig export_evaluated_data_items_config = 10;

Parameter
Name Description
value ExportEvaluatedDataItemsConfig
Returns
Type Description
AutoMlTablesInputs.Builder

mergeFrom(AutoMlTablesInputs other)

public AutoMlTablesInputs.Builder mergeFrom(AutoMlTablesInputs other)
Parameter
Name Description
other AutoMlTablesInputs
Returns
Type Description
AutoMlTablesInputs.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public AutoMlTablesInputs.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input CodedInputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides
Exceptions
Type Description
IOException

mergeFrom(Message other)

public AutoMlTablesInputs.Builder mergeFrom(Message other)
Parameter
Name Description
other Message
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides

mergeUnknownFields(UnknownFieldSet unknownFields)

public final AutoMlTablesInputs.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
Name Description
unknownFields UnknownFieldSet
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides

removeTransformations(int index)

public AutoMlTablesInputs.Builder removeTransformations(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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameter
Name Description
index int
Returns
Type Description
AutoMlTablesInputs.Builder

setAdditionalExperiments(int index, String value)

public AutoMlTablesInputs.Builder setAdditionalExperiments(int index, String value)

Additional experiment flags for the Tables training pipeline.

repeated string additional_experiments = 11;

Parameters
Name Description
index int

The index to set the value at.

value String

The additionalExperiments to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setDisableEarlyStopping(boolean value)

public AutoMlTablesInputs.Builder setDisableEarlyStopping(boolean value)

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.

bool disable_early_stopping = 8;

Parameter
Name Description
value boolean

The disableEarlyStopping to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setExportEvaluatedDataItemsConfig(ExportEvaluatedDataItemsConfig value)

public AutoMlTablesInputs.Builder setExportEvaluatedDataItemsConfig(ExportEvaluatedDataItemsConfig value)

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

.google.cloud.aiplatform.v1.schema.trainingjob.definition.ExportEvaluatedDataItemsConfig export_evaluated_data_items_config = 10;

Parameter
Name Description
value ExportEvaluatedDataItemsConfig
Returns
Type Description
AutoMlTablesInputs.Builder

setExportEvaluatedDataItemsConfig(ExportEvaluatedDataItemsConfig.Builder builderForValue)

public AutoMlTablesInputs.Builder setExportEvaluatedDataItemsConfig(ExportEvaluatedDataItemsConfig.Builder builderForValue)

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

.google.cloud.aiplatform.v1.schema.trainingjob.definition.ExportEvaluatedDataItemsConfig export_evaluated_data_items_config = 10;

Parameter
Name Description
builderForValue ExportEvaluatedDataItemsConfig.Builder
Returns
Type Description
AutoMlTablesInputs.Builder

setField(Descriptors.FieldDescriptor field, Object value)

public AutoMlTablesInputs.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
Name Description
field FieldDescriptor
value Object
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides

setOptimizationObjective(String value)

public AutoMlTablesInputs.Builder setOptimizationObjective(String value)

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).

string optimization_objective = 4;

Parameter
Name Description
value String

The optimizationObjective to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setOptimizationObjectiveBytes(ByteString value)

public AutoMlTablesInputs.Builder setOptimizationObjectiveBytes(ByteString value)

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).

string optimization_objective = 4;

Parameter
Name Description
value ByteString

The bytes for optimizationObjective to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setOptimizationObjectivePrecisionValue(float value)

public AutoMlTablesInputs.Builder setOptimizationObjectivePrecisionValue(float value)

Required when optimization_objective is "maximize-recall-at-precision". Must be between 0 and 1, inclusive.

float optimization_objective_precision_value = 6;

Parameter
Name Description
value float

The optimizationObjectivePrecisionValue to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setOptimizationObjectiveRecallValue(float value)

public AutoMlTablesInputs.Builder setOptimizationObjectiveRecallValue(float value)

Required when optimization_objective is "maximize-precision-at-recall". Must be between 0 and 1, inclusive.

float optimization_objective_recall_value = 5;

Parameter
Name Description
value float

The optimizationObjectiveRecallValue to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setPredictionType(String value)

public AutoMlTablesInputs.Builder setPredictionType(String value)

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.

string prediction_type = 1;

Parameter
Name Description
value String

The predictionType to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setPredictionTypeBytes(ByteString value)

public AutoMlTablesInputs.Builder setPredictionTypeBytes(ByteString value)

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.

string prediction_type = 1;

Parameter
Name Description
value ByteString

The bytes for predictionType to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

public AutoMlTablesInputs.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
Name Description
field FieldDescriptor
index int
value Object
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides

setTargetColumn(String value)

public AutoMlTablesInputs.Builder setTargetColumn(String value)

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

string target_column = 2;

Parameter
Name Description
value String

The targetColumn to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setTargetColumnBytes(ByteString value)

public AutoMlTablesInputs.Builder setTargetColumnBytes(ByteString value)

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

string target_column = 2;

Parameter
Name Description
value ByteString

The bytes for targetColumn to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setTrainBudgetMilliNodeHours(long value)

public AutoMlTablesInputs.Builder setTrainBudgetMilliNodeHours(long value)

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 = 7;

Parameter
Name Description
value long

The trainBudgetMilliNodeHours to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setTransformations(int index, AutoMlTablesInputs.Transformation value)

public AutoMlTablesInputs.Builder setTransformations(int index, AutoMlTablesInputs.Transformation value)

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameters
Name Description
index int
value AutoMlTablesInputs.Transformation
Returns
Type Description
AutoMlTablesInputs.Builder

setTransformations(int index, AutoMlTablesInputs.Transformation.Builder builderForValue)

public AutoMlTablesInputs.Builder setTransformations(int index, AutoMlTablesInputs.Transformation.Builder builderForValue)

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.

repeated .google.cloud.aiplatform.v1.schema.trainingjob.definition.AutoMlTablesInputs.Transformation transformations = 3;

Parameters
Name Description
index int
builderForValue AutoMlTablesInputs.Transformation.Builder
Returns
Type Description
AutoMlTablesInputs.Builder

setUnknownFields(UnknownFieldSet unknownFields)

public final AutoMlTablesInputs.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
Name Description
unknownFields UnknownFieldSet
Returns
Type Description
AutoMlTablesInputs.Builder
Overrides

setWeightColumnName(String value)

public AutoMlTablesInputs.Builder setWeightColumnName(String value)

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.

string weight_column_name = 9;

Parameter
Name Description
value String

The weightColumnName to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.

setWeightColumnNameBytes(ByteString value)

public AutoMlTablesInputs.Builder setWeightColumnNameBytes(ByteString value)

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.

string weight_column_name = 9;

Parameter
Name Description
value ByteString

The bytes for weightColumnName to set.

Returns
Type Description
AutoMlTablesInputs.Builder

This builder for chaining.