Class TablesModelMetadata.Builder (2.31.0)

public static final class TablesModelMetadata.Builder extends GeneratedMessageV3.Builder<TablesModelMetadata.Builder> implements TablesModelMetadataOrBuilder

Model metadata specific to AutoML Tables.

Protobuf type google.cloud.automl.v1beta1.TablesModelMetadata

Static Methods

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
TypeDescription
Descriptor

Methods

addAllInputFeatureColumnSpecs(Iterable<? extends ColumnSpec> values)

public TablesModelMetadata.Builder addAllInputFeatureColumnSpecs(Iterable<? extends ColumnSpec> values)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameter
NameDescription
valuesIterable<? extends com.google.cloud.automl.v1beta1.ColumnSpec>
Returns
TypeDescription
TablesModelMetadata.Builder

addAllTablesModelColumnInfo(Iterable<? extends TablesModelColumnInfo> values)

public TablesModelMetadata.Builder addAllTablesModelColumnInfo(Iterable<? extends TablesModelColumnInfo> values)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameter
NameDescription
valuesIterable<? extends com.google.cloud.automl.v1beta1.TablesModelColumnInfo>
Returns
TypeDescription
TablesModelMetadata.Builder

addInputFeatureColumnSpecs(ColumnSpec value)

public TablesModelMetadata.Builder addInputFeatureColumnSpecs(ColumnSpec value)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameter
NameDescription
valueColumnSpec
Returns
TypeDescription
TablesModelMetadata.Builder

addInputFeatureColumnSpecs(ColumnSpec.Builder builderForValue)

public TablesModelMetadata.Builder addInputFeatureColumnSpecs(ColumnSpec.Builder builderForValue)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameter
NameDescription
builderForValueColumnSpec.Builder
Returns
TypeDescription
TablesModelMetadata.Builder

addInputFeatureColumnSpecs(int index, ColumnSpec value)

public TablesModelMetadata.Builder addInputFeatureColumnSpecs(int index, ColumnSpec value)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameters
NameDescription
indexint
valueColumnSpec
Returns
TypeDescription
TablesModelMetadata.Builder

addInputFeatureColumnSpecs(int index, ColumnSpec.Builder builderForValue)

public TablesModelMetadata.Builder addInputFeatureColumnSpecs(int index, ColumnSpec.Builder builderForValue)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameters
NameDescription
indexint
builderForValueColumnSpec.Builder
Returns
TypeDescription
TablesModelMetadata.Builder

addInputFeatureColumnSpecsBuilder()

public ColumnSpec.Builder addInputFeatureColumnSpecsBuilder()

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Returns
TypeDescription
ColumnSpec.Builder

addInputFeatureColumnSpecsBuilder(int index)

public ColumnSpec.Builder addInputFeatureColumnSpecsBuilder(int index)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameter
NameDescription
indexint
Returns
TypeDescription
ColumnSpec.Builder

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public TablesModelMetadata.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides

addTablesModelColumnInfo(TablesModelColumnInfo value)

public TablesModelMetadata.Builder addTablesModelColumnInfo(TablesModelColumnInfo value)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameter
NameDescription
valueTablesModelColumnInfo
Returns
TypeDescription
TablesModelMetadata.Builder

addTablesModelColumnInfo(TablesModelColumnInfo.Builder builderForValue)

public TablesModelMetadata.Builder addTablesModelColumnInfo(TablesModelColumnInfo.Builder builderForValue)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameter
NameDescription
builderForValueTablesModelColumnInfo.Builder
Returns
TypeDescription
TablesModelMetadata.Builder

addTablesModelColumnInfo(int index, TablesModelColumnInfo value)

public TablesModelMetadata.Builder addTablesModelColumnInfo(int index, TablesModelColumnInfo value)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameters
NameDescription
indexint
valueTablesModelColumnInfo
Returns
TypeDescription
TablesModelMetadata.Builder

addTablesModelColumnInfo(int index, TablesModelColumnInfo.Builder builderForValue)

public TablesModelMetadata.Builder addTablesModelColumnInfo(int index, TablesModelColumnInfo.Builder builderForValue)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameters
NameDescription
indexint
builderForValueTablesModelColumnInfo.Builder
Returns
TypeDescription
TablesModelMetadata.Builder

addTablesModelColumnInfoBuilder()

public TablesModelColumnInfo.Builder addTablesModelColumnInfoBuilder()

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Returns
TypeDescription
TablesModelColumnInfo.Builder

addTablesModelColumnInfoBuilder(int index)

public TablesModelColumnInfo.Builder addTablesModelColumnInfoBuilder(int index)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameter
NameDescription
indexint
Returns
TypeDescription
TablesModelColumnInfo.Builder

build()

public TablesModelMetadata build()
Returns
TypeDescription
TablesModelMetadata

buildPartial()

public TablesModelMetadata buildPartial()
Returns
TypeDescription
TablesModelMetadata

clear()

public TablesModelMetadata.Builder clear()
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides

clearAdditionalOptimizationObjectiveConfig()

public TablesModelMetadata.Builder clearAdditionalOptimizationObjectiveConfig()
Returns
TypeDescription
TablesModelMetadata.Builder

clearDisableEarlyStopping()

public TablesModelMetadata.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 = 12;

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

clearField(Descriptors.FieldDescriptor field)

public TablesModelMetadata.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
NameDescription
fieldFieldDescriptor
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides

clearInputFeatureColumnSpecs()

public TablesModelMetadata.Builder clearInputFeatureColumnSpecs()

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Returns
TypeDescription
TablesModelMetadata.Builder

clearOneof(Descriptors.OneofDescriptor oneof)

public TablesModelMetadata.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
NameDescription
oneofOneofDescriptor
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides

clearOptimizationObjective()

public TablesModelMetadata.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
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

clearOptimizationObjectivePrecisionValue()

public TablesModelMetadata.Builder clearOptimizationObjectivePrecisionValue()

Required when optimization_objective is "MAXIMIZE_RECALL_AT_PRECISION". Must be between 0 and 1, inclusive.

float optimization_objective_precision_value = 18;

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

clearOptimizationObjectiveRecallValue()

public TablesModelMetadata.Builder clearOptimizationObjectiveRecallValue()

Required when optimization_objective is "MAXIMIZE_PRECISION_AT_RECALL". Must be between 0 and 1, inclusive.

float optimization_objective_recall_value = 17;

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

clearTablesModelColumnInfo()

public TablesModelMetadata.Builder clearTablesModelColumnInfo()

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Returns
TypeDescription
TablesModelMetadata.Builder

clearTargetColumnSpec()

public TablesModelMetadata.Builder clearTargetColumnSpec()

Column spec of the dataset's primary table's column the model is predicting. Snapshotted when model creation started. Only 3 fields are used: name - May be set on CreateModel, if it's not then the ColumnSpec corresponding to the current target_column_spec_id of the dataset the model is trained from is used. If neither is set, CreateModel will error. display_name - Output only. data_type - Output only.

.google.cloud.automl.v1beta1.ColumnSpec target_column_spec = 2;

Returns
TypeDescription
TablesModelMetadata.Builder

clearTrainBudgetMilliNodeHours()

public TablesModelMetadata.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 = 6;

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

clearTrainCostMilliNodeHours()

public TablesModelMetadata.Builder clearTrainCostMilliNodeHours()

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.

int64 train_cost_milli_node_hours = 7;

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

clone()

public TablesModelMetadata.Builder clone()
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides

getAdditionalOptimizationObjectiveConfigCase()

public TablesModelMetadata.AdditionalOptimizationObjectiveConfigCase getAdditionalOptimizationObjectiveConfigCase()
Returns
TypeDescription
TablesModelMetadata.AdditionalOptimizationObjectiveConfigCase

getDefaultInstanceForType()

public TablesModelMetadata getDefaultInstanceForType()
Returns
TypeDescription
TablesModelMetadata

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
TypeDescription
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 = 12;

Returns
TypeDescription
boolean

The disableEarlyStopping.

getInputFeatureColumnSpecs(int index)

public ColumnSpec getInputFeatureColumnSpecs(int index)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameter
NameDescription
indexint
Returns
TypeDescription
ColumnSpec

getInputFeatureColumnSpecsBuilder(int index)

public ColumnSpec.Builder getInputFeatureColumnSpecsBuilder(int index)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameter
NameDescription
indexint
Returns
TypeDescription
ColumnSpec.Builder

getInputFeatureColumnSpecsBuilderList()

public List<ColumnSpec.Builder> getInputFeatureColumnSpecsBuilderList()

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Returns
TypeDescription
List<Builder>

getInputFeatureColumnSpecsCount()

public int getInputFeatureColumnSpecsCount()

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Returns
TypeDescription
int

getInputFeatureColumnSpecsList()

public List<ColumnSpec> getInputFeatureColumnSpecsList()

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Returns
TypeDescription
List<ColumnSpec>

getInputFeatureColumnSpecsOrBuilder(int index)

public ColumnSpecOrBuilder getInputFeatureColumnSpecsOrBuilder(int index)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameter
NameDescription
indexint
Returns
TypeDescription
ColumnSpecOrBuilder

getInputFeatureColumnSpecsOrBuilderList()

public List<? extends ColumnSpecOrBuilder> getInputFeatureColumnSpecsOrBuilderList()

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Returns
TypeDescription
List<? extends com.google.cloud.automl.v1beta1.ColumnSpecOrBuilder>

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
TypeDescription
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
TypeDescription
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 = 18;

Returns
TypeDescription
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 = 17;

Returns
TypeDescription
float

The optimizationObjectiveRecallValue.

getTablesModelColumnInfo(int index)

public TablesModelColumnInfo getTablesModelColumnInfo(int index)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameter
NameDescription
indexint
Returns
TypeDescription
TablesModelColumnInfo

getTablesModelColumnInfoBuilder(int index)

public TablesModelColumnInfo.Builder getTablesModelColumnInfoBuilder(int index)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameter
NameDescription
indexint
Returns
TypeDescription
TablesModelColumnInfo.Builder

getTablesModelColumnInfoBuilderList()

public List<TablesModelColumnInfo.Builder> getTablesModelColumnInfoBuilderList()

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Returns
TypeDescription
List<Builder>

getTablesModelColumnInfoCount()

public int getTablesModelColumnInfoCount()

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Returns
TypeDescription
int

getTablesModelColumnInfoList()

public List<TablesModelColumnInfo> getTablesModelColumnInfoList()

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Returns
TypeDescription
List<TablesModelColumnInfo>

getTablesModelColumnInfoOrBuilder(int index)

public TablesModelColumnInfoOrBuilder getTablesModelColumnInfoOrBuilder(int index)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameter
NameDescription
indexint
Returns
TypeDescription
TablesModelColumnInfoOrBuilder

getTablesModelColumnInfoOrBuilderList()

public List<? extends TablesModelColumnInfoOrBuilder> getTablesModelColumnInfoOrBuilderList()

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Returns
TypeDescription
List<? extends com.google.cloud.automl.v1beta1.TablesModelColumnInfoOrBuilder>

getTargetColumnSpec()

public ColumnSpec getTargetColumnSpec()

Column spec of the dataset's primary table's column the model is predicting. Snapshotted when model creation started. Only 3 fields are used: name - May be set on CreateModel, if it's not then the ColumnSpec corresponding to the current target_column_spec_id of the dataset the model is trained from is used. If neither is set, CreateModel will error. display_name - Output only. data_type - Output only.

.google.cloud.automl.v1beta1.ColumnSpec target_column_spec = 2;

Returns
TypeDescription
ColumnSpec

The targetColumnSpec.

getTargetColumnSpecBuilder()

public ColumnSpec.Builder getTargetColumnSpecBuilder()

Column spec of the dataset's primary table's column the model is predicting. Snapshotted when model creation started. Only 3 fields are used: name - May be set on CreateModel, if it's not then the ColumnSpec corresponding to the current target_column_spec_id of the dataset the model is trained from is used. If neither is set, CreateModel will error. display_name - Output only. data_type - Output only.

.google.cloud.automl.v1beta1.ColumnSpec target_column_spec = 2;

Returns
TypeDescription
ColumnSpec.Builder

getTargetColumnSpecOrBuilder()

public ColumnSpecOrBuilder getTargetColumnSpecOrBuilder()

Column spec of the dataset's primary table's column the model is predicting. Snapshotted when model creation started. Only 3 fields are used: name - May be set on CreateModel, if it's not then the ColumnSpec corresponding to the current target_column_spec_id of the dataset the model is trained from is used. If neither is set, CreateModel will error. display_name - Output only. data_type - Output only.

.google.cloud.automl.v1beta1.ColumnSpec target_column_spec = 2;

Returns
TypeDescription
ColumnSpecOrBuilder

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 = 6;

Returns
TypeDescription
long

The trainBudgetMilliNodeHours.

getTrainCostMilliNodeHours()

public long getTrainCostMilliNodeHours()

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.

int64 train_cost_milli_node_hours = 7;

Returns
TypeDescription
long

The trainCostMilliNodeHours.

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 = 18;

Returns
TypeDescription
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 = 17;

Returns
TypeDescription
boolean

Whether the optimizationObjectiveRecallValue field is set.

hasTargetColumnSpec()

public boolean hasTargetColumnSpec()

Column spec of the dataset's primary table's column the model is predicting. Snapshotted when model creation started. Only 3 fields are used: name - May be set on CreateModel, if it's not then the ColumnSpec corresponding to the current target_column_spec_id of the dataset the model is trained from is used. If neither is set, CreateModel will error. display_name - Output only. data_type - Output only.

.google.cloud.automl.v1beta1.ColumnSpec target_column_spec = 2;

Returns
TypeDescription
boolean

Whether the targetColumnSpec field is set.

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
TypeDescription
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
TypeDescription
boolean
Overrides

mergeFrom(TablesModelMetadata other)

public TablesModelMetadata.Builder mergeFrom(TablesModelMetadata other)
Parameter
NameDescription
otherTablesModelMetadata
Returns
TypeDescription
TablesModelMetadata.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public TablesModelMetadata.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputCodedInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides
Exceptions
TypeDescription
IOException

mergeFrom(Message other)

public TablesModelMetadata.Builder mergeFrom(Message other)
Parameter
NameDescription
otherMessage
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides

mergeTargetColumnSpec(ColumnSpec value)

public TablesModelMetadata.Builder mergeTargetColumnSpec(ColumnSpec value)

Column spec of the dataset's primary table's column the model is predicting. Snapshotted when model creation started. Only 3 fields are used: name - May be set on CreateModel, if it's not then the ColumnSpec corresponding to the current target_column_spec_id of the dataset the model is trained from is used. If neither is set, CreateModel will error. display_name - Output only. data_type - Output only.

.google.cloud.automl.v1beta1.ColumnSpec target_column_spec = 2;

Parameter
NameDescription
valueColumnSpec
Returns
TypeDescription
TablesModelMetadata.Builder

mergeUnknownFields(UnknownFieldSet unknownFields)

public final TablesModelMetadata.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides

removeInputFeatureColumnSpecs(int index)

public TablesModelMetadata.Builder removeInputFeatureColumnSpecs(int index)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameter
NameDescription
indexint
Returns
TypeDescription
TablesModelMetadata.Builder

removeTablesModelColumnInfo(int index)

public TablesModelMetadata.Builder removeTablesModelColumnInfo(int index)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameter
NameDescription
indexint
Returns
TypeDescription
TablesModelMetadata.Builder

setDisableEarlyStopping(boolean value)

public TablesModelMetadata.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 = 12;

Parameter
NameDescription
valueboolean

The disableEarlyStopping to set.

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

setField(Descriptors.FieldDescriptor field, Object value)

public TablesModelMetadata.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides

setInputFeatureColumnSpecs(int index, ColumnSpec value)

public TablesModelMetadata.Builder setInputFeatureColumnSpecs(int index, ColumnSpec value)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameters
NameDescription
indexint
valueColumnSpec
Returns
TypeDescription
TablesModelMetadata.Builder

setInputFeatureColumnSpecs(int index, ColumnSpec.Builder builderForValue)

public TablesModelMetadata.Builder setInputFeatureColumnSpecs(int index, ColumnSpec.Builder builderForValue)

Column specs of the dataset's primary table's columns, on which the model is trained and which are used as the input for predictions. The

target_column as well as, according to dataset's state upon model creation,

weight_column, and

ml_use_column must never be included here.

Only 3 fields are used:

  • name - May be set on CreateModel, if set only the columns specified are used, otherwise all primary table's columns (except the ones listed above) are used for the training and prediction input.

  • display_name - Output only.

  • data_type - Output only.

repeated .google.cloud.automl.v1beta1.ColumnSpec input_feature_column_specs = 3;

Parameters
NameDescription
indexint
builderForValueColumnSpec.Builder
Returns
TypeDescription
TablesModelMetadata.Builder

setOptimizationObjective(String value)

public TablesModelMetadata.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
NameDescription
valueString

The optimizationObjective to set.

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

setOptimizationObjectiveBytes(ByteString value)

public TablesModelMetadata.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
NameDescription
valueByteString

The bytes for optimizationObjective to set.

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

setOptimizationObjectivePrecisionValue(float value)

public TablesModelMetadata.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 = 18;

Parameter
NameDescription
valuefloat

The optimizationObjectivePrecisionValue to set.

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

setOptimizationObjectiveRecallValue(float value)

public TablesModelMetadata.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 = 17;

Parameter
NameDescription
valuefloat

The optimizationObjectiveRecallValue to set.

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

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

public TablesModelMetadata.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
NameDescription
fieldFieldDescriptor
indexint
valueObject
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides

setTablesModelColumnInfo(int index, TablesModelColumnInfo value)

public TablesModelMetadata.Builder setTablesModelColumnInfo(int index, TablesModelColumnInfo value)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameters
NameDescription
indexint
valueTablesModelColumnInfo
Returns
TypeDescription
TablesModelMetadata.Builder

setTablesModelColumnInfo(int index, TablesModelColumnInfo.Builder builderForValue)

public TablesModelMetadata.Builder setTablesModelColumnInfo(int index, TablesModelColumnInfo.Builder builderForValue)

Output only. Auxiliary information for each of the input_feature_column_specs with respect to this particular model.

repeated .google.cloud.automl.v1beta1.TablesModelColumnInfo tables_model_column_info = 5;

Parameters
NameDescription
indexint
builderForValueTablesModelColumnInfo.Builder
Returns
TypeDescription
TablesModelMetadata.Builder

setTargetColumnSpec(ColumnSpec value)

public TablesModelMetadata.Builder setTargetColumnSpec(ColumnSpec value)

Column spec of the dataset's primary table's column the model is predicting. Snapshotted when model creation started. Only 3 fields are used: name - May be set on CreateModel, if it's not then the ColumnSpec corresponding to the current target_column_spec_id of the dataset the model is trained from is used. If neither is set, CreateModel will error. display_name - Output only. data_type - Output only.

.google.cloud.automl.v1beta1.ColumnSpec target_column_spec = 2;

Parameter
NameDescription
valueColumnSpec
Returns
TypeDescription
TablesModelMetadata.Builder

setTargetColumnSpec(ColumnSpec.Builder builderForValue)

public TablesModelMetadata.Builder setTargetColumnSpec(ColumnSpec.Builder builderForValue)

Column spec of the dataset's primary table's column the model is predicting. Snapshotted when model creation started. Only 3 fields are used: name - May be set on CreateModel, if it's not then the ColumnSpec corresponding to the current target_column_spec_id of the dataset the model is trained from is used. If neither is set, CreateModel will error. display_name - Output only. data_type - Output only.

.google.cloud.automl.v1beta1.ColumnSpec target_column_spec = 2;

Parameter
NameDescription
builderForValueColumnSpec.Builder
Returns
TypeDescription
TablesModelMetadata.Builder

setTrainBudgetMilliNodeHours(long value)

public TablesModelMetadata.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 = 6;

Parameter
NameDescription
valuelong

The trainBudgetMilliNodeHours to set.

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

setTrainCostMilliNodeHours(long value)

public TablesModelMetadata.Builder setTrainCostMilliNodeHours(long value)

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.

int64 train_cost_milli_node_hours = 7;

Parameter
NameDescription
valuelong

The trainCostMilliNodeHours to set.

Returns
TypeDescription
TablesModelMetadata.Builder

This builder for chaining.

setUnknownFields(UnknownFieldSet unknownFields)

public final TablesModelMetadata.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
TablesModelMetadata.Builder
Overrides