Class ModelExplanation.Builder (1.15.0) 

public static final class ModelExplanation.Builder extends GeneratedMessageV3.Builder<ModelExplanation.Builder> implements ModelExplanationOrBuilder

Aggregated explanation metrics for a Model over a set of instances.

Protobuf type google.cloud.vertexai.v1.ModelExplanation

Inheritance

Object > AbstractMessageLite.Builder<MessageType,BuilderType> > AbstractMessage.Builder<BuilderType> > GeneratedMessageV3.Builder > ModelExplanation.Builder

Static Methods

getDescriptor()

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

Methods

addAllMeanAttributions(Iterable<? extends Attribution> values)

public ModelExplanation.Builder addAllMeanAttributions(Iterable<? extends Attribution> values)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
values Iterable<? extends com.google.cloud.vertexai.api.Attribution>
Returns
Type Description
ModelExplanation.Builder

addMeanAttributions(Attribution value)

public ModelExplanation.Builder addMeanAttributions(Attribution value)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value Attribution
Returns
Type Description
ModelExplanation.Builder

addMeanAttributions(Attribution.Builder builderForValue)

public ModelExplanation.Builder addMeanAttributions(Attribution.Builder builderForValue)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
builderForValue Attribution.Builder
Returns
Type Description
ModelExplanation.Builder

addMeanAttributions(int index, Attribution value)

public ModelExplanation.Builder addMeanAttributions(int index, Attribution value)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameters
Name Description
index int
value Attribution
Returns
Type Description
ModelExplanation.Builder

addMeanAttributions(int index, Attribution.Builder builderForValue)

public ModelExplanation.Builder addMeanAttributions(int index, Attribution.Builder builderForValue)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameters
Name Description
index int
builderForValue Attribution.Builder
Returns
Type Description
ModelExplanation.Builder

addMeanAttributionsBuilder()

public Attribution.Builder addMeanAttributionsBuilder()

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
Attribution.Builder

addMeanAttributionsBuilder(int index)

public Attribution.Builder addMeanAttributionsBuilder(int index)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
index int
Returns
Type Description
Attribution.Builder

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

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

build()

public ModelExplanation build()
Returns
Type Description
ModelExplanation

buildPartial()

public ModelExplanation buildPartial()
Returns
Type Description
ModelExplanation

clear()

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

clearField(Descriptors.FieldDescriptor field)

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

clearMeanAttributions()

public ModelExplanation.Builder clearMeanAttributions()

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
ModelExplanation.Builder

clearOneof(Descriptors.OneofDescriptor oneof)

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

clone()

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

getDefaultInstanceForType()

public ModelExplanation getDefaultInstanceForType()
Returns
Type Description
ModelExplanation

getDescriptorForType()

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

getMeanAttributions(int index)

public Attribution getMeanAttributions(int index)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
index int
Returns
Type Description
Attribution

getMeanAttributionsBuilder(int index)

public Attribution.Builder getMeanAttributionsBuilder(int index)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
index int
Returns
Type Description
Attribution.Builder

getMeanAttributionsBuilderList()

public List<Attribution.Builder> getMeanAttributionsBuilderList()

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
List<Builder>

getMeanAttributionsCount()

public int getMeanAttributionsCount()

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
int

getMeanAttributionsList()

public List<Attribution> getMeanAttributionsList()

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
List<Attribution>

getMeanAttributionsOrBuilder(int index)

public AttributionOrBuilder getMeanAttributionsOrBuilder(int index)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
index int
Returns
Type Description
AttributionOrBuilder

getMeanAttributionsOrBuilderList()

public List<? extends AttributionOrBuilder> getMeanAttributionsOrBuilderList()

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
List<? extends com.google.cloud.vertexai.api.AttributionOrBuilder>

internalGetFieldAccessorTable()

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

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

mergeFrom(ModelExplanation other)

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

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

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

mergeFrom(Message other)

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

mergeUnknownFields(UnknownFieldSet unknownFields)

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

removeMeanAttributions(int index)

public ModelExplanation.Builder removeMeanAttributions(int index)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
index int
Returns
Type Description
ModelExplanation.Builder

setField(Descriptors.FieldDescriptor field, Object value)

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

setMeanAttributions(int index, Attribution value)

public ModelExplanation.Builder setMeanAttributions(int index, Attribution value)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameters
Name Description
index int
value Attribution
Returns
Type Description
ModelExplanation.Builder

setMeanAttributions(int index, Attribution.Builder builderForValue)

public ModelExplanation.Builder setMeanAttributions(int index, Attribution.Builder builderForValue)

Output only. Aggregated attributions explaining the Model's prediction outputs over the set of instances. The attributions are grouped by outputs.

For Models that predict only one output, such as regression Models that predict only one score, there is only one attibution that explains the predicted output. For Models that predict multiple outputs, such as multiclass Models that predict multiple classes, each element explains one specific item. Attribution.output_index can be used to identify which output this attribution is explaining.

The baselineOutputValue, instanceOutputValue and featureAttributions fields are averaged over the test data.

NOTE: Currently AutoML tabular classification Models produce only one attribution, which averages attributions over all the classes it predicts. Attribution.approximation_error is not populated.

repeated .google.cloud.vertexai.v1.Attribution mean_attributions = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameters
Name Description
index int
builderForValue Attribution.Builder
Returns
Type Description
ModelExplanation.Builder

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

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

setUnknownFields(UnknownFieldSet unknownFields)

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