Class Attribution.Builder (1.4.0)

public static final class Attribution.Builder extends GeneratedMessageV3.Builder<Attribution.Builder> implements AttributionOrBuilder

Attribution that explains a particular prediction output.

Protobuf type google.cloud.vertexai.v1.Attribution

Static Methods

getDescriptor()

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

Methods

addAllOutputIndex(Iterable<? extends Integer> values)

public Attribution.Builder addAllOutputIndex(Iterable<? extends Integer> values)

Output only. The index that locates the explained prediction output.

If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0.

repeated int32 output_index = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
values Iterable<? extends java.lang.Integer>

The outputIndex to add.

Returns
Type Description
Attribution.Builder

This builder for chaining.

addOutputIndex(int value)

public Attribution.Builder addOutputIndex(int value)

Output only. The index that locates the explained prediction output.

If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0.

repeated int32 output_index = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value int

The outputIndex to add.

Returns
Type Description
Attribution.Builder

This builder for chaining.

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

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

build()

public Attribution build()
Returns
Type Description
Attribution

buildPartial()

public Attribution buildPartial()
Returns
Type Description
Attribution

clear()

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

clearApproximationError()

public Attribution.Builder clearApproximationError()

Output only. Error of feature_attributions caused by approximation used in the explanation method. Lower value means more precise attributions.

  • For Sampled Shapley attribution, increasing path_count might reduce the error.
  • For Integrated Gradients attribution, increasing step_count might reduce the error.
  • For XRAI attribution, increasing step_count might reduce the error.

    See this introduction for more information.

double approximation_error = 6 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
Attribution.Builder

This builder for chaining.

clearBaselineOutputValue()

public Attribution.Builder clearBaselineOutputValue()

Output only. Model predicted output if the input instance is constructed from the baselines of all the features defined in ExplanationMetadata.inputs. The field name of the output is determined by the key in ExplanationMetadata.outputs.

If the Model's predicted output has multiple dimensions (rank > 1), this is the value in the output located by output_index.

If there are multiple baselines, their output values are averaged.

double baseline_output_value = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
Attribution.Builder

This builder for chaining.

clearFeatureAttributions()

public Attribution.Builder clearFeatureAttributions()

Output only. Attributions of each explained feature. Features are extracted from the prediction instances according to explanation metadata for inputs.

The value is a struct, whose keys are the name of the feature. The values are how much the feature in the instance contributed to the predicted result.

The format of the value is determined by the feature's input format:

  • If the feature is a scalar value, the attribution value is a floating number.

  • If the feature is an array of scalar values, the attribution value is an array.

  • If the feature is a struct, the attribution value is a struct. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct.

    The ExplanationMetadata.feature_attributions_schema_uri field, pointed to by the ExplanationSpec field of the Endpoint.deployed_models object, points to the schema file that describes the features and their attribution values (if it is populated).

.google.protobuf.Value feature_attributions = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
Attribution.Builder

clearField(Descriptors.FieldDescriptor field)

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

clearInstanceOutputValue()

public Attribution.Builder clearInstanceOutputValue()

Output only. Model predicted output on the corresponding explanation instance. The field name of the output is determined by the key in ExplanationMetadata.outputs.

If the Model predicted output has multiple dimensions, this is the value in the output located by output_index.

double instance_output_value = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
Attribution.Builder

This builder for chaining.

clearOneof(Descriptors.OneofDescriptor oneof)

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

clearOutputDisplayName()

public Attribution.Builder clearOutputDisplayName()

Output only. The display name of the output identified by output_index. For example, the predicted class name by a multi-classification Model.

This field is only populated iff the Model predicts display names as a separate field along with the explained output. The predicted display name must has the same shape of the explained output, and can be located using output_index.

string output_display_name = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
Attribution.Builder

This builder for chaining.

clearOutputIndex()

public Attribution.Builder clearOutputIndex()

Output only. The index that locates the explained prediction output.

If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0.

repeated int32 output_index = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
Attribution.Builder

This builder for chaining.

clearOutputName()

public Attribution.Builder clearOutputName()

Output only. Name of the explain output. Specified as the key in ExplanationMetadata.outputs.

string output_name = 7 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
Attribution.Builder

This builder for chaining.

clone()

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

getApproximationError()

public double getApproximationError()

Output only. Error of feature_attributions caused by approximation used in the explanation method. Lower value means more precise attributions.

  • For Sampled Shapley attribution, increasing path_count might reduce the error.
  • For Integrated Gradients attribution, increasing step_count might reduce the error.
  • For XRAI attribution, increasing step_count might reduce the error.

    See this introduction for more information.

double approximation_error = 6 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
double

The approximationError.

getBaselineOutputValue()

public double getBaselineOutputValue()

Output only. Model predicted output if the input instance is constructed from the baselines of all the features defined in ExplanationMetadata.inputs. The field name of the output is determined by the key in ExplanationMetadata.outputs.

If the Model's predicted output has multiple dimensions (rank > 1), this is the value in the output located by output_index.

If there are multiple baselines, their output values are averaged.

double baseline_output_value = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
double

The baselineOutputValue.

getDefaultInstanceForType()

public Attribution getDefaultInstanceForType()
Returns
Type Description
Attribution

getDescriptorForType()

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

getFeatureAttributions()

public Value getFeatureAttributions()

Output only. Attributions of each explained feature. Features are extracted from the prediction instances according to explanation metadata for inputs.

The value is a struct, whose keys are the name of the feature. The values are how much the feature in the instance contributed to the predicted result.

The format of the value is determined by the feature's input format:

  • If the feature is a scalar value, the attribution value is a floating number.

  • If the feature is an array of scalar values, the attribution value is an array.

  • If the feature is a struct, the attribution value is a struct. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct.

    The ExplanationMetadata.feature_attributions_schema_uri field, pointed to by the ExplanationSpec field of the Endpoint.deployed_models object, points to the schema file that describes the features and their attribution values (if it is populated).

.google.protobuf.Value feature_attributions = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
Value

The featureAttributions.

getFeatureAttributionsBuilder()

public Value.Builder getFeatureAttributionsBuilder()

Output only. Attributions of each explained feature. Features are extracted from the prediction instances according to explanation metadata for inputs.

The value is a struct, whose keys are the name of the feature. The values are how much the feature in the instance contributed to the predicted result.

The format of the value is determined by the feature's input format:

  • If the feature is a scalar value, the attribution value is a floating number.

  • If the feature is an array of scalar values, the attribution value is an array.

  • If the feature is a struct, the attribution value is a struct. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct.

    The ExplanationMetadata.feature_attributions_schema_uri field, pointed to by the ExplanationSpec field of the Endpoint.deployed_models object, points to the schema file that describes the features and their attribution values (if it is populated).

.google.protobuf.Value feature_attributions = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
Builder

getFeatureAttributionsOrBuilder()

public ValueOrBuilder getFeatureAttributionsOrBuilder()

Output only. Attributions of each explained feature. Features are extracted from the prediction instances according to explanation metadata for inputs.

The value is a struct, whose keys are the name of the feature. The values are how much the feature in the instance contributed to the predicted result.

The format of the value is determined by the feature's input format:

  • If the feature is a scalar value, the attribution value is a floating number.

  • If the feature is an array of scalar values, the attribution value is an array.

  • If the feature is a struct, the attribution value is a struct. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct.

    The ExplanationMetadata.feature_attributions_schema_uri field, pointed to by the ExplanationSpec field of the Endpoint.deployed_models object, points to the schema file that describes the features and their attribution values (if it is populated).

.google.protobuf.Value feature_attributions = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
ValueOrBuilder

getInstanceOutputValue()

public double getInstanceOutputValue()

Output only. Model predicted output on the corresponding explanation instance. The field name of the output is determined by the key in ExplanationMetadata.outputs.

If the Model predicted output has multiple dimensions, this is the value in the output located by output_index.

double instance_output_value = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
double

The instanceOutputValue.

getOutputDisplayName()

public String getOutputDisplayName()

Output only. The display name of the output identified by output_index. For example, the predicted class name by a multi-classification Model.

This field is only populated iff the Model predicts display names as a separate field along with the explained output. The predicted display name must has the same shape of the explained output, and can be located using output_index.

string output_display_name = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
String

The outputDisplayName.

getOutputDisplayNameBytes()

public ByteString getOutputDisplayNameBytes()

Output only. The display name of the output identified by output_index. For example, the predicted class name by a multi-classification Model.

This field is only populated iff the Model predicts display names as a separate field along with the explained output. The predicted display name must has the same shape of the explained output, and can be located using output_index.

string output_display_name = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
ByteString

The bytes for outputDisplayName.

getOutputIndex(int index)

public int getOutputIndex(int index)

Output only. The index that locates the explained prediction output.

If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0.

repeated int32 output_index = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
index int

The index of the element to return.

Returns
Type Description
int

The outputIndex at the given index.

getOutputIndexCount()

public int getOutputIndexCount()

Output only. The index that locates the explained prediction output.

If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0.

repeated int32 output_index = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
int

The count of outputIndex.

getOutputIndexList()

public List<Integer> getOutputIndexList()

Output only. The index that locates the explained prediction output.

If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0.

repeated int32 output_index = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
List<Integer>

A list containing the outputIndex.

getOutputName()

public String getOutputName()

Output only. Name of the explain output. Specified as the key in ExplanationMetadata.outputs.

string output_name = 7 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
String

The outputName.

getOutputNameBytes()

public ByteString getOutputNameBytes()

Output only. Name of the explain output. Specified as the key in ExplanationMetadata.outputs.

string output_name = 7 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
ByteString

The bytes for outputName.

hasFeatureAttributions()

public boolean hasFeatureAttributions()

Output only. Attributions of each explained feature. Features are extracted from the prediction instances according to explanation metadata for inputs.

The value is a struct, whose keys are the name of the feature. The values are how much the feature in the instance contributed to the predicted result.

The format of the value is determined by the feature's input format:

  • If the feature is a scalar value, the attribution value is a floating number.

  • If the feature is an array of scalar values, the attribution value is an array.

  • If the feature is a struct, the attribution value is a struct. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct.

    The ExplanationMetadata.feature_attributions_schema_uri field, pointed to by the ExplanationSpec field of the Endpoint.deployed_models object, points to the schema file that describes the features and their attribution values (if it is populated).

.google.protobuf.Value feature_attributions = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
boolean

Whether the featureAttributions field is set.

internalGetFieldAccessorTable()

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

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

mergeFeatureAttributions(Value value)

public Attribution.Builder mergeFeatureAttributions(Value value)

Output only. Attributions of each explained feature. Features are extracted from the prediction instances according to explanation metadata for inputs.

The value is a struct, whose keys are the name of the feature. The values are how much the feature in the instance contributed to the predicted result.

The format of the value is determined by the feature's input format:

  • If the feature is a scalar value, the attribution value is a floating number.

  • If the feature is an array of scalar values, the attribution value is an array.

  • If the feature is a struct, the attribution value is a struct. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct.

    The ExplanationMetadata.feature_attributions_schema_uri field, pointed to by the ExplanationSpec field of the Endpoint.deployed_models object, points to the schema file that describes the features and their attribution values (if it is populated).

.google.protobuf.Value feature_attributions = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value Value
Returns
Type Description
Attribution.Builder

mergeFrom(Attribution other)

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

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

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

mergeFrom(Message other)

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

mergeUnknownFields(UnknownFieldSet unknownFields)

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

setApproximationError(double value)

public Attribution.Builder setApproximationError(double value)

Output only. Error of feature_attributions caused by approximation used in the explanation method. Lower value means more precise attributions.

  • For Sampled Shapley attribution, increasing path_count might reduce the error.
  • For Integrated Gradients attribution, increasing step_count might reduce the error.
  • For XRAI attribution, increasing step_count might reduce the error.

    See this introduction for more information.

double approximation_error = 6 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value double

The approximationError to set.

Returns
Type Description
Attribution.Builder

This builder for chaining.

setBaselineOutputValue(double value)

public Attribution.Builder setBaselineOutputValue(double value)

Output only. Model predicted output if the input instance is constructed from the baselines of all the features defined in ExplanationMetadata.inputs. The field name of the output is determined by the key in ExplanationMetadata.outputs.

If the Model's predicted output has multiple dimensions (rank > 1), this is the value in the output located by output_index.

If there are multiple baselines, their output values are averaged.

double baseline_output_value = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value double

The baselineOutputValue to set.

Returns
Type Description
Attribution.Builder

This builder for chaining.

setFeatureAttributions(Value value)

public Attribution.Builder setFeatureAttributions(Value value)

Output only. Attributions of each explained feature. Features are extracted from the prediction instances according to explanation metadata for inputs.

The value is a struct, whose keys are the name of the feature. The values are how much the feature in the instance contributed to the predicted result.

The format of the value is determined by the feature's input format:

  • If the feature is a scalar value, the attribution value is a floating number.

  • If the feature is an array of scalar values, the attribution value is an array.

  • If the feature is a struct, the attribution value is a struct. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct.

    The ExplanationMetadata.feature_attributions_schema_uri field, pointed to by the ExplanationSpec field of the Endpoint.deployed_models object, points to the schema file that describes the features and their attribution values (if it is populated).

.google.protobuf.Value feature_attributions = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value Value
Returns
Type Description
Attribution.Builder

setFeatureAttributions(Value.Builder builderForValue)

public Attribution.Builder setFeatureAttributions(Value.Builder builderForValue)

Output only. Attributions of each explained feature. Features are extracted from the prediction instances according to explanation metadata for inputs.

The value is a struct, whose keys are the name of the feature. The values are how much the feature in the instance contributed to the predicted result.

The format of the value is determined by the feature's input format:

  • If the feature is a scalar value, the attribution value is a floating number.

  • If the feature is an array of scalar values, the attribution value is an array.

  • If the feature is a struct, the attribution value is a struct. The keys in the attribution value struct are the same as the keys in the feature struct. The formats of the values in the attribution struct are determined by the formats of the values in the feature struct.

    The ExplanationMetadata.feature_attributions_schema_uri field, pointed to by the ExplanationSpec field of the Endpoint.deployed_models object, points to the schema file that describes the features and their attribution values (if it is populated).

.google.protobuf.Value feature_attributions = 3 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
builderForValue Builder
Returns
Type Description
Attribution.Builder

setField(Descriptors.FieldDescriptor field, Object value)

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

setInstanceOutputValue(double value)

public Attribution.Builder setInstanceOutputValue(double value)

Output only. Model predicted output on the corresponding explanation instance. The field name of the output is determined by the key in ExplanationMetadata.outputs.

If the Model predicted output has multiple dimensions, this is the value in the output located by output_index.

double instance_output_value = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value double

The instanceOutputValue to set.

Returns
Type Description
Attribution.Builder

This builder for chaining.

setOutputDisplayName(String value)

public Attribution.Builder setOutputDisplayName(String value)

Output only. The display name of the output identified by output_index. For example, the predicted class name by a multi-classification Model.

This field is only populated iff the Model predicts display names as a separate field along with the explained output. The predicted display name must has the same shape of the explained output, and can be located using output_index.

string output_display_name = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value String

The outputDisplayName to set.

Returns
Type Description
Attribution.Builder

This builder for chaining.

setOutputDisplayNameBytes(ByteString value)

public Attribution.Builder setOutputDisplayNameBytes(ByteString value)

Output only. The display name of the output identified by output_index. For example, the predicted class name by a multi-classification Model.

This field is only populated iff the Model predicts display names as a separate field along with the explained output. The predicted display name must has the same shape of the explained output, and can be located using output_index.

string output_display_name = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value ByteString

The bytes for outputDisplayName to set.

Returns
Type Description
Attribution.Builder

This builder for chaining.

setOutputIndex(int index, int value)

public Attribution.Builder setOutputIndex(int index, int value)

Output only. The index that locates the explained prediction output.

If the prediction output is a scalar value, output_index is not populated. If the prediction output has multiple dimensions, the length of the output_index list is the same as the number of dimensions of the output. The i-th element in output_index is the element index of the i-th dimension of the output vector. Indices start from 0.

repeated int32 output_index = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameters
Name Description
index int

The index to set the value at.

value int

The outputIndex to set.

Returns
Type Description
Attribution.Builder

This builder for chaining.

setOutputName(String value)

public Attribution.Builder setOutputName(String value)

Output only. Name of the explain output. Specified as the key in ExplanationMetadata.outputs.

string output_name = 7 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value String

The outputName to set.

Returns
Type Description
Attribution.Builder

This builder for chaining.

setOutputNameBytes(ByteString value)

public Attribution.Builder setOutputNameBytes(ByteString value)

Output only. Name of the explain output. Specified as the key in ExplanationMetadata.outputs.

string output_name = 7 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
value ByteString

The bytes for outputName to set.

Returns
Type Description
Attribution.Builder

This builder for chaining.

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

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

setUnknownFields(UnknownFieldSet unknownFields)

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