Class Attribution.Builder (3.5.0)

Version 3.5.0

• 3.52.0 (latest)
• 3.50.0
• 3.49.0
• 3.48.0
• 3.47.0
• 3.46.0
• 3.45.0
• 3.44.0
• 3.43.0
• 3.42.0
• 3.41.0
• 3.40.0
• 3.38.0
• 3.37.0
• 3.36.0
• 3.35.0
• 3.34.0
• 3.33.0
• 3.32.0
• 3.31.0
• 3.30.0
• 3.29.0
• 3.28.0
• 3.25.0
• 3.24.0
• 3.23.0
• 3.22.0
• 3.21.0
• 3.20.0
• 3.19.0
• 3.18.0
• 3.17.0
• 3.16.0
• 3.15.0
• 3.14.0
• 3.13.0
• 3.12.0
• 3.11.0
• 3.10.0
• 3.9.0
• 3.8.0
• 3.7.0
• 3.6.0
• 3.5.0
• 3.4.2
• 3.3.0
• 3.2.0
• 3.0.0
• 2.9.8
• 2.8.9
• 2.7.4
• 2.5.3
• 2.4.0

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

Attribution that explains a particular prediction output.

Protobuf type google.cloud.aiplatform.v1.Attribution

Inheritance

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

Implements

AttributionOrBuilder

Inherited Members

AbstractMessage.Builder.findInitializationErrors()

AbstractMessage.Builder.getInitializationErrorString()

AbstractMessage.Builder.internalMergeFrom(AbstractMessageLite)

AbstractMessage.Builder.mergeFrom(byte[])

AbstractMessage.Builder.mergeFrom(byte[],ExtensionRegistryLite)

AbstractMessage.Builder.mergeFrom(byte[],int,int)

AbstractMessage.Builder.mergeFrom(byte[],int,int,ExtensionRegistryLite)

AbstractMessage.Builder.mergeFrom(ByteString)

AbstractMessage.Builder.mergeFrom(ByteString,ExtensionRegistryLite)

AbstractMessage.Builder.mergeFrom(CodedInputStream)

AbstractMessage.Builder.mergeFrom(CodedInputStream,ExtensionRegistryLite)

AbstractMessage.Builder.mergeFrom(Message)

AbstractMessage.Builder.mergeFrom(InputStream)

AbstractMessage.Builder.mergeFrom(InputStream,ExtensionRegistryLite)

AbstractMessage.Builder.newUninitializedMessageException(Message)

AbstractMessage.Builder.toString()

AbstractMessageLite.Builder.<T>addAll(Iterable<T>,Collection<? super T>)

AbstractMessageLite.Builder.<T>addAll(Iterable<T>,List<? super T>)

AbstractMessageLite.Builder.internalMergeFrom(MessageType)

AbstractMessageLite.Builder.mergeDelimitedFrom(InputStream)

AbstractMessageLite.Builder.mergeDelimitedFrom(InputStream,ExtensionRegistryLite)

AbstractMessageLite.Builder.mergeFrom(MessageLite)

AbstractMessageLite.Builder.newUninitializedMessageException(MessageLite)

GeneratedMessageV3.Builder.addRepeatedField(Descriptors.FieldDescriptor,Object)

GeneratedMessageV3.Builder.clear()

GeneratedMessageV3.Builder.clearField(Descriptors.FieldDescriptor)

GeneratedMessageV3.Builder.clearOneof(Descriptors.OneofDescriptor)

GeneratedMessageV3.Builder.clone()

GeneratedMessageV3.Builder.getAllFields()

GeneratedMessageV3.Builder.getDescriptorForType()

GeneratedMessageV3.Builder.getField(Descriptors.FieldDescriptor)

GeneratedMessageV3.Builder.getFieldBuilder(Descriptors.FieldDescriptor)

GeneratedMessageV3.Builder.getOneofFieldDescriptor(Descriptors.OneofDescriptor)

GeneratedMessageV3.Builder.getParentForChildren()

GeneratedMessageV3.Builder.getRepeatedField(Descriptors.FieldDescriptor,int)

GeneratedMessageV3.Builder.getRepeatedFieldBuilder(Descriptors.FieldDescriptor,int)

GeneratedMessageV3.Builder.getRepeatedFieldCount(Descriptors.FieldDescriptor)

com.google.protobuf.GeneratedMessageV3.Builder.getUnknownFieldSetBuilder()

GeneratedMessageV3.Builder.getUnknownFields()

GeneratedMessageV3.Builder.hasField(Descriptors.FieldDescriptor)

GeneratedMessageV3.Builder.hasOneof(Descriptors.OneofDescriptor)

GeneratedMessageV3.Builder.internalGetFieldAccessorTable()

GeneratedMessageV3.Builder.internalGetMapField(int)

GeneratedMessageV3.Builder.internalGetMutableMapField(int)

GeneratedMessageV3.Builder.isClean()

GeneratedMessageV3.Builder.isInitialized()

GeneratedMessageV3.Builder.markClean()

GeneratedMessageV3.Builder.mergeUnknownFields(UnknownFieldSet)

com.google.protobuf.GeneratedMessageV3.Builder.mergeUnknownLengthDelimitedField(int,com.google.protobuf.ByteString)

com.google.protobuf.GeneratedMessageV3.Builder.mergeUnknownVarintField(int,int)

GeneratedMessageV3.Builder.newBuilderForField(Descriptors.FieldDescriptor)

GeneratedMessageV3.Builder.onBuilt()

GeneratedMessageV3.Builder.onChanged()

com.google.protobuf.GeneratedMessageV3.Builder.parseUnknownField(com.google.protobuf.CodedInputStream,com.google.protobuf.ExtensionRegistryLite,int)

GeneratedMessageV3.Builder.setField(Descriptors.FieldDescriptor,Object)

GeneratedMessageV3.Builder.setRepeatedField(Descriptors.FieldDescriptor,int,Object)

com.google.protobuf.GeneratedMessageV3.Builder.setUnknownFieldSetBuilder(com.google.protobuf.UnknownFieldSet.Builder)

GeneratedMessageV3.Builder.setUnknownFields(UnknownFieldSet)

GeneratedMessageV3.Builder.setUnknownFieldsProto3(UnknownFieldSet)

Object.equals(Object)

Object.finalize()

Object.getClass()

Object.hashCode()

Object.notify()

Object.notifyAll()

Object.wait()

Object.wait(long)

Object.wait(long,int)

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

GeneratedMessageV3.Builder<BuilderType>.addRepeatedField(Descriptors.FieldDescriptor field, Object value)

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

GeneratedMessageV3.Builder<BuilderType>.clear()

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

GeneratedMessageV3.Builder<BuilderType>.clearField(Descriptors.FieldDescriptor field)

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

GeneratedMessageV3.Builder<BuilderType>.clearOneof(Descriptors.OneofDescriptor oneof)

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

GeneratedMessageV3.Builder<BuilderType>.clone()

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

GeneratedMessageV3.Builder<BuilderType>.getDescriptorForType()

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

GeneratedMessageV3.Builder<BuilderType>.internalGetFieldAccessorTable()

isInitialized()

public final boolean isInitialized()

Returns

Type	Description
boolean

Overrides

GeneratedMessageV3.Builder<BuilderType>.isInitialized()

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

AbstractMessage.Builder<BuilderType>.mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

Exceptions

Type	Description
IOException

mergeFrom(Message other)

public Attribution.Builder mergeFrom(Message other)

Parameter

Name	Description
other	Message

Returns

Type	Description
Attribution.Builder

Overrides

AbstractMessage.Builder<BuilderType>.mergeFrom(Message other)

mergeUnknownFields(UnknownFieldSet unknownFields)

public final Attribution.Builder mergeUnknownFields(UnknownFieldSet unknownFields)

Parameter

Name	Description
unknownFields	UnknownFieldSet

Returns

Type	Description
Attribution.Builder

Overrides

GeneratedMessageV3.Builder<BuilderType>.mergeUnknownFields(UnknownFieldSet unknownFields)

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

GeneratedMessageV3.Builder<BuilderType>.setField(Descriptors.FieldDescriptor field, Object value)

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

GeneratedMessageV3.Builder<BuilderType>.setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

setUnknownFields(UnknownFieldSet unknownFields)

public final Attribution.Builder setUnknownFields(UnknownFieldSet unknownFields)

Parameter

Name	Description
unknownFields	UnknownFieldSet

Returns

Type	Description
Attribution.Builder

Overrides

GeneratedMessageV3.Builder<BuilderType>.setUnknownFields(UnknownFieldSet unknownFields)