public final class Attribution extends GeneratedMessageV3 implements AttributionOrBuilder
Attribution that explains a particular prediction output.
Protobuf type google.cloud.aiplatform.v1.Attribution
Inherited Members
com.google.protobuf.GeneratedMessageV3.<ListT>makeMutableCopy(ListT)
Static Fields
public static final int APPROXIMATION_ERROR_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int BASELINE_OUTPUT_VALUE_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int FEATURE_ATTRIBUTIONS_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int INSTANCE_OUTPUT_VALUE_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int OUTPUT_DISPLAY_NAME_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int OUTPUT_INDEX_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
public static final int OUTPUT_NAME_FIELD_NUMBER
| Field Value |
|---|
| Type | Description |
int | |
Static Methods
public static Attribution getDefaultInstance()
public static final Descriptors.Descriptor getDescriptor()
public static Attribution.Builder newBuilder()
public static Attribution.Builder newBuilder(Attribution prototype)
public static Attribution parseDelimitedFrom(InputStream input)
public static Attribution parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
public static Attribution parseFrom(byte[] data)
| Parameter |
|---|
| Name | Description |
data | byte[]
|
public static Attribution parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
public static Attribution parseFrom(ByteString data)
public static Attribution parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
public static Attribution parseFrom(CodedInputStream input)
public static Attribution parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
public static Attribution parseFrom(InputStream input)
public static Attribution parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
public static Attribution parseFrom(ByteBuffer data)
public static Attribution parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
public static Parser<Attribution> parser()
Methods
public boolean equals(Object obj)
| Parameter |
|---|
| Name | Description |
obj | Object
|
Overrides
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.
|
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.
|
public Attribution getDefaultInstanceForType()
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.
|
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];
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.
|
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.
|
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.
|
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.
|
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.
|
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.
|
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.
|
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.
|
public Parser<Attribution> getParserForType()
Overrides
public int getSerializedSize()
| Returns |
|---|
| Type | Description |
int | |
Overrides
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.
|
| Returns |
|---|
| Type | Description |
int | |
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Overrides
public final boolean isInitialized()
Overrides
public Attribution.Builder newBuilderForType()
protected Attribution.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Overrides
public Attribution.Builder toBuilder()
public void writeTo(CodedOutputStream output)
Overrides
