Class Explanation (1.5.0)

public final class Explanation extends GeneratedMessageV3 implements ExplanationOrBuilder

Explanation of a prediction (provided in PredictResponse.predictions) produced by the Model on a given instance.

Protobuf type google.cloud.vertexai.v1.Explanation

Static Fields

ATTRIBUTIONS_FIELD_NUMBER

public static final int ATTRIBUTIONS_FIELD_NUMBER
Field Value
Type Description
int

NEIGHBORS_FIELD_NUMBER

public static final int NEIGHBORS_FIELD_NUMBER
Field Value
Type Description
int

Static Methods

getDefaultInstance()

public static Explanation getDefaultInstance()
Returns
Type Description
Explanation

getDescriptor()

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

newBuilder()

public static Explanation.Builder newBuilder()
Returns
Type Description
Explanation.Builder

newBuilder(Explanation prototype)

public static Explanation.Builder newBuilder(Explanation prototype)
Parameter
Name Description
prototype Explanation
Returns
Type Description
Explanation.Builder

parseDelimitedFrom(InputStream input)

public static Explanation parseDelimitedFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
Explanation
Exceptions
Type Description
IOException

parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static Explanation parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
Explanation
Exceptions
Type Description
IOException

parseFrom(byte[] data)

public static Explanation parseFrom(byte[] data)
Parameter
Name Description
data byte[]
Returns
Type Description
Explanation
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)

public static Explanation parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data byte[]
extensionRegistry ExtensionRegistryLite
Returns
Type Description
Explanation
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data)

public static Explanation parseFrom(ByteString data)
Parameter
Name Description
data ByteString
Returns
Type Description
Explanation
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)

public static Explanation parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteString
extensionRegistry ExtensionRegistryLite
Returns
Type Description
Explanation
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(CodedInputStream input)

public static Explanation parseFrom(CodedInputStream input)
Parameter
Name Description
input CodedInputStream
Returns
Type Description
Explanation
Exceptions
Type Description
IOException

parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public static Explanation parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input CodedInputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
Explanation
Exceptions
Type Description
IOException

parseFrom(InputStream input)

public static Explanation parseFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
Explanation
Exceptions
Type Description
IOException

parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static Explanation parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
Explanation
Exceptions
Type Description
IOException

parseFrom(ByteBuffer data)

public static Explanation parseFrom(ByteBuffer data)
Parameter
Name Description
data ByteBuffer
Returns
Type Description
Explanation
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)

public static Explanation parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteBuffer
extensionRegistry ExtensionRegistryLite
Returns
Type Description
Explanation
Exceptions
Type Description
InvalidProtocolBufferException

parser()

public static Parser<Explanation> parser()
Returns
Type Description
Parser<Explanation>

Methods

equals(Object obj)

public boolean equals(Object obj)
Parameter
Name Description
obj Object
Returns
Type Description
boolean
Overrides

getAttributions(int index)

public Attribution getAttributions(int index)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

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

Parameter
Name Description
index int
Returns
Type Description
Attribution

getAttributionsCount()

public int getAttributionsCount()

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

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

Returns
Type Description
int

getAttributionsList()

public List<Attribution> getAttributionsList()

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

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

Returns
Type Description
List<Attribution>

getAttributionsOrBuilder(int index)

public AttributionOrBuilder getAttributionsOrBuilder(int index)

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

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

Parameter
Name Description
index int
Returns
Type Description
AttributionOrBuilder

getAttributionsOrBuilderList()

public List<? extends AttributionOrBuilder> getAttributionsOrBuilderList()

Output only. Feature attributions grouped by predicted 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.

By default, we provide Shapley values for the predicted class. However, you can configure the explanation request to generate Shapley values for any other classes too. For example, if a model predicts a probability of 0.4 for approving a loan application, the model's decision is to reject the application since p(reject) = 0.6 > p(approve) = 0.4, and the default Shapley values would be computed for rejection decision and not approval, even though the latter might be the positive class.

If users set ExplanationParameters.top_k, the attributions are sorted by instance_output_value in descending order. If ExplanationParameters.output_indices is specified, the attributions are stored by Attribution.output_index in the same order as they appear in the output_indices.

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

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

getDefaultInstanceForType()

public Explanation getDefaultInstanceForType()
Returns
Type Description
Explanation

getNeighbors(int index)

public Neighbor getNeighbors(int index)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
index int
Returns
Type Description
Neighbor

getNeighborsCount()

public int getNeighborsCount()

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
int

getNeighborsList()

public List<Neighbor> getNeighborsList()

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

Returns
Type Description
List<Neighbor>

getNeighborsOrBuilder(int index)

public NeighborOrBuilder getNeighborsOrBuilder(int index)

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

Parameter
Name Description
index int
Returns
Type Description
NeighborOrBuilder

getNeighborsOrBuilderList()

public List<? extends NeighborOrBuilder> getNeighborsOrBuilderList()

Output only. List of the nearest neighbors for example-based explanations.

For models deployed with the examples explanations feature enabled, the attributions field is empty and instead the neighbors field is populated.

repeated .google.cloud.vertexai.v1.Neighbor neighbors = 2 [(.google.api.field_behavior) = OUTPUT_ONLY];

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

getParserForType()

public Parser<Explanation> getParserForType()
Returns
Type Description
Parser<Explanation>
Overrides

getSerializedSize()

public int getSerializedSize()
Returns
Type Description
int
Overrides

hashCode()

public int hashCode()
Returns
Type Description
int
Overrides

internalGetFieldAccessorTable()

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

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

newBuilderForType()

public Explanation.Builder newBuilderForType()
Returns
Type Description
Explanation.Builder

newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protected Explanation.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Name Description
parent BuilderParent
Returns
Type Description
Explanation.Builder
Overrides

newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Name Description
unused UnusedPrivateParameter
Returns
Type Description
Object
Overrides

toBuilder()

public Explanation.Builder toBuilder()
Returns
Type Description
Explanation.Builder

writeTo(CodedOutputStream output)

public void writeTo(CodedOutputStream output)
Parameter
Name Description
output CodedOutputStream
Overrides
Exceptions
Type Description
IOException