Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class Explanation.
Explanation of a prediction (provided in PredictResponse.predictions) produced by the Model on a given instance.
Generated from protobuf message google.cloud.aiplatform.v1.Explanation
Namespace
Google \ Cloud \ AIPlatform \ V1Methods
__construct
Constructor.
Parameters | |
---|---|
Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ attributions |
array<Google\Cloud\AIPlatform\V1\Attribution>
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 |
↳ neighbors |
array<Google\Cloud\AIPlatform\V1\Neighbor>
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. |
getAttributions
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.
Returns | |
---|---|
Type | Description |
Google\Protobuf\Internal\RepeatedField |
setAttributions
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.
Parameter | |
---|---|
Name | Description |
var |
array<Google\Cloud\AIPlatform\V1\Attribution>
|
Returns | |
---|---|
Type | Description |
$this |
getNeighbors
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.
Returns | |
---|---|
Type | Description |
Google\Protobuf\Internal\RepeatedField |
setNeighbors
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.
Parameter | |
---|---|
Name | Description |
var |
array<Google\Cloud\AIPlatform\V1\Neighbor>
|
Returns | |
---|---|
Type | Description |
$this |