Google Cloud Ai Platform V1 Client - Class ExplainRequest (1.13.1)

Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class ExplainRequest.

Request message for PredictionService.Explain.

Generated from protobuf message google.cloud.aiplatform.v1.ExplainRequest

Namespace

Google \ Cloud \ AIPlatform \ V1

Methods

__construct

Constructor.

Parameters
Name	Description
`data`	`array` Optional. Data for populating the Message object.
`↳ endpoint`	`string` Required. The name of the Endpoint requested to serve the explanation. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
`↳ instances`	`array<Google\Protobuf\Value>` Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
`↳ parameters`	`Google\Protobuf\Value` The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
`↳ explanation_spec_override`	`ExplanationSpecOverride` If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as: - Explaining top-5 predictions results as opposed to top-1; - Increasing path count or step count of the attribution methods to reduce approximate errors; - Using different baselines for explaining the prediction results.
`↳ deployed_model_id`	`string` If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.

getEndpoint

Required. The name of the Endpoint requested to serve the explanation.

Format: projects/{project}/locations/{location}/endpoints/{endpoint}

Returns
Type	Description
`string`

setEndpoint

Required. The name of the Endpoint requested to serve the explanation.

Format: projects/{project}/locations/{location}/endpoints/{endpoint}

Parameter
Name	Description
`var`	`string`

Returns
Type	Description
`$this`

getInstances

Required. The instances that are the input to the explanation call.

A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

Returns
Type	Description
`Google\Protobuf\Internal\RepeatedField`

setInstances

Required. The instances that are the input to the explanation call.

Parameter
Name	Description
`var`	`array<Google\Protobuf\Value>`

Returns
Type	Description
`$this`

getParameters

The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.

Returns
Type	Description
`Google\Protobuf\Value\|null`

hasParameters

clearParameters

setParameters

The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.

Parameter
Name	Description
`var`	`Google\Protobuf\Value`

Returns
Type	Description
`$this`

getExplanationSpecOverride

If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:

Explaining top-5 predictions results as opposed to top-1;
Increasing path count or step count of the attribution methods to reduce approximate errors;
Using different baselines for explaining the prediction results.

Returns
Type	Description
`ExplanationSpecOverride\|null`

hasExplanationSpecOverride

clearExplanationSpecOverride

setExplanationSpecOverride

If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:

Explaining top-5 predictions results as opposed to top-1;
Increasing path count or step count of the attribution methods to reduce approximate errors;
Using different baselines for explaining the prediction results.

Parameter
Name	Description
`var`	`ExplanationSpecOverride`

Returns
Type	Description
`$this`

getDeployedModelId

If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.

Returns
Type	Description
`string`

setDeployedModelId

If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.

Parameter
Name	Description
`var`	`string`

Returns
Type	Description
`$this`

static::build

Parameters
Name	Description
`endpoint`	`string` Required. The name of the Endpoint requested to serve the explanation. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` Please see PredictionServiceClient::endpointName() for help formatting this field.
`instances`	`array<Google\Protobuf\Value>` Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.
`parameters`	`Google\Protobuf\Value` The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.
`deployedModelId`	`string` If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.

Returns
Type	Description
`ExplainRequest`