Struct google_ml1_beta1::ProjectPredictCall [−] [src]

pub struct ProjectPredictCall<'a, C, A> where
    C: 'a,
    A: 'a,  { /* fields omitted */ }

Performs prediction on the data in the request.

Responses are very similar to requests. There are two top-level fields, each of which are JSON lists:

predictions
The list of predictions, one per instance in the request.
error
An error message returned instead of a prediction list if any instance produced an error.

If the call is successful, the response body will contain one prediction entry per instance in the request body. If prediction fails for any instance, the response body will contain no predictions and will contian a single error entry instead.

Even though there is one prediction per instance, the format of a prediction is not directly related to the format of an instance. Predictions take whatever format is specified in the outputs collection defined in the model. The collection of predictions is returned in a JSON list. Each member of the list can be a simple value, a list, or a JSON object of any complexity. If your model has more than one output tensor, each prediction will be a JSON object containing a name/value pair for each output. The names identify the output aliases in the graph.

The following examples show some possible responses:

A simple set of predictions for three input instances, where each prediction is an integer value: 

{"predictions": [5, 4, 3]}
A more complex set of predictions, each containing two named values that correspond to output tensors, named label and scores respectively. The value of label is the predicted category ("car" or "beach") and scores contains a list of probabilities for that instance across the possible categories. 
{"predictions": [{"label": "beach", "scores": [0.1, 0.9]},
                 {"label": "car", "scores": [0.75, 0.25]}]}
A response when there is an error processing an input instance: 
{"error": "Divide by zero"}

A builder for the predict method supported by a project resource. It is not used directly, but through a ProjectMethods instance.

Example

Instantiate a resource method builder

use ml1_beta1::GoogleCloudMlV1beta1__PredictRequest;
 
// As the method needs a request, you would usually fill it with the desired information
// into the respective structure. Some of the parts shown here might not be applicable !
// Values shown here are possibly random and not representative !
let mut req = GoogleCloudMlV1beta1__PredictRequest::default();
 
// You can configure optional parameters by calling the respective setters at will, and
// execute the final call using `doit()`.
// Values shown here are possibly random and not representative !
let result = hub.projects().predict(req, "name")
             .doit();

Methods

impl<'a, C, A> ProjectPredictCall<'a, C, A> where
    C: BorrowMut<Client>,
    A: GetToken, 
[src]

Perform the operation you have build so far.

Sets the request property to the given value.

Even though the property as already been set when instantiating this call, we provide this method for API completeness.

Required. The resource name of a model or a version.

Authorization: requires Viewer role on the parent project.

Sets the name path property to the given value.

Even though the property as already been set when instantiating this call, we provide this method for API completeness.

The delegate implementation is consulted whenever there is an intermediate result, or if something goes wrong while executing the actual API request.

It should be used to handle progress information, and to implement a certain level of resilience.

Sets the delegate property to the given value.

Set any additional parameter of the query string used in the request. It should be used to set parameters which are not yet available through their own setters.

Please note that this method must not be used to set any of the known paramters which have their own setter method. If done anyway, the request will fail.

Additional Parameters

  • bearer_token (query-string) - OAuth bearer token.
  • pp (query-boolean) - Pretty-print response.
  • prettyPrint (query-boolean) - Returns response with indentations and line breaks.
  • upload_protocol (query-string) - Upload protocol for media (e.g. "raw", "multipart").
  • access_token (query-string) - OAuth access token.
  • fields (query-string) - Selector specifying which fields to include in a partial response.
  • quotaUser (query-string) - Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
  • callback (query-string) - JSONP
  • oauth_token (query-string) - OAuth 2.0 token for the current user.
  • key (query-string) - API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
  • uploadType (query-string) - Legacy upload protocol for media (e.g. "media", "multipart").
  • alt (query-string) - Data format for response.
  • $.xgafv (query-string) - V1 error format.

Identifies the authorization scope for the method you are building.

Use this method to actively specify which scope should be used, instead the default Scope variant Scope::CloudPlatform.

The scope will be added to a set of scopes. This is important as one can maintain access tokens for more than one scope.

Usually there is more than one suitable scope to authorize an operation, some of which may encompass more rights than others. For example, for listing resources, a read-only scope will be sufficient, a read-write scope will do as well.

Trait Implementations

impl<'a, C, A> CallBuilder for ProjectPredictCall<'a, C, A>
[src]