PredictionServiceClient

AutoML Prediction API.

On any input that is documented to expect a string parameter in snake_case or kebab-case, either of those cases is accepted.

Constructor

new PredictionServiceClient(optionsopt)

Construct an instance of PredictionServiceClient.

Parameters:

Name Type Attributes Description

options

object

The configuration object. See the subsequent parameters for more details.

Properties

Name Type Attributes Description

credentials

object

Credentials object.

Properties

Name	Type	Attributes	Description
`client_email`	string	<optional>
`private_key`	string	<optional>

email

string

Account email address. Required when using a .pem or .p12 keyFilename.

keyFilename

string

Full path to the a .json, .pem, or .p12 key downloaded from the Google Developers Console. If you provide a path to a JSON file, the projectId option below is not necessary. NOTE: .pem and .p12 require you to specify options.email as well.

port

number

The port on which to connect to the remote host.

projectId

string

The project ID from the Google Developer's Console, e.g. 'grape-spaceship-123'. We will also check the environment variable GCLOUD_PROJECT for your project ID. If your app is running in an environment which supports Application Default Credentials, your project ID will be detected automatically.

apiEndpoint

string

The domain name of the API remote host.

Members

(static) apiEndpoint

The DNS address for this API service - same as servicePath(), exists for compatibility reasons.

(static) port

The port for this API service.

(static) scopes

The scopes needed to make gRPC calls for every method defined in this service.

(static) servicePath

The DNS address for this API service.

Methods

annotationSpecPath(project, location, dataset, annotation_spec) → {string}

Return a fully-qualified annotationSpec resource name string.

Parameters:

Name	Type	Description
`project`	string
`location`	string
`dataset`	string
`annotation_spec`	string

batchPredict(request, optionsopt) → {Promise}

Perform a batch prediction. Unlike the online Predict, batch prediction result won't be immediately available in the response. Instead, a long running operation object is returned. User can poll the operation result via GetOperation method. Once the operation is done, BatchPredictResult is returned in the response field. Available for following ML problems:

Image Classification
Image Object Detection
Video Classification
Video Object Tracking * Text Extraction
Tables

Parameters:

Name Type Attributes Description

request

Object

The request object that will be sent.

Properties

Name	Type	Description
`name`	string	Required. Name of the model requested to serve the batch prediction.
`inputConfig`	google.cloud.automl.v1beta1.BatchPredictInputConfig	Required. The input configuration for batch prediction.
`outputConfig`	google.cloud.automl.v1beta1.BatchPredictOutputConfig	Required. The Configuration specifying where output predictions should be written.
`params`	Array.<number>	Required. Additional domain-specific parameters for the predictions, any string must be up to 25000 characters long. For Text Classification: `score_threshold` - (float) A value from 0.0 to 1.0. When the model makes predictions for a text snippet, it will only produce results that have at least this confidence score. The default is 0.5. For Image Classification: `score_threshold` - (float) A value from 0.0 to 1.0. When the model makes predictions for an image, it will only produce results that have at least this confidence score. The default is 0.5. For Image Object Detection: `score_threshold` - (float) When Model detects objects on the image, it will only produce bounding boxes which have at least this confidence score. Value in 0 to 1 range, default is 0.5. `max_bounding_box_count` - (int64) No more than this number of bounding boxes will be produced per image. Default is 100, the requested value may be limited by server. For Video Classification : `score_threshold` - (float) A value from 0.0 to 1.0. When the model makes predictions for a video, it will only produce results that have at least this confidence score. The default is 0.5. `segment_classification` - (boolean) Set to true to request segment-level classification. AutoML Video Intelligence returns labels and their confidence scores for the entire segment of the video that user specified in the request configuration. The default is "true". `shot_classification` - (boolean) Set to true to request shot-level classification. AutoML Video Intelligence determines the boundaries for each camera shot in the entire segment of the video that user specified in the request configuration. AutoML Video Intelligence then returns labels and their confidence scores for each detected shot, along with the start and end time of the shot. WARNING: Model evaluation is not done for this classification type, the quality of it depends on training data, but there are no metrics provided to describe that quality. The default is "false". `1s_interval_classification` - (boolean) Set to true to request classification for a video at one-second intervals. AutoML Video Intelligence returns labels and their confidence scores for each second of the entire segment of the video that user specified in the request configuration. WARNING: Model evaluation is not done for this classification type, the quality of it depends on training data, but there are no metrics provided to describe that quality. The default is "false". For Tables: feature_importance - (boolean) Whether feature importance should be populated in the returned TablesAnnotations. The default is false. For Video Object Tracking: `score_threshold` - (float) When Model detects objects on video frames, it will only produce bounding boxes which have at least this confidence score. Value in 0 to 1 range, default is 0.5. `max_bounding_box_count` - (int64) No more than this number of bounding boxes will be returned per frame. Default is 100, the requested value may be limited by server. `min_bounding_box_size` - (float) Only bounding boxes with shortest edge at least that long as a relative value of video frame size will be returned. Value in 0 to 1 range. Default is 0.

options

object

Call options. See CallOptions for more details.

close()

Terminate the GRPC channel and close the client.

The client will no longer be usable and all future behavior is undefined.

columnSpecPath(project, location, dataset, table_spec, column_spec) → {string}

Return a fully-qualified columnSpec resource name string.

Parameters:

Name	Type	Description
`project`	string
`location`	string
`dataset`	string
`table_spec`	string
`column_spec`	string

datasetPath(project, location, dataset) → {string}

Return a fully-qualified dataset resource name string.

Parameters:

Name	Type	Description
`project`	string
`location`	string
`dataset`	string

getProjectId(callback)

Return the project ID used by this class.

Parameters:

Name	Type	Description
`callback`	function	the callback to be called with the current project Id.

initialize() → {Promise}

Initialize the client. Performs asynchronous operations (such as authentication) and prepares the client. This function will be called automatically when any class method is called for the first time, but if you need to initialize it before calling an actual method, feel free to call initialize() directly.

You can await on this method if you want to make sure the client is initialized.

matchAnnotationSpecFromAnnotationSpecName(annotationSpecName) → {string}

Parse the annotation_spec from AnnotationSpec resource.

Parameters:

Name	Type	Description
`annotationSpecName`	string	A fully-qualified path representing AnnotationSpec resource.

matchColumnSpecFromColumnSpecName(columnSpecName) → {string}

Parse the column_spec from ColumnSpec resource.

Parameters:

Name	Type	Description
`columnSpecName`	string	A fully-qualified path representing ColumnSpec resource.

matchDatasetFromAnnotationSpecName(annotationSpecName) → {string}

Parse the dataset from AnnotationSpec resource.

Parameters:

Name	Type	Description
`annotationSpecName`	string	A fully-qualified path representing AnnotationSpec resource.

matchDatasetFromColumnSpecName(columnSpecName) → {string}

Parse the dataset from ColumnSpec resource.

Parameters:

Name	Type	Description
`columnSpecName`	string	A fully-qualified path representing ColumnSpec resource.

matchDatasetFromDatasetName(datasetName) → {string}

Parse the dataset from Dataset resource.

Parameters:

Name	Type	Description
`datasetName`	string	A fully-qualified path representing Dataset resource.

matchDatasetFromTableSpecName(tableSpecName) → {string}

Parse the dataset from TableSpec resource.

Parameters:

Name	Type	Description
`tableSpecName`	string	A fully-qualified path representing TableSpec resource.

matchLocationFromAnnotationSpecName(annotationSpecName) → {string}

Parse the location from AnnotationSpec resource.

Parameters:

Name	Type	Description
`annotationSpecName`	string	A fully-qualified path representing AnnotationSpec resource.

matchLocationFromColumnSpecName(columnSpecName) → {string}

Parse the location from ColumnSpec resource.

Parameters:

Name	Type	Description
`columnSpecName`	string	A fully-qualified path representing ColumnSpec resource.

matchLocationFromDatasetName(datasetName) → {string}

Parse the location from Dataset resource.

Parameters:

Name	Type	Description
`datasetName`	string	A fully-qualified path representing Dataset resource.

matchLocationFromModelEvaluationName(modelEvaluationName) → {string}

Parse the location from ModelEvaluation resource.

Parameters:

Name	Type	Description
`modelEvaluationName`	string	A fully-qualified path representing ModelEvaluation resource.

matchLocationFromModelName(modelName) → {string}

Parse the location from Model resource.

Parameters:

Name	Type	Description
`modelName`	string	A fully-qualified path representing Model resource.

matchLocationFromTableSpecName(tableSpecName) → {string}

Parse the location from TableSpec resource.

Parameters:

Name	Type	Description
`tableSpecName`	string	A fully-qualified path representing TableSpec resource.

matchModelEvaluationFromModelEvaluationName(modelEvaluationName) → {string}

Parse the model_evaluation from ModelEvaluation resource.

Parameters:

Name	Type	Description
`modelEvaluationName`	string	A fully-qualified path representing ModelEvaluation resource.

matchModelFromModelEvaluationName(modelEvaluationName) → {string}

Parse the model from ModelEvaluation resource.

Parameters:

Name	Type	Description
`modelEvaluationName`	string	A fully-qualified path representing ModelEvaluation resource.

matchModelFromModelName(modelName) → {string}

Parse the model from Model resource.

Parameters:

Name	Type	Description
`modelName`	string	A fully-qualified path representing Model resource.

matchProjectFromAnnotationSpecName(annotationSpecName) → {string}

Parse the project from AnnotationSpec resource.

Parameters:

Name	Type	Description
`annotationSpecName`	string	A fully-qualified path representing AnnotationSpec resource.

matchProjectFromColumnSpecName(columnSpecName) → {string}

Parse the project from ColumnSpec resource.

Parameters:

Name	Type	Description
`columnSpecName`	string	A fully-qualified path representing ColumnSpec resource.

matchProjectFromDatasetName(datasetName) → {string}

Parse the project from Dataset resource.

Parameters:

Name	Type	Description
`datasetName`	string	A fully-qualified path representing Dataset resource.

matchProjectFromModelEvaluationName(modelEvaluationName) → {string}

Parse the project from ModelEvaluation resource.

Parameters:

Name	Type	Description
`modelEvaluationName`	string	A fully-qualified path representing ModelEvaluation resource.

matchProjectFromModelName(modelName) → {string}

Parse the project from Model resource.

Parameters:

Name	Type	Description
`modelName`	string	A fully-qualified path representing Model resource.

matchProjectFromTableSpecName(tableSpecName) → {string}

Parse the project from TableSpec resource.

Parameters:

Name	Type	Description
`tableSpecName`	string	A fully-qualified path representing TableSpec resource.

matchTableSpecFromColumnSpecName(columnSpecName) → {string}

Parse the table_spec from ColumnSpec resource.

Parameters:

Name	Type	Description
`columnSpecName`	string	A fully-qualified path representing ColumnSpec resource.

matchTableSpecFromTableSpecName(tableSpecName) → {string}

Parse the table_spec from TableSpec resource.

Parameters:

Name	Type	Description
`tableSpecName`	string	A fully-qualified path representing TableSpec resource.

modelEvaluationPath(project, location, model, model_evaluation) → {string}

Return a fully-qualified modelEvaluation resource name string.

Parameters:

Name	Type	Description
`project`	string
`location`	string
`model`	string
`model_evaluation`	string

modelPath(project, location, model) → {string}

Return a fully-qualified model resource name string.

Parameters:

Name	Type	Description
`project`	string
`location`	string
`model`	string

predict(request, optionsopt) → {Promise}

Perform an online prediction. The prediction result will be directly returned in the response. Available for following ML problems, and their expected request payloads:

Image Classification - Image in .JPEG, .GIF or .PNG format, image_bytes up to 30MB.
Image Object Detection - Image in .JPEG, .GIF or .PNG format, image_bytes up to 30MB.
Text Classification - TextSnippet, content up to 60,000 characters, UTF-8 encoded.
Text Extraction - TextSnippet, content up to 30,000 characters, UTF-8 NFC encoded.
Translation - TextSnippet, content up to 25,000 characters, UTF-8 encoded.
Tables - Row, with column values matching the columns of the model, up to 5MB. Not available for FORECASTING

prediction_type.

Text Sentiment - TextSnippet, content up 500 characters, UTF-8 encoded.

Parameters:

Name Type Attributes Description

request

Object

The request object that will be sent.

Properties

Name Type Description

name

string

Required. Name of the model requested to serve the prediction.

payload

google.cloud.automl.v1beta1.ExamplePayload

Required. Payload to perform a prediction on. The payload must match the problem type that the model was trained to solve.

params

Array.<number>

Additional domain-specific parameters, any string must be up to 25000 characters long.

For Image Classification:

score_threshold - (float) A value from 0.0 to 1.0. When the model makes predictions for an image, it will only produce results that have at least this confidence score. The default is 0.5.
For Image Object Detection: score_threshold - (float) When Model detects objects on the image, it will only produce bounding boxes which have at least this confidence score. Value in 0 to 1 range, default is 0.5. max_bounding_box_count - (int64) No more than this number of bounding boxes will be returned in the response. Default is 100, the requested value may be limited by server.
For Tables: feature_importance - (boolean) Whether feature importance should be populated in the returned TablesAnnotation. The default is false.

options

object

Call options. See CallOptions for more details.

tableSpecPath(project, location, dataset, table_spec) → {string}

Return a fully-qualified tableSpec resource name string.

Parameters:

Name	Type	Description
`project`	string
`location`	string
`dataset`	string
`table_spec`	string