Class PredictionServiceClient (0.8.0)

PredictionServiceClient(
    transport=None,
    channel=None,
    credentials=None,
    client_config=None,
    client_info=None,
    client_options=None,
)

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.

Methods

PredictionServiceClient

PredictionServiceClient(
    transport=None,
    channel=None,
    credentials=None,
    client_config=None,
    client_info=None,
    client_options=None,
)

Constructor.

Parameters
NameDescription
channel grpc.Channel

DEPRECATED. A Channel instance through which to make calls. This argument is mutually exclusive with credentials; providing both will raise an exception.

credentials google.auth.credentials.Credentials

The authorization credentials to attach to requests. These credentials identify this application to the service. If none are specified, the client will attempt to ascertain the credentials from the environment. This argument is mutually exclusive with providing a transport instance to transport; doing so will raise an exception.

client_config dict

DEPRECATED. A dictionary of call options for each method. If not specified, the default configuration is used.

client_info google.api_core.gapic_v1.client_info.ClientInfo

The client info used to send a user-agent string along with API requests. If None, then default info will be used. Generally, you only need to set this if you're developing your own client library.

client_options Union[dict, google.api_core.client_options.ClientOptions]

Client options used to set user options on the client. API Endpoint should be set through client_options.

batch_predict

batch_predict(name, input_config, output_config, params=None, retry=<_MethodDefault._DEFAULT_VALUE: <object object>>, timeout=<_MethodDefault._DEFAULT_VALUE: <object object>>, metadata=None)

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

.. rubric:: Example

from google.cloud import automl_v1beta1

client = automl_v1beta1.PredictionServiceClient()

name = client.model_path('[PROJECT]', '[LOCATION]', '[MODEL]')

TODO: Initialize input_config:

input_config = {}

TODO: Initialize output_config:

output_config = {}

response = client.batch_predict(name, input_config, output_config)

def callback(operation_future): ... # Handle result. ... result = operation_future.result()

response.add_done_callback(callback)

Handle metadata.

metadata = response.metadata()

Parameters
NameDescription
name str

Name of the model requested to serve the batch prediction.

input_config Union[dict, BatchPredictInputConfig]

Required. The input configuration for batch prediction. If a dict is provided, it must be of the same form as the protobuf message BatchPredictInputConfig

output_config Union[dict, BatchPredictOutputConfig]

Required. The Configuration specifying where output predictions should be written. If a dict is provided, it must be of the same form as the protobuf message BatchPredictOutputConfig

params dict[str -> str]

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 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.

retry Optional[google.api_core.retry.Retry]

A retry object used to retry requests. If None is specified, requests will be retried using a default configuration.

timeout Optional[float]

The amount of time, in seconds, to wait for the request to complete. Note that if retry is specified, the timeout applies to each individual attempt.

metadata Optional[Sequence[Tuple[str, str]]]

Additional metadata that is provided to the method.

Exceptions
TypeDescription
google.api_core.exceptions.GoogleAPICallErrorIf the request failed for any reason.
google.api_core.exceptions.RetryErrorIf the request failed due to a retryable error and retry attempts failed.
ValueErrorIf the parameters are invalid.

from_service_account_file

from_service_account_file(filename, *args, **kwargs)

Creates an instance of this client using the provided credentials file.

Parameter
NameDescription
filename str

The path to the service account private key json file.

Returns
TypeDescription
PredictionServiceClientThe constructed client.

from_service_account_json

from_service_account_json(filename, *args, **kwargs)

Creates an instance of this client using the provided credentials file.

Parameter
NameDescription
filename str

The path to the service account private key json file.

Returns
TypeDescription
PredictionServiceClientThe constructed client.

model_path

model_path(project, location, model)

Return a fully-qualified model string.

predict

predict(name, payload, params=None, retry=<_MethodDefault._DEFAULT_VALUE: <object object>>, timeout=<_MethodDefault._DEFAULT_VALUE: <object object>>, metadata=None)

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.

.. rubric:: Example

from google.cloud import automl_v1beta1

client = automl_v1beta1.PredictionServiceClient()

name = client.model_path('[PROJECT]', '[LOCATION]', '[MODEL]')

TODO: Initialize payload:

payload = {}

response = client.predict(name, payload)

Parameters
NameDescription
name str

Name of the model requested to serve the prediction.

payload Union[dict, ExamplePayload]

Required. Payload to perform a prediction on. The payload must match the problem type that the model was trained to solve. If a dict is provided, it must be of the same form as the protobuf message ExamplePayload

params dict[str -> str]

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][[google.cloud.automl.v1beta1.TablesModelColumnInfo.feature_importance] should be populated in the returned [TablesAnnotation(-s)][[google.cloud.automl.v1beta1.TablesAnnotation]. The default is false.

retry Optional[google.api_core.retry.Retry]

A retry object used to retry requests. If None is specified, requests will be retried using a default configuration.

timeout Optional[float]

The amount of time, in seconds, to wait for the request to complete. Note that if retry is specified, the timeout applies to each individual attempt.

metadata Optional[Sequence[Tuple[str, str]]]

Additional metadata that is provided to the method.

Exceptions
TypeDescription
google.api_core.exceptions.GoogleAPICallErrorIf the request failed for any reason.
google.api_core.exceptions.RetryErrorIf the request failed due to a retryable error and retry attempts failed.
ValueErrorIf the parameters are invalid.