Cloud AutoML V1beta1 Client - Class PredictResponse (1.5.4)

Reference documentation and code samples for the Cloud AutoML V1beta1 Client class PredictResponse.

Response message for PredictionService.Predict.

Generated from protobuf message google.cloud.automl.v1beta1.PredictResponse

Namespace

Google \ Cloud \ AutoMl \ V1beta1

Methods

__construct

Constructor.

Parameters
NameDescription
data array

Optional. Data for populating the Message object.

↳ payload array<Google\Cloud\AutoMl\V1beta1\AnnotationPayload>

Prediction result. Translation and Text Sentiment will return precisely one payload.

↳ preprocessed_input Google\Cloud\AutoMl\V1beta1\ExamplePayload

The preprocessed example that AutoML actually makes prediction on. Empty if AutoML does not preprocess the input example. * For Text Extraction: If the input is a .pdf file, the OCR'ed text will be provided in document_text.

↳ metadata array|Google\Protobuf\Internal\MapField

Additional domain-specific prediction response metadata. * For Image Object Detection: max_bounding_box_count - (int64) At most that many bounding boxes per image could have been returned. * For Text Sentiment: sentiment_score - (float, deprecated) A value between -1 and 1, -1 maps to least positive sentiment, while 1 maps to the most positive one and the higher the score, the more positive the sentiment in the document is. Yet these values are relative to the training data, so e.g. if all data was positive then -1 will be also positive (though the least). The sentiment_score shouldn't be confused with "score" or "magnitude" from the previous Natural Language Sentiment Analysis API.

getPayload

Prediction result.

Translation and Text Sentiment will return precisely one payload.

Returns
TypeDescription
Google\Protobuf\Internal\RepeatedField

setPayload

Prediction result.

Translation and Text Sentiment will return precisely one payload.

Parameter
NameDescription
var array<Google\Cloud\AutoMl\V1beta1\AnnotationPayload>
Returns
TypeDescription
$this

getPreprocessedInput

The preprocessed example that AutoML actually makes prediction on.

Empty if AutoML does not preprocess the input example.

  • For Text Extraction: If the input is a .pdf file, the OCR'ed text will be provided in document_text.
Returns
TypeDescription
Google\Cloud\AutoMl\V1beta1\ExamplePayload|null

hasPreprocessedInput

clearPreprocessedInput

setPreprocessedInput

The preprocessed example that AutoML actually makes prediction on.

Empty if AutoML does not preprocess the input example.

  • For Text Extraction: If the input is a .pdf file, the OCR'ed text will be provided in document_text.
Parameter
NameDescription
var Google\Cloud\AutoMl\V1beta1\ExamplePayload
Returns
TypeDescription
$this

getMetadata

Additional domain-specific prediction response metadata.

  • For Image Object Detection: max_bounding_box_count - (int64) At most that many bounding boxes per image could have been returned.
  • For Text Sentiment: sentiment_score - (float, deprecated) A value between -1 and 1, -1 maps to least positive sentiment, while 1 maps to the most positive one and the higher the score, the more positive the sentiment in the document is. Yet these values are relative to the training data, so e.g. if all data was positive then -1 will be also positive (though the least). The sentiment_score shouldn't be confused with "score" or "magnitude" from the previous Natural Language Sentiment Analysis API.
Returns
TypeDescription
Google\Protobuf\Internal\MapField

setMetadata

Additional domain-specific prediction response metadata.

  • For Image Object Detection: max_bounding_box_count - (int64) At most that many bounding boxes per image could have been returned.
  • For Text Sentiment: sentiment_score - (float, deprecated) A value between -1 and 1, -1 maps to least positive sentiment, while 1 maps to the most positive one and the higher the score, the more positive the sentiment in the document is. Yet these values are relative to the training data, so e.g. if all data was positive then -1 will be also positive (though the least). The sentiment_score shouldn't be confused with "score" or "magnitude" from the previous Natural Language Sentiment Analysis API.
Parameter
NameDescription
var array|Google\Protobuf\Internal\MapField
Returns
TypeDescription
$this