Cloud AutoML V1 Client - Class ModelEvaluation (2.0.0)

Reference documentation and code samples for the Cloud AutoML V1 Client class ModelEvaluation.

Evaluation results of a model.

Generated from protobuf message google.cloud.automl.v1.ModelEvaluation

Namespace

Google \ Cloud \ AutoMl \ V1

Methods

__construct

Constructor.

Parameters
Name Description
data array

Optional. Data for populating the Message object.
↳ classification_evaluation_metrics Google\Cloud\AutoMl\V1\ClassificationEvaluationMetrics

Model evaluation metrics for image, text, video and tables classification. Tables problem is considered a classification when the target column is CATEGORY DataType.
↳ translation_evaluation_metrics Google\Cloud\AutoMl\V1\TranslationEvaluationMetrics

Model evaluation metrics for translation.
↳ image_object_detection_evaluation_metrics Google\Cloud\AutoMl\V1\ImageObjectDetectionEvaluationMetrics

Model evaluation metrics for image object detection.
↳ text_sentiment_evaluation_metrics Google\Cloud\AutoMl\V1\TextSentimentEvaluationMetrics

Evaluation metrics for text sentiment models.
↳ text_extraction_evaluation_metrics Google\Cloud\AutoMl\V1\TextExtractionEvaluationMetrics

Evaluation metrics for text extraction models.
↳ name string

Output only. Resource name of the model evaluation. Format: projects/{project_id}/locations/{location_id}/models/{model_id}/modelEvaluations/{model_evaluation_id}
↳ annotation_spec_id string

Output only. The ID of the annotation spec that the model evaluation applies to. The The ID is empty for the overall model evaluation. For Tables annotation specs in the dataset do not exist and this ID is always not set, but for CLASSIFICATION prediction_type-s the display_name field is used.
↳ display_name string

Output only. The value of display_name at the moment when the model was trained. Because this field returns a value at model training time, for different models trained from the same dataset, the values may differ, since display names could had been changed between the two model's trainings. For Tables CLASSIFICATION prediction_type-s distinct values of the target column at the moment of the model evaluation are populated here. The display_name is empty for the overall model evaluation.
↳ create_time Google\Protobuf\Timestamp

Output only. Timestamp when this model evaluation was created.
↳ evaluated_example_count int

Output only. The number of examples used for model evaluation, i.e. for which ground truth from time of model creation is compared against the predicted annotations created by the model. For overall ModelEvaluation (i.e. with annotation_spec_id not set) this is the total number of all examples used for evaluation. Otherwise, this is the count of examples that according to the ground truth were annotated by the annotation_spec_id.

getClassificationEvaluationMetrics

Model evaluation metrics for image, text, video and tables classification.

Tables problem is considered a classification when the target column is CATEGORY DataType.

Returns
Type Description
Google\Cloud\AutoMl\V1\ClassificationEvaluationMetrics|null

hasClassificationEvaluationMetrics

setClassificationEvaluationMetrics

Model evaluation metrics for image, text, video and tables classification.

Tables problem is considered a classification when the target column is CATEGORY DataType.

Parameter
Name Description
var Google\Cloud\AutoMl\V1\ClassificationEvaluationMetrics
Returns
Type Description
$this

getTranslationEvaluationMetrics

Model evaluation metrics for translation.

Returns
Type Description
Google\Cloud\AutoMl\V1\TranslationEvaluationMetrics|null

hasTranslationEvaluationMetrics

setTranslationEvaluationMetrics

Model evaluation metrics for translation.

Parameter
Name Description
var Google\Cloud\AutoMl\V1\TranslationEvaluationMetrics
Returns
Type Description
$this

getImageObjectDetectionEvaluationMetrics

Model evaluation metrics for image object detection.

Returns
Type Description
Google\Cloud\AutoMl\V1\ImageObjectDetectionEvaluationMetrics|null

hasImageObjectDetectionEvaluationMetrics

setImageObjectDetectionEvaluationMetrics

Model evaluation metrics for image object detection.

Parameter
Name Description
var Google\Cloud\AutoMl\V1\ImageObjectDetectionEvaluationMetrics
Returns
Type Description
$this

getTextSentimentEvaluationMetrics

Evaluation metrics for text sentiment models.

Returns
Type Description
Google\Cloud\AutoMl\V1\TextSentimentEvaluationMetrics|null

hasTextSentimentEvaluationMetrics

setTextSentimentEvaluationMetrics

Evaluation metrics for text sentiment models.

Parameter
Name Description
var Google\Cloud\AutoMl\V1\TextSentimentEvaluationMetrics
Returns
Type Description
$this

getTextExtractionEvaluationMetrics

Evaluation metrics for text extraction models.

Returns
Type Description
Google\Cloud\AutoMl\V1\TextExtractionEvaluationMetrics|null

hasTextExtractionEvaluationMetrics

setTextExtractionEvaluationMetrics

Evaluation metrics for text extraction models.

Parameter
Name Description
var Google\Cloud\AutoMl\V1\TextExtractionEvaluationMetrics
Returns
Type Description
$this

getName

Output only. Resource name of the model evaluation.

Format: projects/{project_id}/locations/{location_id}/models/{model_id}/modelEvaluations/{model_evaluation_id}

Returns
Type Description
string

setName

Output only. Resource name of the model evaluation.

Format: projects/{project_id}/locations/{location_id}/models/{model_id}/modelEvaluations/{model_evaluation_id}

Parameter
Name Description
var string
Returns
Type Description
$this

getAnnotationSpecId

Output only. The ID of the annotation spec that the model evaluation applies to. The The ID is empty for the overall model evaluation.

For Tables annotation specs in the dataset do not exist and this ID is always not set, but for CLASSIFICATION prediction_type-s the display_name field is used.

Returns
Type Description
string

setAnnotationSpecId

Output only. The ID of the annotation spec that the model evaluation applies to. The The ID is empty for the overall model evaluation.

For Tables annotation specs in the dataset do not exist and this ID is always not set, but for CLASSIFICATION prediction_type-s the display_name field is used.

Parameter
Name Description
var string
Returns
Type Description
$this

getDisplayName

Output only. The value of display_name at the moment when the model was trained. Because this field returns a value at model training time, for different models trained from the same dataset, the values may differ, since display names could had been changed between the two model's trainings. For Tables CLASSIFICATION prediction_type-s distinct values of the target column at the moment of the model evaluation are populated here.

The display_name is empty for the overall model evaluation.

Returns
Type Description
string

setDisplayName

Output only. The value of display_name at the moment when the model was trained. Because this field returns a value at model training time, for different models trained from the same dataset, the values may differ, since display names could had been changed between the two model's trainings. For Tables CLASSIFICATION prediction_type-s distinct values of the target column at the moment of the model evaluation are populated here.

The display_name is empty for the overall model evaluation.

Parameter
Name Description
var string
Returns
Type Description
$this

getCreateTime

Output only. Timestamp when this model evaluation was created.

Returns
Type Description
Google\Protobuf\Timestamp|null

hasCreateTime

clearCreateTime

setCreateTime

Output only. Timestamp when this model evaluation was created.

Parameter
Name Description
var Google\Protobuf\Timestamp
Returns
Type Description
$this

getEvaluatedExampleCount

Output only. The number of examples used for model evaluation, i.e. for which ground truth from time of model creation is compared against the predicted annotations created by the model.

For overall ModelEvaluation (i.e. with annotation_spec_id not set) this is the total number of all examples used for evaluation. Otherwise, this is the count of examples that according to the ground truth were annotated by the annotation_spec_id.

Returns
Type Description
int

setEvaluatedExampleCount

Output only. The number of examples used for model evaluation, i.e. for which ground truth from time of model creation is compared against the predicted annotations created by the model.

For overall ModelEvaluation (i.e. with annotation_spec_id not set) this is the total number of all examples used for evaluation. Otherwise, this is the count of examples that according to the ground truth were annotated by the annotation_spec_id.

Parameter
Name Description
var int
Returns
Type Description
$this

getMetrics

Returns
Type Description
string