Cloud AutoML V1beta1 Client - Class ClassificationEvaluationMetrics (1.5.4)

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

Model evaluation metrics for classification problems.

Note: For Video Classification this metrics only describe quality of the Video Classification predictions of "segment_classification" type.

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

Namespace

Google \ Cloud \ AutoMl \ V1beta1

Methods

__construct

Constructor.

Parameters
NameDescription
data array

Optional. Data for populating the Message object.

↳ au_prc float

Output only. The Area Under Precision-Recall Curve metric. Micro-averaged for the overall evaluation.

↳ base_au_prc float

Output only. The Area Under Precision-Recall Curve metric based on priors. Micro-averaged for the overall evaluation. Deprecated.

↳ au_roc float

Output only. The Area Under Receiver Operating Characteristic curve metric. Micro-averaged for the overall evaluation.

↳ log_loss float

Output only. The Log Loss metric.

↳ confidence_metrics_entry array<Google\Cloud\AutoMl\V1beta1\ClassificationEvaluationMetrics\ConfidenceMetricsEntry>

Output only. Metrics for each confidence_threshold in 0.00,0.05,0.10,...,0.95,0.96,0.97,0.98,0.99 and position_threshold = INT32_MAX_VALUE. ROC and precision-recall curves, and other aggregated metrics are derived from them. The confidence metrics entries may also be supplied for additional values of position_threshold, but from these no aggregated metrics are computed.

↳ confusion_matrix Google\Cloud\AutoMl\V1beta1\ClassificationEvaluationMetrics\ConfusionMatrix

Output only. Confusion matrix of the evaluation. Only set for MULTICLASS classification problems where number of labels is no more than 10. Only set for model level evaluation, not for evaluation per label.

↳ annotation_spec_id array

Output only. The annotation spec ids used for this evaluation.

getAuPrc

Output only. The Area Under Precision-Recall Curve metric. Micro-averaged for the overall evaluation.

Returns
TypeDescription
float

setAuPrc

Output only. The Area Under Precision-Recall Curve metric. Micro-averaged for the overall evaluation.

Parameter
NameDescription
var float
Returns
TypeDescription
$this

getBaseAuPrc

Output only. The Area Under Precision-Recall Curve metric based on priors.

Micro-averaged for the overall evaluation. Deprecated.

Returns
TypeDescription
float

setBaseAuPrc

Output only. The Area Under Precision-Recall Curve metric based on priors.

Micro-averaged for the overall evaluation. Deprecated.

Parameter
NameDescription
var float
Returns
TypeDescription
$this

getAuRoc

Output only. The Area Under Receiver Operating Characteristic curve metric.

Micro-averaged for the overall evaluation.

Returns
TypeDescription
float

setAuRoc

Output only. The Area Under Receiver Operating Characteristic curve metric.

Micro-averaged for the overall evaluation.

Parameter
NameDescription
var float
Returns
TypeDescription
$this

getLogLoss

Output only. The Log Loss metric.

Returns
TypeDescription
float

setLogLoss

Output only. The Log Loss metric.

Parameter
NameDescription
var float
Returns
TypeDescription
$this

getConfidenceMetricsEntry

Output only. Metrics for each confidence_threshold in 0.00,0.05,0.10,...,0.95,0.96,0.97,0.98,0.99 and position_threshold = INT32_MAX_VALUE.

ROC and precision-recall curves, and other aggregated metrics are derived from them. The confidence metrics entries may also be supplied for additional values of position_threshold, but from these no aggregated metrics are computed.

Returns
TypeDescription
Google\Protobuf\Internal\RepeatedField

setConfidenceMetricsEntry

Output only. Metrics for each confidence_threshold in 0.00,0.05,0.10,...,0.95,0.96,0.97,0.98,0.99 and position_threshold = INT32_MAX_VALUE.

ROC and precision-recall curves, and other aggregated metrics are derived from them. The confidence metrics entries may also be supplied for additional values of position_threshold, but from these no aggregated metrics are computed.

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

getConfusionMatrix

Output only. Confusion matrix of the evaluation.

Only set for MULTICLASS classification problems where number of labels is no more than 10. Only set for model level evaluation, not for evaluation per label.

Returns
TypeDescription
Google\Cloud\AutoMl\V1beta1\ClassificationEvaluationMetrics\ConfusionMatrix|null

hasConfusionMatrix

clearConfusionMatrix

setConfusionMatrix

Output only. Confusion matrix of the evaluation.

Only set for MULTICLASS classification problems where number of labels is no more than 10. Only set for model level evaluation, not for evaluation per label.

Parameter
NameDescription
var Google\Cloud\AutoMl\V1beta1\ClassificationEvaluationMetrics\ConfusionMatrix
Returns
TypeDescription
$this

getAnnotationSpecId

Output only. The annotation spec ids used for this evaluation.

Returns
TypeDescription
Google\Protobuf\Internal\RepeatedField

setAnnotationSpecId

Output only. The annotation spec ids used for this evaluation.

Parameter
NameDescription
var string[]
Returns
TypeDescription
$this