Class Model (1.25.0)

Protocol buffer.

Required. Unique identifier for this model.

Output only. The time when this model was last modified, in millisecs since the epoch.

Optional. A descriptive name for this model.

Optional. The time when this model expires, in milliseconds since the epoch. If not present, the model will persist indefinitely. Expired models will be deleted and their storage reclaimed. The defaultTableExpirationMs property of the encapsulating dataset can be used to set a default expirationTime on newly created models.

Custom encryption configuration (e.g., Cloud KMS keys). This shows the encryption configuration of the model data while stored in BigQuery storage.

Output only. Information for all training runs in increasing order of start_time.

Output only. Label columns that were used to train this model. The output of the model will have a "predicted_" prefix to these columns.


builtins.object > google.protobuf.pyext._message.CMessage > builtins.object > google.protobuf.message.Message > Model



Aggregate metrics for classification/classifier models. For multi-class models, the metrics are either macro-averaged or micro-averaged. When macro-averaged, the metrics are calculated for each label and then an unweighted average is taken of those values. When micro-averaged, the metric is calculated globally by counting the total number of correctly predicted rows.

Recall is the fraction of actual positive labels that were given a positive prediction. For multiclass this is a macro- averaged metric.

Threshold at which the metrics are computed. For binary classification models this is the positive class threshold. For multi-class classfication models this is the confidence threshold.

Logarithmic Loss. For multiclass this is a macro-averaged metric.


Evaluation metrics for binary classification/classifier models.

Binary confusion matrix at multiple thresholds.

Label representing the negative class.


Evaluation metrics for clustering models.

Mean of squared distances between each sample to its cluster centroid.


Evaluation metrics of a model. These are either computed on all training data or just the eval data based on whether eval data was used during training. These are not present for imported models.

Populated for binary classification/classifier models.

Populated for clustering models.


API documentation for bigquery_v2.types.Model.KmeansEnums class.


API documentation for bigquery_v2.types.Model.LabelsEntry class.


Evaluation metrics for multi-class classification/classifier models.

Confusion matrix at different thresholds.


Evaluation metrics for regression and explicit feedback type matrix factorization models.

Mean squared error.

Median absolute error.


Information about a single training query run for the model.

The start time of this training run.

The evaluation metrics over training/eval data that were computed at the end of training.