EstimatorReport.cache_predictions#

EstimatorReport.cache_predictions(*, data_source='both')[source]

Cache estimator’s predictions.

Parameters:
data_source{“test”, “train”, “both”}, default=”both”

The data source(s) for which to precompute predictions.

  • “test” : cache predictions for the test set only.

  • “train” : cache predictions for the train set only.

  • “both” : cache predictions for both train and test sets when available.

Examples

>>> from sklearn.datasets import load_breast_cancer
>>> from sklearn.linear_model import LogisticRegression
>>> from skore import evaluate
>>> X, y = load_breast_cancer(return_X_y=True)
>>> classifier = LogisticRegression(max_iter=10_000)
>>> report = evaluate(classifier, X, y, splitter=0.2)
>>> report.cache_predictions()
>>> report._cache
{...}