ComparisonReport.cache_predictions

ComparisonReport.cache_predictions(response_methods='auto', n_jobs=None)

Cache the predictions for sub-estimators reports.

Parameters:

response_methods{“auto”, “predict”, “predict_proba”, “decision_function”}, default=”auto

The methods to use to compute the predictions.

n_jobsint, default=None

The number of jobs to run in parallel. If None, we use the n_jobs parameter when initializing the report.

Examples

>>> from sklearn.datasets import make_classification
>>> from sklearn.linear_model import LogisticRegression
>>> from sklearn.model_selection import train_test_split
>>> from skore import ComparisonReport
>>> X, y = make_classification(random_state=42)
>>> X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)
>>> estimator_1 = LogisticRegression()
>>> estimator_report_1 = EstimatorReport(
...     estimator_1,
...     X_train=X_train,
...     y_train=y_train,
...     X_test=X_test,
...     y_test=y_test
... )
>>> estimator_2 = LogisticRegression(C=2)  # Different regularization
>>> estimator_report_2 = EstimatorReport(
...     estimator_2,
...     X_train=X_train,
...     y_train=y_train,
...     X_test=X_test,
...     y_test=y_test
... )
>>> report = ComparisonReport([estimator_report_1, estimator_report_2])
>>> report.cache_predictions()
>>> report._cache
{...}