Report for a cross-validation of an estimator

The class CrossValidationReport performs cross-validation and provides a report to inspect and evaluate a scikit-learn estimator in an interactive way. The functionalities of the report are exposed through accessors.

CrossValidationReport(estimator, X[, y, ...])

Report for cross-validation results.

Methods

CrossValidationReport.help()	Display report help using rich or HTML.
CrossValidationReport.cache_predictions([...])	Cache the predictions for sub-estimators reports.
CrossValidationReport.clear_cache()	Clear the cache.
CrossValidationReport.create_estimator_report(*)	Create an estimator report from the cross-validation report.
CrossValidationReport.get_predictions(*, ...)	Get estimator's predictions.

Accessors

CrossValidationReport.data	The data accessor helps you to get insights about the dataset used.
CrossValidationReport.inspection	Accessor for model inspection related operations.
CrossValidationReport.metrics	Accessor for metrics-related operations.

Data

The data accessor helps you to get insights about the dataset used in the cross-validation.

CrossValidationReport.data.help()	Display accessor help using rich or HTML.
CrossValidationReport.data.analyze([with_y, ...])	Plot dataset statistics.

Metrics

The metrics accessor helps you to evaluate the statistical performance of your estimator across cross-validation splits.

CrossValidationReport.metrics.help()	Display accessor help using rich or HTML.
CrossValidationReport.metrics.summarize(*[, ...])	Report a set of metrics for our estimator.
CrossValidationReport.metrics.accuracy(*[, ...])	Compute the accuracy score.
CrossValidationReport.metrics.brier_score(*)	Compute the Brier score.
CrossValidationReport.metrics.confusion_matrix(*)	Plot the confusion matrix.
CrossValidationReport.metrics.custom_metric(...)	Compute a custom metric.
CrossValidationReport.metrics.log_loss(*[, ...])	Compute the log loss.
CrossValidationReport.metrics.precision(*[, ...])	Compute the precision score.
CrossValidationReport.metrics.precision_recall(*)	Plot the precision-recall curve.
CrossValidationReport.metrics.prediction_error(*)	Plot the prediction error of a regression model.
CrossValidationReport.metrics.r2(*[, ...])	Compute the R² score.
CrossValidationReport.metrics.recall(*[, ...])	Compute the recall score.
CrossValidationReport.metrics.rmse(*[, ...])	Compute the root mean squared error.
CrossValidationReport.metrics.roc(*[, ...])	Plot the ROC curve.
CrossValidationReport.metrics.roc_auc(*[, ...])	Compute the ROC AUC score.
CrossValidationReport.metrics.timings([...])	Get all measured processing times related to the estimator.

Inspection

The inspection accessor helps you inspect your model by e.g. evaluating the importance of the features in your model.

CrossValidationReport.inspection.help()	Display accessor help using rich or HTML.
CrossValidationReport.inspection.coefficients()	Retrieve the coefficients across splits, including the intercept.