Report for a single estimator

The class EstimatorReport provides a report allowing to inspect and evaluate a scikit-learn estimator in an interactive way. The functionalities of the report are accessible through accessors.

EstimatorReport(estimator, *[, fit, ...])

Report for a fitted estimator.

Methods

EstimatorReport.help()	Display available methods using rich.
EstimatorReport.cache_predictions([...])	Cache estimator's predictions.
EstimatorReport.clear_cache()	Clear the cache.
EstimatorReport.get_predictions(*, data_source)	Get estimator's predictions.

Accessors

EstimatorReport.feature_importance	Accessor for feature importance related operations.
EstimatorReport.metrics	Accessor for metrics-related operations.

Data

The data accessor helps you to get insights about the dataset used to train and test your estimator.

EstimatorReport.data.help()	Display available methods using rich.
EstimatorReport.data.analyze([data_source, ...])	Plot dataset statistics.

Metrics

The metrics accessor helps you to evaluate the statistical performance of your estimator.

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

Feature importance

The feature_importance accessor helps you to evaluate the importance of the features used to train your estimator.

EstimatorReport.feature_importance.help()	Display available methods using rich.
EstimatorReport.feature_importance.coefficients()	Retrieve the coefficients of a linear model, including the intercept.
EstimatorReport.feature_importance.mean_decrease_impurity()	Retrieve the mean decrease impurity (MDI) of a tree-based model.
EstimatorReport.feature_importance.permutation(*)	Report the permutation feature importance.