Metrics#

Regression#

`aic_score`(y_true, y_score, input_relation[, k])	Returns the AIC score.
`anova_table`(y_true, y_score, input_relation)	Computes the ANOVA table.
`bic_score`(y_true, y_score, input_relation[, k])	Returns the BIC score.
`explained_variance`(y_true, y_score, ...)	Computes the Explained Variance.
`max_error`(y_true, y_score, input_relation)	Computes the Max Error.
`mean_absolute_error`(y_true, y_score, ...)	Computes the Mean Absolute Error.
`mean_squared_error`(y_true, y_score, ...[, root])	Computes the Mean Squared Error.
`mean_squared_log_error`(y_true, y_score, ...)	Computes the Mean Squared Log Error.
`median_absolute_error`(y_true, y_score, ...)	Computes the Median Absolute Error.
`quantile_error`(y_true, y_score, ...)	Computes the input quantile of the Error.
`r2_score`(y_true, y_score, input_relation[, ...])	Computes the R2 score.
`regression_report`(y_true, y_score, ...[, ...])	Computes a regression report using multiple metrics to evaluate the model (`r2`, `mse`, `max error`...).

Classification#

`accuracy_score`(y_true, y_score, input_relation)	Computes the Accuracy score.
`balanced_accuracy_score`(y_true, y_score, ...)	Computes the Balanced Accuracy.
`best_cutoff`(y_true, y_score, input_relation)	Computes the ROC AUC (Area Under Curve).
`classification_report`([y_true, y_score, ...])	Computes a classification report using multiple metrics (AUC, accuracy, PRC AUC, F1...).
`confusion_matrix`(y_true, y_score, input_relation)	Computes the confusion matrix.
`critical_success_index`(y_true, y_score, ...)	Computes the Critical Success Index.
`diagnostic_odds_ratio`(y_true, y_score, ...)	Computes the Diagnostic odds ratio.
`false_discovery_rate`(y_true, y_score, ...[, ...])	Computes the False Discovery Rate.
`false_omission_rate`(y_true, y_score, ...[, ...])	Computes the False Omission Rate.
`false_negative_rate`(y_true, y_score, ...[, ...])	Computes the False Negative Rate.
`false_positive_rate`(y_true, y_score, ...[, ...])	Computes the False Positive Rate.
`f1_score`(y_true, y_score, input_relation[, ...])	Computes the F1 score.
`fowlkes_mallows_index`(y_true, y_score, ...)	Computes the Fowlkes–Mallows index.
`informedness`(y_true, y_score, input_relation)	Computes the Informedness.
`log_loss`(y_true, y_score, input_relation[, ...])	Computes the Log Loss.
`markedness`(y_true, y_score, input_relation)	Computes the Markedness.
`matthews_corrcoef`(y_true, y_score, ...[, ...])	Computes the Matthews Correlation Coefficient.
`negative_likelihood_ratio`(y_true, y_score, ...)	Computes the Positive Likelihood ratio.
`negative_predictive_score`(y_true, y_score, ...)	Computes the Negative Predictive Score.
`positive_likelihood_ratio`(y_true, y_score, ...)	Computes the Positive Likelihood ratio.
`precision_score`(y_true, y_score, input_relation)	Computes the Precision Score.
`prevalence_threshold`(y_true, y_score, ...[, ...])	Computes the Prevalence Threshold.
`prc_auc_score`(y_true, y_score, input_relation)	Computes the area under the curve (AUC) of a Precision-Recall (PRC) curve.
`recall_score`(y_true, y_score, input_relation)	Computes the Recall score.
`roc_auc_score`(y_true, y_score, input_relation)	Computes the ROC AUC (Area Under Curve).
`specificity_score`(y_true, y_score, ...[, ...])	Computes the Specificity score.