Add support for more metrics

casper-hansen / Nested-Cross-Validation

Nested cross-validation for unbiased predictions. Can be used with Scikit-Learn, XGBoost, Keras and LightGBM, or any other estimator that implements the scikit-learn interface.

MIT License

62 stars 20 forks source link

Add support for more metrics #6

Closed casper-hansen closed 5 years ago

casper-hansen commented 5 years ago

Go through each metric from sklearn.metrics and make sure every metric works.

Supported metrics: the ones with metric(y_true, y_pred)

(i.e. roc_auc_score doesn't work, since it implements a metric(y_true, y_score))

casper-hansen commented 5 years ago

Support for predict_proba on model must be implemented to get a y_score.

casper-hansen commented 5 years ago

Support added for binary roc_auc_score in dev

casper-hansen commented 5 years ago

Support added for multiclass scoring metrics. Use 'multiclass_average' in cv_options and specify either ‘micro’, ‘macro’, ‘samples’ or ‘weighted’