clf_for_eval.set_params(**clf_gs.best_params_) metrics, std = training_utils.evaluate_on_cv(training_data, train_X_all, clf_for_eval, fuzzy_option, fuzzy_dist_column, fuzzy_err_column, xgb_flag=True) pr_curve = training_utils.predict_and_pr_curve_on_cv(training_data, train_X_all, clf_for_eval, fuzzy_option, fuzzy_dist_column, fuzzy_err_column, xgb_flag=True) # best model from grid search: clf_best = clf_gs.best_estimator_ # generalization: general_data["y_pred"] = clf_best.predict(general_X) general_data["y_prob_positive_class"] = clf_best.predict_proba( general_X)[:, 1] training_utils.save_results(output_path, experiment_name, fuzzy_option, training_data, general_data, metrics, std, pr_curve, best_param_df, gs_results_df, info_columns, features) print("done.")
fuzzy_dist_column, fuzzy_err_column) pr_curve = training_utils.predict_and_pr_curve_on_cv( training_data, train_X, clf, fuzzy_option, fuzzy_dist_column, fuzzy_err_column) # fit to the data: if fuzzy_option == "normal": clf.fit(X=train_X, y=training_data["Y"]) elif fuzzy_option == "fuzzy_dist": clf.fit(X=train_X, y=training_data["Y"], sample_weight=training_data[fuzzy_dist_column].values.T[0]) elif fuzzy_option == "fuzzy_err": clf.fit(X=train_X, y=training_data["Y"], sample_weight=training_data[fuzzy_err_column].values.T[0]) else: print("wrong fuzzy option") # generalization: general_data["y_pred"] = clf.predict(general_X) general_data["y_prob_positive_class"] = clf.predict_proba(general_X)[:, 1] training_utils.save_results(output_path, experiment_name, fuzzy_option, training_data, general_data, metrics, std, pr_curve, pd.DataFrame(), pd.DataFrame(), info_columns, features) print("done.")