models.py 文件源码

def run(self):
        training_x, training_y, training_ids = self.get_training_data()
        test_x, test_y, test_ids = self.get_test_data()
        clf = self.define_model(self.model_name, self.model_params)
        clf.fit(training_x, training_y)
        res_predict = clf.predict(test_x)
        if (self.model_name == "SGDClassifier" and (clf.loss =="hinge" or clf.loss == "perceptron")) or self.model_name == "linear.SVC":
            res = list(clf.decision_function(test_x))
        else:
            res = list(clf.predict_proba(test_x)[:,1])
        #fp, fn, tp, tn = self.compute_confusion_matrix(res[:,0], test_y)
        result_dictionary = {'training_ids': training_ids, 
                             'predictions_test_y': list(res_predict),
                             'prob_prediction_test_y': res ,
                             'test_y': list(test_y),
                             'test_ids': list(test_ids),
                             'model_name': self.model_name,
                             'model_params': self.model_params,
                             'label': self.label,
                             'feature_columns_used': self.cols_to_use,
                             'config': self.config,
                             'feature_importance': self.get_feature_importance(clf, self.model_name),
                             'columned_used_for_feat_importance': list(training_x.columns.values)}
        return  result_dictionary, clf