TMDetection.py 文件源码

def random_forest(self, sensors_set):
        features = list(self.dataset.get_sensors_set_features(sensors_set))
        print("RANDOM FOREST.....")
        print("CLASSIFICATION BASED ON THESE SENSORS: ", self.dataset.get_remained_sensors(sensors_set))
        print("NUMBER OF FEATURES: ", len(features))
        train_features, train_classes, test_features, test_classes = self.__get_sets_for_classification(
            self.dataset.get_train, self.dataset.get_test, features)
        classifier_forest = RandomForestClassifier(n_estimators=const.PAR_RF_ESTIMATOR)
        classifier_forest.fit(train_features, train_classes)
        test_prediction = classifier_forest.predict(test_features)
        acc = accuracy_score(test_classes, test_prediction)
        df_feature = pd.DataFrame(
            {'accuracy': acc, 'featureName': features, 'importance': classifier_forest.feature_importances_})
        df_feature = df_feature.sort_values(by='importance', ascending=False)
        print("ACCURACY : " + str(acc))
        print("END RANDOM FOREST")

        if not os.path.exists(const.DIR_RESULTS):
            os.makedirs(const.DIR_RESULTS)
        df_feature.to_csv(const.DIR_RESULTS + "/" + str(sensors_set) + const.FILE_RANDOM_FOREST_RESULTS, index=False)

    # neural network algorithm training on training al train set and test on all test set