prediction_data.py 文件源码

def setup_training_columns(self):
        """ Return array of Training Columns.

        When "training_columns" array is empty it means return all columns except the "target_column"
        """

        training_columns = self.prediction_config.DATASET_LOCATION[self.dataset_choice]["training_columns"]

        if not training_columns and not isinstance(self.df_listings, type(None)):
            features = self.df_listings.columns.tolist()

            # Remove "target_column" (if already in the dataset, as may not yet have been generated by Clustering)
            if self.target_column in features:
                features.remove(self.target_column)

            # Remove columns containing Excluded full text
            for index, column_name in enumerate(self.prediction_config.EXCLUDE_TRAINING_COLUMNS_WITH_FULL_TEXT):
                if column_name in features:
                    features.remove(column_name)

            # Retain columns that do not contain Excluded partial text
            is_features_to_retain = [False] * len(features)
            for idx_outer, column_partial_name in enumerate(self.prediction_config.EXCLUDE_TRAINING_COLUMNS_WITH_PARTIAL_TEXT):
                for idx_inner, column_name in enumerate(features):
                    if column_partial_name not in column_name:
                        is_features_to_retain[idx_inner] = True
            filtered = list(compress(features, is_features_to_retain))
            return filtered
        else:
            return training_columns