feature_construction.py 文件源码

def _answer_quantifier_density(self, row):
        """Percentage of tokens in the answer that are quantifier words
        - Args:
            row(pandas.dataframe): input pandas dataframe
        - Returns:
            row(pandas.dataframe): result a pandas dataframe with new feature
        """
        answer = row.Answer
        if answer:
            tokens = answer.split()
            answer_len = len(tokens)
            quantifier_tokens = [
                i for i in tokens if i in ling.QUANTIFIER_WORDS]
            quantifier_tokens_len = len(quantifier_tokens)
            row['ANSWER_QUANTIFIER_DENSITY'] = float(
                quantifier_tokens_len) / answer_len
            return row
        else:
            row['ANSWER_QUANTIFIER_DENSITY'] = 0
            return row