feature_construction.py 文件源码

def _percentage_capitalized_word_in_answer(self, row):
        """Percentage of capitalized words in the sentence that are in the answer
        - Args:
            row(pandas.dataframe): input pandas dataframe
        - Returns:
            row(pandas.dataframe): result a pandas dataframe with new feature
        """
        answer = row.Answer
        sentence = row.Sentence
        if answer is not None and sentence is not None:
            tokens = sentence.split()
            num_tokens = len(tokens)
            cap_tokens = [i for i in tokens if i.isupper() == True]
            cap_tokens_in_answer = [i for i in cap_tokens if i in answer]
            row['PERCENT_CAPITALIZED_WORDS_IN_ANSWER'] = float(
                len(cap_tokens_in_answer)) / num_tokens
            return row
        else:
            row['PERCENT_CAPITALIZED_WORDS_IN_ANSWER'] = 0
            return row