document_scores.py 文件源码

def __init__(self, *args, **kwargs):
        super(score_simple, self).__init__(*args, **kwargs)

        f_db = os.path.join(
            kwargs['output_data_directory'],
            kwargs['term_frequency']['f_db']
        )
        if not os.path.exists(f_db):
            msg = "{} not computed yet, needed for TF methods!"
            raise ValueError(msg.format(f_db))

        score_config = simple_config.load()["score"]
        f_csv = os.path.join(
            score_config["output_data_directory"],
            score_config["term_document_frequency"]["f_db"],
        )
        IDF = pd.read_csv(f_csv)
        IDF = dict(zip(IDF["word"].values, IDF["count"].values))
        self.corpus_N = IDF.pop("__pipeline_document_counter")

        # Compute the IDF
        for key in IDF:
            IDF[key] = np.log(float(self.corpus_N) / (IDF[key] + 1))
        self.IDF = IDF