rank_verbs.py 文件源码

def get_similarity_scores(verb_token, vectorizer, tf_idf_matrix):
    """ Compute the cosine similarity score of a given verb token against the input corpus TF/IDF matrix.

        :param str verb_token: Surface form of a verb, e.g., *born*
        :param sklearn.feature_extraction.text.TfidfVectorizer vectorizer: Vectorizer
         used to transform verbs into vectors
        :return: cosine similarity score
        :rtype: ndarray
    """
    verb_token_vector = vectorizer.transform([verb_token])
    # Here the linear kernel is the same as the cosine similarity, but faster
    # cf. http://scikit-learn.org/stable/modules/metrics.html#cosine-similarity
    scores = linear_kernel(verb_token_vector, tf_idf_matrix)
    logger.debug("Corpus-wide TF/IDF scores for '%s': %s" % (verb_token, scores))
    logger.debug("Average TF/IDF score for '%s': %f" % (verb_token, average(scores)))
    return scores