tfidf_doc_ranker.py 文件源码

def closest_docs(self, query, k=1):
        """Closest docs by dot product between query and documents
        in tfidf weighted word vector space.
        """
        spvec = self.text2spvec(query)
        res = spvec * self.doc_mat

        if len(res.data) <= k:
            o_sort = np.argsort(-res.data)
        else:
            o = np.argpartition(-res.data, k)[0:k]
            o_sort = o[np.argsort(-res.data[o])]

        doc_scores = res.data[o_sort]
        doc_ids = [self.get_doc_id(i) for i in res.indices[o_sort]]
        return doc_ids, doc_scores