tfidf_retrieval.py 文件源码

def tfidf_retrieval(tfidf_vec, train_contexts_txt, train_responses_txt, output_file):
    print type(tfidf_vec)
    tfidf_vec = tfidf_vec.toarray()
    print tfidf_vec.shape
    prod_mat = np.dot(tfidf_vec, tfidf_vec.T)
    print prod_mat.shape
    prod_mat = prod_mat / mat_vector_2norm_squared(tfidf_vec)
    print prod_mat.shape

    response_list = []
    for i in xrange(len(prod_mat)):
        row = prod_mat[i]
        # No idea what's going on here. See the following page:
        # stackoverflow.com/questions/6910641/how-to-get-indices-of-n-maximum-values-in-a-numpy-array
        ind = np.argpartition(row, -2)[-2:]
        ind = ind[np.argsort(row[ind])][0]
        response_list.append(train_responses_txt[ind])
        print train_contexts_txt[i]
        print response_list[i]

    with open(output_file, 'w') as f1:
        for response in response_list:
            f1.write(response)