knock85.py 文件源码

def dimension_compression():
    X_t_c = make_matrix()
    token_list = []
    contexts_list = []
    for token, contexts in sorted(X_t_c.items()):
        token_list.append(token)
        contexts_list.append(contexts)

    pca = PCA(n_components = 300)
    DictoVec = DictVectorizer(sparse = True)

    sparse = DictoVec.fit_transform(contexts_list)

    print(sparse.shape)

    vec_list = pca.fit_transform(sparse.todense())

    word_vec = {}
    for token, vec in zip(token_list, vec_list):
        word_vec[token] = vec

    return word_vec