visualize_space.py 文件源码

def main():

    args = parse_args()

    print('Called with args:')
    print(args)
    lang_db = get_language_model(args.lang_name)
    imdb = get_imdb(args.imdb_name)

    # Get words in space
    vocabulary = imdb.get_labels(args.space)

    # Get features for words
    wv = [lang_db.word_vector(w) for w in vocabulary]
    from sklearn.metrics.pairwise import cosine_similarity
    from scipy import spatial
    #spatial.distance.cosine(dataSetI, dataSetII)
    tsne = TSNE(n_components=2, random_state=0)
    np.set_printoptions(suppress=True)
    Y = tsne.fit_transform(wv)

    plt.scatter(Y[:, 0], Y[:, 1])
    for label, x, y in zip(vocabulary, Y[:, 0], Y[:, 1]):
        plt.annotate(label, xy=(x, y), xytext=(0, 0), textcoords='offset points')
    plt.show()