kmeans.py 文件源码

def closest_label(X, labels, vec, dist='cosine', ooc_only=False, top=10):
    if dist == 'euclidean':
        sim = euclidean_distances(X, vec.reshape(1, -1))
    elif dist == 'cosine':
        sim = cosine_similarity(X, vec.reshape(1, -1))
    else:
        raise NotImplementedError('dist must be euclidean or cosine')
    # get the top five indices
    indices = sim.argsort(axis=0)[-top:][::-1]
    words = []
    for i in indices:
        words.append(labels[i[0]])
    return " ".join(words)