similarity.py 文件源码

def cosine_similarity(repr1, repr2):
    """Calculates cosine similarity (https://en.wikipedia.org/wiki/Cosine_similarity)."""
    if repr1 is None or repr2 is None:
        return 0
    assert not (np.isnan(repr2).any() or np.isinf(repr2).any())
    assert not (np.isnan(repr1).any() or np.isinf(repr1).any())
    sim = 1 - scipy.spatial.distance.cosine(repr1, repr2)
    if np.isnan(sim):
        # the similarity is nan if no term in the document is in the vocabulary
        return 0
    return sim