similarity.py 文件源码

def compute_document_similarity(X):
    '''
    From a matrix of unit distances, computes the cosine similarity
    then changes to the angular distance (for a proper metric).
    '''

    S = cdist(X, X, metric='cosine')
    S -= 1
    S *= -1
    S[S > 1] = 1.0
    S[S < 0] = 0.0

    # Set nan values to zero
    S[np.isnan(S)] = 0

    # Convert to angular distance (a proper metric)
    S = 1 - (np.arccos(S) / np.pi)
    assert(not np.isnan(S).any())
    assert(not np.isinf(S).any())

    return S