similarity.py 文件源码

def jaccard_similarity_weighted(F, fill_diagonal=True):
    assert F.format == 'csr'
    if not F.has_sorted_indices:
        F.sort_indices()

    ind = F.indices
    ptr = F.indptr
    dat = F.data.astype(np.float64, copy=False) # dtype needed for jaccard computation

    shift = 1 if fill_diagonal else 0
    data, rows, cols = _jaccard_similarity_weighted_tri(dat, ind, ptr, shift)

    S = sp.sparse.coo_matrix((data, (rows, cols)), shape=(F.shape[0],)*2).tocsc()
    S += S.T # doubles diagonal values if fill_diagonal is False

    if fill_diagonal:
        set_diagonal_values(S, 1)
    else:
        set_diagonal_values(S, np.sign(S.diagonal())) # set to 1, preserve zeros
    return S