libcity.model.utils¶
-
libcity.model.utils.build_sparse_matrix(device, lap)[源代码]¶ 构建稀疏矩阵(tensor)
- 参数
device –
lap – 拉普拉斯
Returns:
-
libcity.model.utils.calculate_normalized_laplacian(adj)[源代码]¶ L = D^-1/2 (D-A) D^-1/2 = I - D^-1/2 A D^-1/2 对称归一化的拉普拉斯
- 参数
adj – adj matrix
- 返回
L
- 返回类型
np.ndarray
-
libcity.model.utils.calculate_random_walk_matrix(adj_mx)[源代码]¶ L = D^-1 * A 随机游走拉普拉斯
- 参数
adj_mx – adj matrix
- 返回
L
- 返回类型
np.ndarray
-
libcity.model.utils.calculate_scaled_laplacian(adj_mx, lambda_max=2, undirected=True)[源代码]¶ 计算近似后的拉普莱斯矩阵~L
- 参数
adj_mx –
lambda_max –
undirected –
- 返回
~L = 2 * L / lambda_max - I
-
libcity.model.utils.get_cheb_polynomial(l_tilde, k)[源代码]¶ compute a list of chebyshev polynomials from T_0 to T_{K-1}
- 参数
l_tilde (scipy.sparse.coo.coo_matrix) – scaled Laplacian, shape (N, N)
k (int) – the maximum order of chebyshev polynomials
- 返回
cheb_polynomials, length: K, from T_0 to T_{K-1}
- 返回类型
list(np.ndarray)