wehub-resource-sync
30 lines
816 B
Python
30 lines
816 B
Python
#!/usr/bin/env python
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
This file re-uses implementation from https://github.com/yl-1993/learn-to-cluster
|
|
"""
|
|
|
|
import numpy as np
|
|
import scipy.sparse as sp
|
|
from scipy.sparse import coo_matrix
|
|
|
|
|
|
def row_normalize(mx):
|
|
"""Row-normalize sparse matrix"""
|
|
rowsum = np.array(mx.sum(1))
|
|
# if rowsum <= 0, keep its previous value
|
|
rowsum[rowsum <= 0] = 1
|
|
r_inv = np.power(rowsum, -1).flatten()
|
|
r_inv[np.isinf(r_inv)] = 0.0
|
|
r_mat_inv = sp.diags(r_inv)
|
|
mx = r_mat_inv.dot(mx)
|
|
return mx, r_inv
|
|
|
|
|
|
def sparse_mx_to_indices_values(sparse_mx):
|
|
sparse_mx = sparse_mx.tocoo().astype(np.float32)
|
|
indices = np.vstack((sparse_mx.row, sparse_mx.col)).astype(np.int64)
|
|
values = sparse_mx.data
|
|
shape = np.array(sparse_mx.shape)
|
|
return indices, values, shape
|