Graph_algorithm/OpenANE
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix row_as_probdist

Browse Source
This commit is contained in:
Dongzy 2018-11-17 21:09:15 +08:00
parent d486f011e8
commit 4696bc9497
2 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/libnrl/abrw.py
View File

@ -8,7 +8,7 @@ import gensim
from gensim.models import Word2Vec
from . import walker
import networkx as nx
from libnrl.utils import *
from .utils import *
import multiprocessing
'''
@ -99,7 +99,7 @@ class ABRW(object):
sum_row = P_X[i].sum()
if sum_row != 1.0: #to avoid some numerical issue...
delta = 1.0 - sum_row #delta is very very samll number say 1e-10 or even less...
P_X[i][i] = P_X[i][i] + delta #the diagnoal must be largest of the that row + delta --> almost no effect
P_X[i, i] = P_X[i, i] + delta #the diagnoal must be largest of the that row + delta --> almost no effect
t4 = time.time()
print('topk time: ',t2-t1 ,'row normlize time: ',t3-t2, 'dealing numerical issue time: ', t4-t3)
del A, X, X_compressed, X_sim
@ -108,13 +108,14 @@ class ABRW(object):
print('------alpha for P = alpha * P_A + (1-alpha) * P_X----: ', self.alpha)
n = self.g.get_num_nodes()
P = np.zeros((n,n), dtype=float)
# TODO: Vectorization
for i in range(n):
if (P_A[i] == 0).all(): #single node case if the whole row are 0s
if (P_A[i] == 0).toarray().all(): #single node case if the whole row are 0s
#if P_A[i].sum() == 0:
P[i] = P_X[i] #use 100% attr info to compensate
else: #non-single node case; use (1.0-self.alpha) attr info to compensate
P[i] = self.alpha * P_A[i] + (1.0-self.alpha) * P_X[i]
print('# of single nodes for P_A: ', n - P_A.sum(axis=1).sum(), ' # of non-zero entries of P_A: ', np.count_nonzero(P_A))
print('# of single nodes for P_A: ', n - P_A.sum(axis=1).sum(), ' # of non-zero entries of P_A: ', P_A.count_nonzero())
print('# of single nodes for P_X: ', n - P_X.sum(axis=1).sum(), ' # of non-zero entries of P_X: ', np.count_nonzero(P_X))
t5 = time.time()
print('ABRW biased transition prob preprocessing time: {:.2f}s'.format(t5-t4))

2
src/libnrl/utils.py
View File

@ -33,7 +33,7 @@ def row_as_probdist(mat):
return dense matrix if input is dense matrix or numpy array
return sparse matrix for sparse matrix input
"""
row_sum = np.array(mat.sum(axis=1)) # type: np.array
row_sum = np.array(mat.sum(axis=1)).ravel() # type: np.array
zero_rows = row_sum == 0
row_sum[zero_rows] = 1
diag = sparse.dia_matrix((1 / row_sum, 0), (mat.shape[0], mat.shape[0]))