def learn_embedding(self,
graph=None,
edge_f=None,
is_weighted=False,
no_python=False):
c_flag = True
if not graph and not edge_f:
raise Exception('graph/edge_f needed')
if no_python:
try:
from c_ext import graphFac_ext
except ImportError:
print(
'Could not import C++ module for Graph Factorization. Reverting to python implementation. Please recompile graphFac_ext from graphFac.cpp using bjam'
)
c_flag = False
if c_flag:
if edge_f:
graph = graph_util.loadGraphFromEdgeListTxt(edge_f)
graph_util.saveGraphToEdgeListTxt(graph, 'tempGraph.graph')
is_weighted = True
edge_f = 'tempGraph.graph'
t1 = time()
graphFac_ext.learn_embedding(edge_f, "tempGraphGF.emb", True,
is_weighted, self._d, self._eta,
self._regu, self._max_iter)
self._X = graph_util.loadEmbedding('tempGraphGF.emb')
t2 = time()
return self._X, (t2 - t1)
if not graph:
graph = graph_util.loadGraphFromEdgeListTxt(edge_f)
t1 = time()
self._node_num = graph.number_of_nodes()
self._X = 0.01 * np.random.randn(self._node_num, self._d)
for iter_id in range(self._max_iter):
if not iter_id % self._print_step:
[f1, f2, f] = self._get_f_value(graph)
print('\t\tIter id: %d, Objective: %g, f1: %g, f2: %g' %
(iter_id, f, f1, f2))
for i, j, w in graph.edges(data='weight', default=1):
if j <= i:
continue
term1 = -(w -
np.dot(self._X[i, :], self._X[j, :])) * self._X[j, :]
term2 = self._regu * self._X[i, :]
delPhi = term1 + term2
self._X[i, :] -= self._eta * delPhi
t2 = time()
return self._X, (t2 - t1)
def learn_embedding(self, graph=None, edge_f=None,
is_weighted=False, no_python=True):
c_flag = True
if not graph and not edge_f:
raise Exception('graph/edge_f needed')
if no_python:
if sys.platform[0] == "w":
args = ["gem/c_exe/gf.exe"]
else:
args = ["gem/c_exe/gf"]
if not graph and not edge_f:
raise Exception('graph/edge_f needed')
if edge_f:
graph = graph_util.loadGraphFromEdgeListTxt(edge_f)
graphFileName = 'gem/intermediate/%s_gf.graph' % self._data_set
embFileName = 'gem/intermediate/%s_%d_gf.emb' % (self._data_set, self._d)
# try:
# f = open(graphFileName, 'r')
# f.close()
# except IOError:
graph_util.saveGraphToEdgeListTxt(graph, graphFileName)
args.append(graphFileName)
args.append(embFileName)
args.append("1") # Verbose
args.append("1") # Weighted
args.append("%d" % self._d)
args.append("%f" % self._eta)
args.append("%f" % self._regu)
args.append("%d" % self._max_iter)
args.append("%d" % self._print_step)
t1 = time()
try:
call(args)
except Exception as e:
print(str(e))
c_flag = False
print('./gf not found. Reverting to Python implementation. Please compile gf, place node2vec in the path and grant executable permission')
if c_flag:
try:
self._X = graph_util.loadEmbedding(embFileName)
except FileNotFoundError:
self._X = np.random.randn(len(graph.nodes), self._d)
t2 = time()
try:
call(["rm", embFileName])
except:
pass
return self._X, (t2 - t1)
if not graph:
graph = graph_util.loadGraphFromEdgeListTxt(edge_f)
t1 = time()
self._node_num = len(graph.nodes)
self._X = 0.01 * np.random.randn(self._node_num, self._d)
for iter_id in range(self._max_iter):
if not iter_id % self._print_step:
[f1, f2, f] = self._get_f_value(graph)
print('\t\tIter id: %d, Objective: %g, f1: %g, f2: %g' % (
iter_id,
f,
f1,
f2
))
for i, j, w in graph.edges(data='weight', default=1):
if j <= i:
continue
term1 = -(w - np.dot(self._X[i, :], self._X[j, :])) * self._X[j, :]
term2 = self._regu * self._X[i, :]
delPhi = term1 + term2
self._X[i, :] -= self._eta * delPhi
t2 = time()
return self._X, (t2 - t1)
