def _spacey_metagraph_only_random_walk(
self, root_node): # metapath, multi-metapath, metagraph
root_type = self._net.get_node_type(root_node)
if root_type not in self._metagraph:
# root_type = random.choice(list(self._metagraph.nodes))
# root_node = random.choice(self._nodes_type_dict[root_type][0])
return []
if self._history_position == "local":
history = np.ones([self.node_types_size], dtype=np.float64)
elif self._history_position == "global":
history = self._history
# current node
cur_node = root_node
cur_type = root_type
path = [str(cur_node)]
for __ in range(self._walk_length):
# logger.info("history={}".format(history))
# choose next type
if random.random() < self._walk_restart:
cur_node = root_node
cur_type = root_type
if random.random() < self._alpha:
cur_node_adj_typelist = self._adj_lookupdict[cur_node].keys()
next_type_list = [
v for v in self._metagraph[cur_type]
if v in cur_node_adj_typelist
]
if len(next_type_list) == 0:
# cur_type = root_type
# cur_node = root_node
break
elif len(next_type_list) == 1:
cur_type = next_type_list[0]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
else:
occupancy = history[next_type_list]
cur_type = utils.unigram_sample(population=next_type_list,
size=1,
weight=occupancy)[0]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
history[cur_type] += 1
else:
cur_node_adj_typelist = self._adj_lookupdict[cur_node].keys()
next_type_list = [
v for v in self._metagraph[cur_type]
if v in cur_node_adj_typelist
]
if len(next_type_list) == 0:
# cur_type = root_type
# cur_node = root_node
break
else:
cur_type = random.choice(next_type_list)
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
history[cur_type] += 1
path.append(str(cur_node))
return path
def _spacey_metaschema_only_random_walk(self, root_node, file_vector,
file_dist, window_size):
root_type = self._net.get_node_type(root_node)
if self._history_position == "local":
history = np.ones([self.node_types_size], dtype=np.float64)
elif self._history_position == "global":
history = self._history
occur_count_vector = np.zeros(self.nodes_size, dtype=np.int32)
occur_count_vector[root_node] = 1
last_distribution = occur_count_vector / np.sum(occur_count_vector)
fr_dist = open(file_dist, "w")
cur_node = root_node
cur_type = root_type
for wl_cnt in range(1, self._walk_length + 1):
next_type_list = list(self._adj_lookupdict[cur_node].keys())
if random.random() < self._alpha:
if len(next_type_list) == 0:
cur_type = root_type
cur_node = root_node
elif len(next_type_list) == 1:
cur_type = next_type_list[0]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
else:
occupancy = history[next_type_list]
cur_type = utils.unigram_sample(population=next_type_list,
size=1,
weight=occupancy)[0]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
history[cur_type] += 1
else:
if len(next_type_list) == 0:
cur_type = root_type
cur_node = root_node
else:
cur_type = random.choice(next_type_list)
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
history[cur_type] += 1
occur_count_vector[cur_node] += 1
if wl_cnt % window_size == 0:
cur_distribution = occur_count_vector / np.sum(
occur_count_vector)
mix_distribution = (cur_distribution + last_distribution) / 2
JS_dist = (scipy.stats.entropy(
cur_distribution, mix_distribution) + scipy.stats.entropy(
last_distribution, mix_distribution)) / 2
EUC_dist = np.sqrt(
np.sum(np.square(cur_distribution - last_distribution)))
fr_dist.write("{} {}\n".format(JS_dist, EUC_dist))
fr_dist.flush()
last_distribution = cur_distribution
fr_dist.close()
np.savetxt(file_vector, occur_count_vector, fmt="%d")
return
def _spacey_metatree_only_random_walk(
self, root_node, file_vector, file_dist,
window_size): # metapath, multi-metapath, metagraph
root_type = self._net.get_node_type(root_node)
if root_type not in self._metatree_type_id_dict:
return []
root_id = random.choice(self._metatree_type_id_dict[root_type])
if self._history_position == "local":
history = np.ones([len(self._metagraph.nodes())], dtype=np.float64)
elif self._history_position == "global":
history = self._history
occur_count_vector = np.zeros(self.nodes_size, dtype=np.int32)
occur_count_vector[root_node] = 1
last_distribution = occur_count_vector / np.sum(occur_count_vector)
fr_dist = open(file_dist, "w")
# current node
cur_node = root_node
cur_type = root_type
cur_id = root_id
for wl_cnt in range(1, self._walk_length + 1):
if random.random() < self._alpha:
cur_node_adj_typelist = self._adj_lookupdict[cur_node].keys()
next_id_list = [
v for v in self._metagraph[cur_id] if
self._metagraph.nodes[v]["type"] in cur_node_adj_typelist
]
if len(next_id_list) == 0:
cur_node = root_node
cur_type = root_type
cur_id = root_id
elif len(next_id_list) == 1:
cur_id = next_id_list[0]
cur_type = self._metagraph.nodes[cur_id]["type"]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
else:
occupancy = history[next_id_list]
cur_id = utils.unigram_sample(population=next_id_list,
size=1,
weight=occupancy)[0]
cur_type = self._metagraph.nodes[cur_id]["type"]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
# logger.info('next: %d %d' % (cur_type, cur_id))
history[cur_id] += 1
# spacey out
cur_id = utils.unigram_sample(
population=self._metatree_type_id_dict[cur_type],
size=1,
weight=history[self._metatree_type_id_dict[cur_type]])[0]
else:
cur_node_adj_typelist = self._adj_lookupdict[cur_node].keys()
next_id_list = [
v for v in self._metagraph[cur_id] if
self._metagraph.nodes[v]["type"] in cur_node_adj_typelist
]
if len(next_id_list) == 0:
cur_node = root_node
cur_type = root_type
cur_id = root_id
else:
cur_id = random.choice(next_id_list)
cur_type = self._metagraph.nodes[cur_id]["type"]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
history[cur_id] += 1
occur_count_vector[cur_node] += 1
if wl_cnt % window_size == 0:
cur_distribution = occur_count_vector / np.sum(
occur_count_vector)
mix_distribution = (cur_distribution + last_distribution) / 2
JS_dist = (scipy.stats.entropy(
cur_distribution, mix_distribution) + scipy.stats.entropy(
last_distribution, mix_distribution)) / 2
EUC_dist = np.sqrt(
np.sum(np.square(cur_distribution - last_distribution)))
fr_dist.write("{} {}\n".format(JS_dist, EUC_dist))
fr_dist.flush()
last_distribution = cur_distribution
fr_dist.close()
np.savetxt(file_vector, occur_count_vector, fmt="%d")
return
def _spacey_metatree_random_walk(
self,
root_node,
walk_times=0): # metapath, multi-metapath, metagraph
root_type = self._net.get_node_type(root_node)
if root_type not in self._metatree_type_id_dict:
root_type = random.choice(list(self._metatree_type_id_dict.keys()))
root_node = random.choice(self._nodes_type_dict[root_type][0])
root_id = random.choice(self._metatree_type_id_dict[root_type])
context_nodes_dict = {} #
if self._history_position == "local":
history = np.ones([len(self._metagraph.nodes())], dtype=np.float64)
elif self._history_position == "global":
history = self._history
for _ in range(walk_times):
if self._history_position == "local_walktime":
history = np.ones([len(self._metagraph.nodes())],
dtype=np.float64)
# current node
cur_node = root_node
cur_type = root_type
cur_id = root_id
# logger.info('start: %d %d' % (cur_type, cur_id))
for __ in range(self._walk_length):
# choose next type
if random.random() < self._walk_restart:
cur_node = root_node
cur_type = root_type
cur_id = root_id
cur_node_adj_typelist = self._adj_lookupdict[cur_node].keys()
next_id_list = [
v for v in self._metagraph[cur_id] if
self._metagraph.nodes[v]["type"] in cur_node_adj_typelist
]
if len(next_id_list) == 0:
cur_type = root_type
cur_node = root_node
cur_id = root_id
elif len(next_id_list) == 1:
cur_id = next_id_list[0]
cur_type = self._metagraph.nodes[cur_id]["type"]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
history[cur_id] += 1
else:
occupancy = history[next_id_list]
cur_id = utils.unigram_sample(population=next_id_list,
size=1,
weight=occupancy)[0]
cur_type = self._metagraph.nodes[cur_id]["type"]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
history[cur_id] += 1
cur_id = utils.unigram_sample(
population=self._metatree_type_id_dict[cur_type],
size=1,
weight=history[self._metatree_type_id_dict[cur_type]])[0]
if cur_type in context_nodes_dict:
context_nodes_dict[cur_type][0].append(
cur_node) # context_list
context_nodes_dict[cur_type][1].add(cur_node) # except_set
else:
context_nodes_dict[cur_type] = [[cur_node],
{cur_node, root_node}]
type_context_nodes_list = []
type_neg_nodes_list = []
type_mask_list = []
for k in range(self.node_types_size):
if k in context_nodes_dict:
context_nodes = context_nodes_dict[k][0]
except_set = context_nodes_dict[k][1]
type_mask_list.append(1)
type_context_nodes_list.append(context_nodes)
type_neg_nodes_list.append(
utils.neg_sample(self._nodes_type_dict[k][0],
except_set,
num=self._neg_sampled,
alias_table=self._nodes_type_dict[k][1]))
else:
type_mask_list.append(0)
type_context_nodes_list.append([0])
type_neg_nodes_list.append([0])
return root_node, type_context_nodes_list, type_mask_list, type_neg_nodes_list
def _spacey_metaschema_random_walk(self, root_node, walk_times=0):
root_type = self._net.get_node_type(root_node)
context_nodes_dict = {} #
if self._history_position == "local":
history = np.ones([self.node_types_size], dtype=np.float64)
elif self._history_position == "global":
history = self._history
for _ in range(walk_times):
if self._history_position == "local_walktime":
history = np.ones([self.node_types_size], dtype=np.float64)
# current node
cur_node = root_node
cur_type = root_type
for __ in range(self._walk_length):
# choose next type
if random.random() < self._walk_restart:
cur_node = root_node
cur_type = root_type
next_type_list = list(self._adj_lookupdict[cur_node].keys())
if len(next_type_list) == 0:
cur_type = root_type
cur_node = root_node
elif len(next_type_list) == 1:
cur_type = next_type_list[0]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
history[cur_type] += 1
else:
occupancy = history[next_type_list]
cur_type = utils.unigram_sample(population=next_type_list,
size=1,
weight=occupancy)[0]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
history[cur_type] += 1
if cur_type in context_nodes_dict:
context_nodes_dict[cur_type][0].append(
cur_node) # context_list
context_nodes_dict[cur_type][1].add(cur_node) # except_set
else:
context_nodes_dict[cur_type] = [[cur_node],
{cur_node, root_node}]
type_context_nodes_list = []
type_neg_nodes_list = []
type_mask_list = []
for k in range(self.node_types_size):
if k in context_nodes_dict:
context_nodes = context_nodes_dict[k][0]
except_set = context_nodes_dict[k][1]
type_mask_list.append(1)
type_context_nodes_list.append(context_nodes)
type_neg_nodes_list.append(
utils.neg_sample(self._nodes_type_dict[k][0],
except_set,
num=self._neg_sampled,
alias_table=self._nodes_type_dict[k][1]))
else:
type_mask_list.append(0)
type_context_nodes_list.append([0])
type_neg_nodes_list.append([0])
return root_node, type_context_nodes_list, type_mask_list, type_neg_nodes_list
def _spacey_metatree_only_random_walk(
self, root_node): # metapath, multi-metapath, metagraph
root_type = self._net.get_node_type(root_node)
if root_type not in self._metatree_type_id_dict:
return []
root_id = random.choice(self._metatree_type_id_dict[root_type])
if self._history_position == "local":
history = np.ones([len(self._metagraph.nodes())], dtype=np.float64)
elif self._history_position == "global":
history = self._history
# current node
cur_node = root_node
cur_type = root_type
cur_id = root_id
path = [str(cur_node)]
for __ in range(self._walk_length):
# logger.info("history={}".format(history))
# choose next type
if random.random() < self._walk_restart:
cur_node = root_node
cur_type = root_type
cur_id = root_id
if random.random() < self._alpha:
cur_node_adj_typelist = self._adj_lookupdict[cur_node].keys()
next_id_list = [
v for v in self._metagraph[cur_id] if
self._metagraph.nodes[v]["type"] in cur_node_adj_typelist
]
if len(next_id_list) == 0:
break
elif len(next_id_list) == 1:
cur_id = next_id_list[0]
cur_type = self._metagraph.nodes[cur_id]["type"]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
else:
occupancy = history[next_id_list]
cur_id = utils.unigram_sample(population=next_id_list,
size=1,
weight=occupancy)[0]
cur_type = self._metagraph.nodes[cur_id]["type"]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
# logger.info('next: %d %d' % (cur_type, cur_id))
history[cur_id] += 1
# spacey out
cur_id = utils.unigram_sample(
population=self._metatree_type_id_dict[cur_type],
size=1,
weight=history[self._metatree_type_id_dict[cur_type]])[0]
else:
cur_node_adj_typelist = self._adj_lookupdict[cur_node].keys()
next_id_list = [
v for v in self._metagraph[cur_id] if
self._metagraph.nodes[v]["type"] in cur_node_adj_typelist
]
if len(next_id_list) == 0:
break
else:
cur_id = random.choice(next_id_list)
cur_type = self._metagraph.nodes[cur_id]["type"]
cur_node = random.choice(
self._adj_lookupdict[cur_node][cur_type])
history[cur_id] += 1
# logger.info('next: %d %d' % (cur_type, cur_id))
# spacey out
path.append(str(cur_node))
return path