def test_main():
import numpy as np
from features_infra.graph_features import GraphFeatures
from loggers import PrintLogger
import os
import pickle
import networkx as nx
dataset = "citeseer"
logger = PrintLogger("MetaTest")
base_dir = r"/home/benami/git/pygcn/data"
gnx = pickle.load(open(os.path.join(base_dir, dataset, "gnx.pkl"), 'rb'))
max_subgnx = max(nx.connected_component_subgraphs(gnx.to_undirected()),
key=len)
gnx = gnx.subgraph(max_subgnx)
features = GraphFeatures(gnx,
TEST_FEATURES,
dir_path="./%s_features_sub" % dataset,
logger=logger)
features.build(should_dump=True)
measures_mx = features.to_matrix(add_ones=False,
dtype=np.float32,
mtype=np.matrix)
logger.info("Finished")
def create_features(data_name, time_range):
for i in range(time_range):
gnx = pickle.load(open("./dataset/"+data_name+"/pkl/gcn_input/"+"graph_"+str(i)+".pkl","rb"))
# with open(os.path.join('data',str(data_name),'gcn_input', 'graph_'+str(i)+'.pkl'), 'rb') as f:
# gnx = pickle.load(f)
logger = PrintLogger("MyLogger")
features_meta = {
"page_rank": FeatureMeta(PageRankCalculator, {"pr"}),
"general": FeatureMeta(GeneralCalculator, {"gen"}),
"Average_Neighbor_Degree": FeatureMeta(AverageNeighborDegreeCalculator, {"avg_nd"}),
"k_core": FeatureMeta(KCoreCalculator, {"kc"})}
features = GraphFeatures(gnx, features_meta, "./dataset/"+str(data_name)+"/pkl/feature", logger=logger)
features.build()
mx = features.to_matrix(mtype=np.matrix)
pickle.dump(mx, open("./dataset/"+data_name+"/pkl/gcn_input/"+"mx_"+str(i)+".pkl", "wb"))
# with open(os.path.join('data',str(data_name),'gcn_input','mx_'+str(i)+'.pkl'), 'wb') as f:
# pickle.dump(mx, f, protocol=pickle.HIGHEST_PROTOCOL)
return
# with open(os.path.join('data',str(data_name),'pkl', 'mx_1.pkl'), 'rb') as f:
# l = pickle.load(f)
#
# print (l[0])
def create_features():
for i in range(21):
with open(os.path.join('graphs_by_years', 'graph_' + str(i) + '.pkl'),
'rb') as f:
gnx = pickle.load(f)
logger = PrintLogger("MyLogger")
features_meta = {
"page_rank":
FeatureMeta(PageRankCalculator, {"pr"}),
"general":
FeatureMeta(GeneralCalculator, {"gen"}),
"Average_Neighbor_Degree":
FeatureMeta(AverageNeighborDegreeCalculator, {"avg_nd"}),
"k_core":
FeatureMeta(KCoreCalculator, {"kc"}),
}
features = GraphFeatures(gnx,
features_meta,
"/home/dsi/racheli/graph_calculations",
logger=logger)
features.build()
mx = features.to_matrix(mtype=np.matrix)
with open(os.path.join('graphs_by_years', 'mx_' + str(i) + '.pkl'),
'wb') as f:
pickle.dump(mx, f, protocol=pickle.HIGHEST_PROTOCOL)
def __get_features(self):
with open(self.dirname + '/data/' + self.DATASET + '.pickle',
'rb') as f:
data = pkl.load(f)
self._original_adj_matrices = data['A']
y = data['y']
node_labels = []
for a in y.todense():
if a.max() != 0:
node_labels.append(a.argmax())
else:
node_labels.append(-1)
sum_adj = AsymmetricRGCNWithNeighborHistograms.__sum_sparse(self.A)
gnx = nx.from_scipy_sparse_matrix(sum_adj, parallel_edges=True)
gnx = nx.DiGraph(gnx, labels=node_labels)
for n, label in zip(gnx.nodes, node_labels):
gnx.node[n]['label'] = label
real_labels = list(set(node_labels) - {-1})
# Get the features for the graph
NEIGHBOR_FEATURES = {
"first_neighbor_histogram":
FeatureMeta(
nth_neighbor_calculator(1, labels_to_consider=real_labels),
{"fnh", "first_neighbor"}),
"second_neighbor_histogram":
FeatureMeta(
nth_neighbor_calculator(2, labels_to_consider=real_labels),
{"snh", "second_neighbor"}),
}
features_path = os.path.join(os.path.abspath('../features'),
self.DATASET)
features = GraphFeatures(gnx,
NEIGHBOR_FEATURES,
dir_path=features_path)
features.build(include=set(self.idx_train), should_dump=True)
add_ones = bool(
{"first_neighbor_histogram",
"second_neighbor_histogram"}.intersection(NEIGHBOR_FEATURES))
_topo_mx = features.to_matrix(add_ones=add_ones,
dtype=np.float64,
mtype=np.matrix,
should_zscore=True)
del data
return sp.csr_matrix(
np.hstack([
_topo_mx,
np.zeros(
(_topo_mx.shape[0], _topo_mx.shape[0] - _topo_mx.shape[1]))
]))
def set_train(self, train_set, features_meta):
features = GraphFeatures(self._gnx, features_meta, dir_path=self._paths["features"], logger=self._logger,
is_max_connected=False) # Already taking the max sub_graph in init
features.build(include=set(train_set), should_dump=True)
add_ones = bool({"first_neighbor_histogram", "second_neighbor_histogram"}.intersection(features_meta))
self._topo_mx = features.to_matrix(add_ones=add_ones, dtype=np.float64, mtype=np.matrix, should_zscore=True)
ratio = 10 ** np.ceil(np.log10(abs(np.mean(self._topo_mx) / np.mean(self._bow_mx))))
self._topo_mx /= ratio
def split_train(self, train_p, features_meta):
train_set, val_set, self._train_idx, self._val_idx = train_test_split(self._train_set, self._base_train_idx,
test_size=1 - train_p, shuffle=True)
features_path = self._features_path()
features = GraphFeatures(self._gnx, features_meta, dir_path=features_path,
logger=self._logger, is_max_connected=self._is_max_connected)
features.build(include=set(train_set), should_dump=False)
add_ones = bool({"first_neighbor_histogram", "second_neighbor_histogram"}.intersection(features_meta))
self._topo_mx = features.to_matrix(add_ones=add_ones, dtype=np.float64, mtype=np.matrix, should_zscore=True)
ratio = 10 ** np.ceil(np.log10(abs(np.mean(self._topo_mx) / np.mean(self._bow_mx))))
self._topo_mx /= ratio
def _prepare_data(self):
self._split_data()
self._inputs = self._targets = None
for path in self._get_gnx_paths():
feat_path = os.path.join(path, "features_0")
gnx = pickle.load(open(os.path.join(feat_path, "gnx.pkl"), "rb"))
gnx = gnx.subgraph(self._nodes_order)
features = GraphFeatures(gnx,
self._features_meta,
dir_path=feat_path,
logger=self._logger)
features.build(include=self._train_set)
add_ones = bool(
set(self._features_meta).intersection(
["first_neighbor_histogram", "second_neighbor_histogram"]))
cur_data = features.to_matrix(add_ones=add_ones,
dtype=np.float32,
mtype=np.array,
should_zscore=True)
self._inputs = cur_data if self._inputs is None else np.dstack(
(self._inputs, cur_data))
pickle.dump(cur_data,
open(os.path.join(feat_path, "data.pkl"), "wb"))
cur_labels = self._encode_onehot_gnx(gnx, self._nodes_order)
self._targets = cur_labels if self._targets is None else np.dstack(
(self._targets, cur_labels))
pickle.dump(cur_labels,
open(os.path.join(feat_path, "labels.pkl"), "wb"))
# Arranging data as <batch, seq, feature>
if self._gnx_idx is None:
self._inputs = self._inputs.transpose((0, 2, 1))
self._targets = self._targets.transpose((0, 2, 1))
self._logger.debug("Finished preparing the data")