def get_pattern_infos(pattern_paths):
patterns = []
OBDPatterns = []
root_nodes_patterns = []
indices = []
equiv = []
non_equiv = []
for pattern_path in pattern_paths:
print pattern_path
pattern = nx.read_gml(os.path.join(pattern_path, 'pattern.gml'))
patterns.append(pattern)
with open(os.path.join(pattern_path, 'startNodeId.info')) as f:
start_node = int(f.readline().rstrip())
OBD = OBDsearch.get_heuristic4_OBD(pattern, startNode=start_node)
OBDPatterns.append(OBD)
with open(os.path.join(pattern_path, 'rootNode.info')) as f:
root_node = f.readline().rstrip()
root_nodes_patterns.append(root_node)
ind = []
with open(os.path.join(pattern_path, 'indices.info')) as f:
for line in f:
ind.append(int(line.rstrip()))
indices.append(ind)
if not os.path.isfile(os.path.join(pattern_path, 'equivalence.info')):
equiv.append(None)
else:
indices_equiv = []
with open(os.path.join(pattern_path, 'equivalence.info')) as f:
for line in f:
a = []
l = line.rstrip().split(" ")
for elem in l:
a.append(int(elem))
indices_equiv.append(a)
equiv.append(indices_equiv)
if not os.path.isfile(
os.path.join(pattern_path, 'non_equivalence.info')):
non_equiv.append(None)
else:
indices_equiv = []
with open(os.path.join(pattern_path, 'non_equivalence.info')) as f:
for line in f:
a = []
l = line.rstrip().split(" ")
for elem in l:
a.append(int(elem))
indices_equiv.append(a)
non_equiv.append(indices_equiv)
return patterns, OBDPatterns, root_nodes_patterns, indices, equiv, non_equiv
if __name__ == '__main__':
#dict_path='/home/irma/work/DATA/DATA/yeast/exhaustive_approach/fdict_exhaustive_pattern4.pickle'
#pkl_file = open(dict_path, 'rb')
#count_combinations_arity_2(pickle.load(pkl_file),0,2)
#data_graph = '/home/irma/work/DATA/DATA/yeast/YEAST_equiv.gpickle'
#data_graph = nx.read_gpickle(data_graph)
data_graph = '/home/irma/work/DATA/DATA/yeast/dummy_yeast.gml'
data_graph = nx.read_gml(data_graph)
#Target
target_attr = 'function'
target_constant = 'constant'
root_node_target = 'function'
target = gtp.get_target_graph(target_constant, target_attr)
OBD1 = OBDsearch.get_heuristic4_OBD(target, startNode=2)
print OBD1
OBDTarget = [[2], [1]]
print OBDTarget
# pattern=nx.read_gml('/home/irma/work/DATA/DATA/yeast/pattern4.gml')
# #ground_pattern = gtp.ground_pattern(tg, pattern)
# OBD1 = OBDsearch.get_heuristic4_OBD(pattern, startNode = 6)
# patterns=[pattern]
# OBDPatterns=[OBD1]
# root_nodes_patterns=['function']
# indices=[[1,6]]
# csvfile = '/home/irma/work/DATA/DATA/yeast/testFurer.csv'
# fieldnames = ['dummy','target', 'patt2']
# generate_csv_furerOBD_count(data_graph, target, OBDTarget, root_node_target, patterns,OBDPatterns,indices, root_nodes_patterns, csvfile, fieldnames)
for pattern,OBD,root_node in zip(patterns,OBDPatterns,root_nodes_patterns):
ground_pattern = gtp.ground_pattern(target, pattern)
nr_pat=exact_counting(ground_pattern, data_graph, OBD, root_node)
dict_res[fieldnames[fieldcounter]]=nr_pat
fieldcounter=fieldcounter+1
writer.writerow(dict_res)
if __name__ == '__main__':
data_graph = '/home/irma/work/DATA/DATA/YEAST_equiv.gpickle'
data_graph = nx.read_gpickle(data_graph)
tg=gtp.find_all_groundings_of_predicates(data_graph, 'function','constant')[0]
pattern=nx.read_gml('/home/irma/work/DATA/DATA/yeast/pattern2.gml')
ground_pattern = gtp.ground_pattern(tg, pattern)
OBD1 = OBDsearch.get_heuristic4_OBD(pattern, startNode = 0)
target_attr='function'
target_constant='constant'
root_node_target='function'
OBDTarget=[[1],[2]]
patterns=[pattern]
OBDPatterns=[OBD1]
root_nodes_patterns=['protein_class']
csvfile='/home/irma/work/DATA/DATA/yeast/test.csv'
fieldnames=['target','patt2']
print "Pattern OBD:",OBD1
#generate_csv_furerOBD_counts(data_graph, target_attr, target_constant, OBDTarget, root_node_target, patterns,OBDPatterns, root_nodes_patterns, csvfile, fieldnames)
generate_csv_exact_counts(data_graph, target_attr, target_constant, OBDTarget, root_node_target, patterns,
OBDPatterns, root_nodes_patterns, csvfile, fieldnames)
#print exact_counting(tg, data_graph,OBD,'function')
output_train_csv = os.path.join(args.o, experiment, 'train.csv')
output_test_csv = os.path.join(args.o, experiment, 'test.csv')
time_dict_train_csv = os.path.join(args.o, experiment,
'time_dict_train.csv')
time_dict_test_csv = os.path.join(args.o, experiment, 'time_dict_test.csv')
pattern_path = args.p
patterns, OBDPatterns, root_nodes_patterns, indices, pattern_equivalence, non_equivalence = get_pattern_infos(
pattern_path)
target = gtp.get_target_graph(args.const, args.attr)
for i in target:
print i, target.node[i]
print "Equal: ", pattern_equivalence
print "Not equal: ", non_equivalence
OBDTarget = OBDsearch.get_heuristic4_OBD(target, startNode=int(args.sT))
root_node_target = args.rT
fieldnames = ['dummy', 'target', patterns[0].name]
if args.e == "exact":
print "HERE"
if args.t == None or (args.t != None and args.t == "train"):
exact.generate_csv_exact_counts(
train_data, target, args.const, args.attr, OBDTarget,
root_node_target, patterns, OBDPatterns, indices,
root_nodes_patterns, pattern_equivalence, non_equivalence,
output_train_csv, fieldnames, time_dict_train_csv,
args.max_time)
print "Training data counted ..."
if args.t == None or (args.t != None and args.t == "test"):