def load_dataset(f):
"""
Loads a given dataset (.gsp file)
:param f: dataset path
:return: list of graphs
"""
return load_graphs(f)
def main(filename='gd10.txt', min_sup=8):
filename = os.path.join(filepath, filename)
graphs = load_graphs(filename)
C = list()
with open("Malware_sub_Goodware.txt", "r") as ins:
content = ins.read().splitlines()
temp = list()
for line in content:
if line != 'Pattern':
line = re.sub(r'[\(\)]', '', line)
u, v, L_u, L_v, L_uv = line.split(", ")
u, v, L_u, L_v, L_uv = int(u), int(v), L_u.strip(
"'"), L_v.strip("'"), L_uv.strip("'")
#print("u= {} v= {} L_u= {} L_v= {} L_uv= {}\n".format(u,v,L_u,L_v,L_uv))
temp.append((u, v, L_u, L_v, L_uv))
elif line == 'Pattern':
C.append(temp)
temp = []
# for num, li in enumerate(C):
# for t in li:
# print("Element {}: {}\n".format(num,t[2]))
for g, graph in enumerate(graphs):
for p, li in enumerate(C):
E = subgraph_isomorphisms(li, graph)
if len(E) == 0:
print("Graph: {} , Pattern: {} Not Matched".format(
g + 1, p + 1))
else:
print("Graph: {} , Pattern: {} Matched".format(g + 1, p + 1))
def main(filename='data/exampleG.txt', min_sup=2):
filename = os.path.join(filepath, filename)
graphs = load_graphs(filename)
n = len(graphs)
extensions = []
gSpan([], graphs, min_sup=min_sup, extensions=extensions)
for i, ext in enumerate(extensions):
print('Pattern %d' % (i + 1))
for _c in ext:
print(_c)
print('')
def main(filename=fname, min_sup=msup):
start_time = time.time()
filename = os.path.join(filepath, filename)
graphs, maxW = load_graphs(filename, rough_min, span, db_size, bin_count)
for wdt in WDT:
print("*************")
print(wdt)
n = len(graphs)
extensions = []
canCount = 0
gCount = 0
fwsCount = 0
oc = range(len(graphs))
fwsCount, canCount, gCount = gSpan([],
graphs,
min_sup=min_sup,
extensions=extensions,
maxW=maxW,
fwsCount=fwsCount,
canCount=canCount,
gCount=gCount,
oc=oc)
end_time = time.time()
obj = open("output.txt", "w+")
for i, ext in enumerate(extensions):
obj.write('Pattern %d\n' % (i + 1))
for _c in ext:
obj.write(str(_c))
obj.write('\n')
obj.write('')
obj.write("--- %s seconds ---\n" % (end_time - start_time))
obj.write(str(fwsCount))
obj.write('\n')
obj.write(str(canCount))
obj.write('\n')
obj.write(str(gCount))
obj.write('\n')
obj.close()
def gspan(train_test_split, path_to_graph_dataset, min_sup):
graphs=[]
graph = load_graphs(path_to_graph_dataset)
n = len(graph)
idxs = np.arange(0,n,1)
random.shuffle(idxs)
#graphs = graph[idxs.tolist()]
# print idxs
for e in idxs:
graphs.append(graph[e])
#print e
#print graphs
with open("/home/N1801734D/grid/graph_2D_CNN/datasets/classes/test/test_classes.txt", 'r') as f:
y = f.read().splitlines()
y = [int(elt) for elt in y]
for e in y:
ys = y[e]
# print("number of graphs: ", n)
np.save("shuffled_graph_idxs", idxs)
train_graphs = graphs[:(int)(train_test_split*n)]
test_graphs = graphs[(int)(train_test_split*n):]
#print("number of graphs for train: ", len(train_graphs), " for test: ", len(test_graphs))
extensions = []
gSpan([], train_graphs, min_sup=30, extensions=extensions)
#with open("out.txt","w") as f:
for i, ext in enumerate(extensions):
#print('Pattern %d' % (i+1))
for _c in ext:
print(_c)
#f.write(_c)
print('')
#f.write('')
#print("Compute subgraphs list in train graphs: ")
support, train_graphs_list = get_graphs_for_each_subgraph(extensions=extensions, graphs=train_graphs)
train_subgraphs_list = get_subgraphs_for_each_graph(graphs=train_graphs, graphs_list=train_graphs_list)
for i in range(len(train_graphs)):
np.save("id/train_np/g_" + str(i), np.array(train_subgraphs_list[i]))
with open("id/train/g_" + str(i) + ".txt","w") as f:
f.writelines(["%s " % item for item in train_subgraphs_list[i]])
#print(train_subgraphs_list[i])
#print("Compute subgraphs list in test graphs: ")
_, test_graphs_list = get_graphs_for_each_subgraph(extensions=extensions, graphs=test_graphs)
test_subgraphs_list = get_subgraphs_for_each_graph(graphs=test_graphs, graphs_list=test_graphs_list)
for i in range(len(test_graphs)):
np.save("id/test_np/g_" + str(i), np.array(test_subgraphs_list[i]))
with open("id/test/g_" + str(i) + ".txt","w") as fo:
fo.writelines(["%s " % item for item in test_subgraphs_list[i]])
#print(test_subgraphs_list[i])
np.save("extensions", extensions)
np.save("support", support)
def main(filename='data/Compound_422.txt', min_sup=300):
filename = os.path.join(filepath, filename)
graphs1 = load_graphs(filename)
extensions = []
print("original frequent pattern:")
gSpan([], graphs1, min_sup=min_sup, extensions=extensions)
for i, ext in enumerate(extensions):
print('Pattern %d' % (i + 1))
for _c in ext:
print(_c)
print('')
print("--- %s seconds ---" % (time.time() - start_time))
extensions1 = extensions
print("original frequent pattern list:")
print(extensions1)
n = len(graphs1)
print("total number of graph:")
print(n)
x = int(input('what percentage want to take:'))
p = round((x / 100) * n)
print("graph size now is :")
print(p)
graphs = random.sample(graphs1, p)
#print(graphs)
#b=len(graphs)
#print(b)
extensions = []
print("percentwise frequent pattern:")
gSpan([], graphs, min_sup=175, extensions=extensions)
for i, ext in enumerate(extensions):
print('Pattern %d' % (i + 1))
for _c in ext:
print(_c)
print('')
print("percentwise frequent pattern list:")
print(extensions)
l2 = len(extensions)
'''results = confusion_matrix(extensions1, extensions)
print ('Confusion Matrix :')
print(results)
print ('Accuracy Score :',accuracy_score(extensions1, extensions) )
print ('Report : ')
print (classification_report(extensions1, extensions))'''
tp1 = []
fp1 = []
for list in extensions:
if list in extensions1:
tp1.append(list)
#print("differences")
#print(differences)
tp = len(tp1)
#print("tp :",tp)
l1 = len(extensions1)
#print("length of frqnt pattern:")
#print(l1)
for list in extensions:
if list not in extensions1:
fp1.append(list)
fp = len(fp1)
# print("fp :" ,fp)
fn = l1 - tp
#print("fn :", fn)
accuracy = (tp / l1) * 100
print("accuracy:", accuracy)
prcn = tp / (fp + tp)
print("precission", prcn)
recall = tp / (tp + fn)
print("recall", recall)
jc = (tp / (l1 + l2)) * 100
print("jaccard coefficient", jc)
f1score = 2 * ((prcn * recall) / (prcn + recall))
print("F1Score:", f1score)
def main(min_sup):
allGraph2Dic = generateInput()
#filename = os.path.join(filepath, filename)
gspanInput = []
for graph2Dic in allGraph2Dic:
gspanInput.append(list(numberingIndex(graph2Dic)))
graphs = load_graphs(gspanInput)
n = len(graphs)
extensions = []
extensions_sups = list()
graphIndex = list()
gSpan([], graphs, min_sup, extensions, extensions_sups)
_report_df = pd.DataFrame()
'''
_report_df = _report_df.append(
pd.DataFrame(
{
'support': [_support],
'vertex': [nodeInfo],
'link' : [linkInfo],
'num_vert': [_num_vertices]
},
index=[i]
)
)
'''
for i, ext in enumerate(extensions):
#print('Pattern %d' % (i+1))
#print('Support : %d' %extensions_sups[i])
nodelist = list()
edgelist = list()
graphIndex.append(i)
for _c in ext:
#print(_c)
nodes = []
nodes.append(_c[0])
nodes.append(_c[2])
nodelist.append(nodes)
nodes = []
nodes.append(_c[1])
nodes.append(_c[3])
nodelist.append(nodes)
edges = []
edges.append(_c[2])
edges.append(_c[3])
edges.append(_c[4])
edgelist.append(edges)
nodelist = list(set(map(tuple, nodelist)))
nodecnt = len(nodelist)
_report_df = _report_df.append(
pd.DataFrame(
{
'support': [extensions_sups[i]],
'vertex': [nodelist],
'link': [edgelist],
'num_vert': [nodecnt]
},
index=[i]))
#print('')
#print("_report_df : print")
#print(_report_df)
return _report_df
