-
Notifications
You must be signed in to change notification settings - Fork 0
/
CreateDataset.py
183 lines (154 loc) · 6.38 KB
/
CreateDataset.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
# -*- coding: utf-8 -*-
"""
Created on Tue Jun 15 12:55:25 2021
@author: prctha
"""
from step2graph import StepToGraph
import os
from tqdm import tqdm
def create_dataset(dataset_folder,output_file, filter_list = None):
import pickle
print(' Dataset folder(s):\n', dataset_folder)
if not isinstance(dataset_folder, list):
pk_path = os.path.join(dataset_folder,output_file)
dataset = {}
i = 0
total = 0
for root, subdirs, files in os.walk(dataset_folder):
for file in files:
filename, file_extension = os.path.splitext(file)
if file_extension in [".stp",".step",".STEP",".STP"]:
total += 1
print("Total step files:", total)
start_point = 0
good_count = 0
pbar = tqdm(total=total)
problem_files = []
for root, subdirs, files in os.walk(dataset_folder):
path = root.split(os.sep)
for file in files:
filename, file_extension = os.path.splitext(file)
if file_extension in [".stp",".step",".STEP",".STP"]:
i += 1
pbar.update(1)
if filter_list != None:
if filename not in filter_list:
print("Not in filter_list: ",filename)
continue
#print(path[-2],file)
filepath = os.path.join(root,file)
try:
if i < start_point:
continue
print(filename)
if filename in ['00000360_9ee540a56d79451e8026e1e6_step_002', '0004376_0161a8b664ac4b21aaf2f0c4_step_000']:
raise ValueError('Dud')
try:
with open(pk_path,'rb') as f:
dataset = pickle.load(f)
#print(dataset.keys())
except:
print("no current pickle file")
print("in dataset?", filename in dataset)
if filename not in dataset:
s2g = StepToGraph(filepath)
s2g.compute_faces_surface()
dataset[filename] = {"cat":path[-2],"graph_nx":s2g.G}
with open(pk_path,'wb') as handle:
pickle.dump(dataset,handle, protocol=pickle.HIGHEST_PROTOCOL)
good_count += 1
#print(i, "/",total)
except Exception as inst:
print(inst)
problem_files.append(filepath)
textfile = open(os.path.join(dataset_folder,"problems.txt"), "w")
for element in problem_files:
textfile.write(element + "\n")
textfile.close()
print("problem with:", filepath)
pbar.close()
print(dataset)
print("problem files",problem_files)
print("good count",good_count)
# save problems
textfile = open(os.path.join(dataset_folder,"problems.txt"), "w")
for element in problem_files:
textfile.write(element + "\n")
textfile.close()
else:
# file list
model_list = dataset_folder
pbar = tqdm(total=len(model_list))
pk_path = output_file
dataset = {}
for filepath in model_list:
print()
print(filepath)
file_path_name, file_extension = os.path.splitext(filepath)
print(file_path_name)
_, filename = os.path.split(file_path_name)
print(filename)
try:
with open(pk_path,'rb') as f:
dataset = pickle.load(f)
#print(dataset.keys())
except:
print("no current pickle file")
print()
print("in dataset?", filename in dataset)
print()
if filename not in dataset:
s2g = StepToGraph(filepath)
s2g.compute_faces_surface()
dataset[filename] = {"cat":"None","graph_nx":s2g.G}
''' HR 01/06/22 Workaround to avoid FileNotFoundError '''
print('pk_path:',pk_path)
folder,file = os.path.split(pk_path)
if not os.path.isdir(folder):
print(' Making folder', folder)
os.makedirs(folder)
with open(pk_path,'wb') as handle:
pickle.dump(dataset,handle, protocol=pickle.HIGHEST_PROTOCOL)
pbar.update(1)
pbar.close()
problem_files = []
good_count = 0
def ex_bool(x):
if x == 'False':
return False
else:
return True
def read_triples(file):
used_list = []
useful_triples = 0
import csv
with open(file) as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
line_count = 0
for row in csv_reader:
line_count += 1
if line_count == 1:
continue
userid = row[0]
model1 = row[2]
model2 = row[3]
model3 = row[4]
sim1 = ex_bool(row[5])
sim2 = ex_bool(row[6])
sim3 = ex_bool(row[7])
if sim1 + sim2 + sim3 == 2:
useful_triples += 1
if model1 not in used_list:
used_list.append(model1)
if model2 not in used_list:
used_list.append(model2)
if model3 not in used_list:
used_list.append(model3)
print("Total models:",len(used_list))
print("Useful triples:",useful_triples)
return used_list
if __name__ == "__main__":
#dataset_folder = "C:\\Users\\prctha\\PythonDev\\ABC_Data"
#output_file = "ABC_nx.pickle"
filter_list = read_triples("exp1_triplets2.csv")
#create_dataset(dataset_folder,output_file,filter_list = filter_list)