-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdata_splitter_test.py
54 lines (32 loc) · 1.84 KB
/
data_splitter_test.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
import os
from utils.data_splitter import DataSplitter
def run_with_cora_epgm():
input_dir = os.path.expanduser('../tests/resources/data/cora/cora.epgm')
output_dir = os.path.expanduser('../tests/resources/data_splitter/cora.epgm.out')
ds = DataSplitter()
y = ds.load_data(input_dir, dataset_name='cora', target_attribute='subject', node_type='paper')
y_train, y_val, y_test = ds.split_data(y, nc=20, test_size=100)
ds.write_data(output_dir=output_dir, dataset_name='cora', y_train=y_train, y_test=y_test, y_val=y_val)
print("Done")
def run_with_yelp_epgm():
input_dir = os.path.expanduser('../tests/resources/data/yelp/yelp.epgm')
output_dir = os.path.expanduser('../tests/resources/data_splitter/yelp.epgm.out')
dataset_name = 'small_yelp_example'
ds = DataSplitter()
y = ds.load_data(input_dir, dataset_name=dataset_name, target_attribute='elite', node_type='user')
y_train, y_val, y_test, y_unlabeled = ds.split_data(y, nc=20, test_size=100)
ds.write_data(output_dir=output_dir, dataset_name=dataset_name,
y_train=y_train, y_test=y_test, y_val=y_val, y_unlabeled=y_unlabeled)
print("Done")
def run_with_yelp_lab():
input_dir = os.path.expanduser('../tests/resources/data_splitter/yelp.epgm.out/small_yelp_example.lab')
output_dir = os.path.expanduser('../tests/resources/data_splitter/yelp.epgm.out')
dataset_name = 'small_yelp_example'
ds = DataSplitter()
y = ds.load_data(input_dir, dataset_name=dataset_name, target_attribute='elite', node_type='user')
y_train, y_val, y_test, y_unlabeled = ds.split_data(y, nc=20, test_size=100)
ds.write_data(output_dir=output_dir, dataset_name=dataset_name,
y_train=y_train, y_test=y_test, y_val=y_val, y_unlabeled=y_unlabeled)
print("Done")
if __name__ == '__main__':
run_with_yelp_lab()