-
Notifications
You must be signed in to change notification settings - Fork 4
/
Split_Dataset.py
38 lines (29 loc) · 1.47 KB
/
Split_Dataset.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
import os
import shutil
import random
import pandas as pd
from tqdm import tqdm
random.seed(0)
df = pd.read_csv(os.path.join('Dataset', 'Reference.csv'))
if os.path.isdir('Split Dataset'):
shutil.rmtree('Split Dataset')
os.mkdir('Split Dataset')
os.mkdir(os.path.join('Split Dataset', 'Train'))
os.mkdir(os.path.join('Split Dataset', 'Validation'))
for Class in df['Class']:
os.mkdir(os.path.join('Split Dataset', 'Train', str(Class)))
os.mkdir(os.path.join('Split Dataset', 'Validation', str(Class)))
for Class in tqdm(df.iloc[:,0], unit_scale = True, miniters = 1, desc = 'Splitting Dataset '):
Files = os.listdir(os.path.join('Dataset', str(Class)))
random.shuffle(Files)
if len(Files) == 2000:
for File in Files[:200]:
shutil.copy(os.path.join('Dataset', str(Class), File), os.path.join('Split Dataset', 'Validation', str(Class), File))
for File in Files[200:]:
shutil.copy(os.path.join('Dataset', str(Class), File), os.path.join('Split Dataset', 'Train', str(Class), File))
elif len(Files) == 1250:
for File in Files[:125]:
shutil.copy(os.path.join('Dataset', str(Class), File), os.path.join('Split Dataset', 'Validation', str(Class), File))
for File in Files[125:]:
shutil.copy(os.path.join('Dataset', str(Class), File), os.path.join('Split Dataset', 'Train', str(Class), File))
shutil.copy(os.path.join('Dataset', 'Reference.csv'), os.path.join('Split Dataset', 'Reference.csv'))