-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathDataset.py
250 lines (168 loc) · 5.02 KB
/
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
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
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
# -*- coding: utf-8 -*-
"""dataset.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1OcAekMnpIoscR9di-X3zx9M5MO4taxde
"""
from google.colab import drive
drive.mount('/content/drive')
!pip install zipfile36
!pip install pydicom
pip install opencv-python
cd /content/drive/MyDrive
import numpy as np
import pandas as pd
import os
import random
import shutil
import pydicom
import cv2
import csv
import zipfile
import glob
archive = zipfile.ZipFile('data.zip') #Extract Kaggle Dataset
for file in archive.namelist():
archive.extract(file, '.')
inputdir = '/content/drive/MyDrive/data/data_set/'
outdir = '/content/drive/MyDrive/output_images/'
#os.mkdir(outdir)
#os.mkdir(outdir)
test_list = [os.path.basename(x) for x in glob.glob(inputdir + './*.dcm')]
print(test_list)
for f in test_list:
ds = pydicom.read_file(inputdir + f) # read dicom imageS
img = ds.pixel_array # get image array
cv2.imwrite(outdir + f.replace('.dcm','.png'),img) # write png image"""
print(len(test_list))
outdir = '/content/drive/MyDrive/output_images/'
out_list = [os.path.basename(x) for x in glob.glob(outdir + './*.png')]
print(out_list)
print(len(out_list))
pwd
import shutil, os
import pandas as pd
labels = pd.read_csv("All.csv")
labels = labels.sort_values('Class')
class_names = list(labels.Class.unique())
#print(class_names)
images = '/output_images'
train_new = '/dataset'
#creating subfolders
for i in class_names:
os.makedirs(os.path.join('dataset', i))
#moving the image files to their respective categories
for c in class_names: # Category Name
for i in list(labels[labels['Class']==c]['filename']): # Image Id
get_image = os.path.join('output_images', i) # Path to Images
move_image = shutil.move(get_image, 'dataset/'+c)
normaldir = 'dataset/normal/'
normal_list = [os.path.basename(x) for x in glob.glob(normaldir + './*.png')]
print(len(normal_list))
pneumoniadir = 'dataset/pneumonia/'
pneumonia_list = [os.path.basename(x) for x in glob.glob(pneumoniadir + './*.png')]
print(pneumonia_list)
print(len(pneumonia_list))
for i in normal_list:
#print(i) # Image Id
get_image = os.path.join('dataset','normal', i) # Path to Images
#print(get_image)
move_image = shutil.move(get_image, 'output_images/')
print(len(normal_list))
outdir = '/content/drive/MyDrive/output_images/'
out_list = [os.path.basename(x) for x in glob.glob(outdir + './*.png')]
#print(out_list)
print(len(out_list))
import shutil, os
import pandas as pd
labels = pd.read_csv("All.csv")
labels = labels.sort_values('Class')
class_names = list(labels.Class.unique())
print(class_names)
images = '/output_images'
train_new = '/data'
#creating subfolders
for i in class_names:
os.makedirs(os.path.join('data', i))
pwd
ls
cd data/
ls
cd ..
#moving the image files to their respective categories
for c in class_names: # Category Name
for i in list(labels[labels['Class']==c]['filename']): # Image Id
get_image = os.path.join('output_images', i) # Path to Images
move_image = shutil.move(get_image, 'data/'+c)
outdir = '/content/drive/MyDrive/output_images/'
out_list = [os.path.basename(x) for x in glob.glob(outdir + './*.png')]
#print(out_list)
print(len(out_list))
cd /data
cd data/
ls
cd normal/
ls
cd ..
cd pneumonia/
ls
cd ..
cd ..
normaldir = 'data/normal/'
normal_list = [os.path.basename(x) for x in glob.glob(normaldir + './*.png')]
print(len(normal_list))
#print(normal_list)
pneumoniadir = 'data/pneumonia/'
pneumonia_list = [os.path.basename(x) for x in glob.glob(pneumoniadir + './*.png')]
print(len(pneumonia_list))
#print(pneumonia_list)
cd data/pneumonia
ls
cd ..
cd ..
pwd
ls
outdir = 'output_images/'
out_list = [os.path.basename(x) for x in glob.glob(outdir + './*.png')]
print(out_list)
print(len(out_list))
ls
rm -rf output_images/
ls
pwd
pwd
cd /content/drive/MyDrive/
from google.colab import drive
drive.mount('/content/drive')
import zipfile
archive = zipfile.ZipFile('dataset.zip') #Extract Kaggle Dataset
for file in archive.namelist():
archive.extract(file, '.')
pwd
cd /content/drive/MyDrive/dataset/output/test/normal/
ls
cd ..
cd /content/drive/MyDrive/dataset/output/test/pneumonia/
ls
cd /content/drive/MyDrive/dataset/output/train/normal/
ls
cd /content/drive/MyDrive/dataset/output/train/pneumonia/
ls
ls
ls
pwd
outdir = '/content/drive/MyDrive/dataset/output/train/pneumonia/'
out_list = [os.path.basename(x) for x in glob.glob(outdir + './*.png')]
#print(out_list)
print(len(out_list))
outdir = '/content/drive/MyDrive/dataset/output/train/normal/'
out_list = [os.path.basename(x) for x in glob.glob(outdir + './*.png')]
#print(out_list)
print(len(out_list))
outdir = '/content/drive/MyDrive/dataset/output/test/pneumonia/'
out_list = [os.path.basename(x) for x in glob.glob(outdir + './*.png')]
#print(out_list)
print(len(out_list))
outdir = '/content/drive/MyDrive/dataset/output/test/normal/'
out_list = [os.path.basename(x) for x in glob.glob(outdir + './*.png')]
#print(out_list)
print(len(out_list))