|
a |
|
b/ipynb/split into folders.ipynb |
|
|
1 |
{ |
|
|
2 |
"cells": [ |
|
|
3 |
{ |
|
|
4 |
"cell_type": "code", |
|
|
5 |
"execution_count": 4, |
|
|
6 |
"metadata": {}, |
|
|
7 |
"outputs": [], |
|
|
8 |
"source": [ |
|
|
9 |
"import os\n", |
|
|
10 |
"import shutil\n", |
|
|
11 |
"src = \"/home/serge/database/data/genomes/bacillus/ncbi-genomes-2019-06-25/train/\"\n", |
|
|
12 |
"t = \"/home/serge/database/data/genomes/bacillus/ncbi-genomes-2019-06-25\"\n", |
|
|
13 |
"\n", |
|
|
14 |
"src_files = os.listdir(src)" |
|
|
15 |
] |
|
|
16 |
}, |
|
|
17 |
{ |
|
|
18 |
"cell_type": "code", |
|
|
19 |
"execution_count": 5, |
|
|
20 |
"metadata": {}, |
|
|
21 |
"outputs": [ |
|
|
22 |
{ |
|
|
23 |
"data": { |
|
|
24 |
"text/plain": [ |
|
|
25 |
"3966" |
|
|
26 |
] |
|
|
27 |
}, |
|
|
28 |
"execution_count": 5, |
|
|
29 |
"metadata": {}, |
|
|
30 |
"output_type": "execute_result" |
|
|
31 |
} |
|
|
32 |
], |
|
|
33 |
"source": [ |
|
|
34 |
"len(src_files)\n" |
|
|
35 |
] |
|
|
36 |
}, |
|
|
37 |
{ |
|
|
38 |
"cell_type": "code", |
|
|
39 |
"execution_count": 6, |
|
|
40 |
"metadata": {}, |
|
|
41 |
"outputs": [], |
|
|
42 |
"source": [ |
|
|
43 |
"num=500\n", |
|
|
44 |
"\n", |
|
|
45 |
"for i, file_name in enumerate(src_files):\n", |
|
|
46 |
" if i % num == 0:\n", |
|
|
47 |
" dest = f\"{t}/{i}/\"\n", |
|
|
48 |
" if not os.path.exists(dest):\n", |
|
|
49 |
" os.mkdir(dest)\n", |
|
|
50 |
" full_file_name = os.path.join(src, file_name)\n", |
|
|
51 |
" if os.path.isfile(full_file_name):\n", |
|
|
52 |
" shutil.copy(full_file_name, dest)" |
|
|
53 |
] |
|
|
54 |
}, |
|
|
55 |
{ |
|
|
56 |
"cell_type": "code", |
|
|
57 |
"execution_count": 14, |
|
|
58 |
"metadata": {}, |
|
|
59 |
"outputs": [], |
|
|
60 |
"source": [ |
|
|
61 |
"from sklearn.model_selection import train_test_split\n", |
|
|
62 |
"train, test = train_test_split(src_files,test_size=0.2, random_state=42)\n", |
|
|
63 |
"portions = {\"train\":train, \"valid\":test}\n", |
|
|
64 |
"\n", |
|
|
65 |
"for part in portions.keys():\n", |
|
|
66 |
" for file_name in portions[part]:\n", |
|
|
67 |
" dest = f\"{t}/{part}\"\n", |
|
|
68 |
" if not os.path.exists(dest):\n", |
|
|
69 |
" os.mkdir(dest)\n", |
|
|
70 |
" full_file_name = os.path.join(src, file_name)\n", |
|
|
71 |
" if os.path.isfile(full_file_name):\n", |
|
|
72 |
" shutil.copy(full_file_name, dest)" |
|
|
73 |
] |
|
|
74 |
}, |
|
|
75 |
{ |
|
|
76 |
"cell_type": "code", |
|
|
77 |
"execution_count": null, |
|
|
78 |
"metadata": {}, |
|
|
79 |
"outputs": [], |
|
|
80 |
"source": [] |
|
|
81 |
} |
|
|
82 |
], |
|
|
83 |
"metadata": { |
|
|
84 |
"kernelspec": { |
|
|
85 |
"display_name": "Python [conda env:bio] *", |
|
|
86 |
"language": "python", |
|
|
87 |
"name": "conda-env-bio-py" |
|
|
88 |
}, |
|
|
89 |
"language_info": { |
|
|
90 |
"codemirror_mode": { |
|
|
91 |
"name": "ipython", |
|
|
92 |
"version": 3 |
|
|
93 |
}, |
|
|
94 |
"file_extension": ".py", |
|
|
95 |
"mimetype": "text/x-python", |
|
|
96 |
"name": "python", |
|
|
97 |
"nbconvert_exporter": "python", |
|
|
98 |
"pygments_lexer": "ipython3", |
|
|
99 |
"version": "3.6.8" |
|
|
100 |
} |
|
|
101 |
}, |
|
|
102 |
"nbformat": 4, |
|
|
103 |
"nbformat_minor": 2 |
|
|
104 |
} |