Mercurial > ift6266

comparison scripts/nist_divide.py @ 60:d508f5a8acd0

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Script pour creer ensembles train, valid et test NIST pur
author boulanni <nicolas_boulanger@hotmail.com>
date Mon, 08 Feb 2010 14:55:22 -0500
parents
children 2b6a28e4cadc
comparison
equal deleted inserted replaced
59:8b9fca879543 60:d508f5a8acd0
1 #!/usr/bin/env python
2
3 '''
4 creation des ensembles train, valid et test NIST pur
5 ensemble test est pris tel quel
6 ensemble valid est trainorig[:20000]
7 ensemble train est trainorig[20000:]
8 trainorig est deja shuffled
9 '''
10
11 from pylearn.io import filetensor as ft
12 import numpy, os
13
14 dir1 = "/data/lisa/data/nist/by_class/all/"
15 dir2 = "/data/lisa/data/ift6266h10/"
16
17 os.system("cp %s %s" % (dir1 + "all_test_data.ft", dir2 + "test_data.ft"))
18 os.system("cp %s %s" % (dir1 + "all_test_labels.ft", dir2 + "test_labels.ft"))
19
20 f = open(dir1 + "/all_train_data.ft")
21 d = ft.read(f)
22 f = open(dir2 + "valid_data.ft", 'wb')
23 ft.write(f, d[:20000])
24 f = open(dir2 + "train_data.ft", 'wb')
25 ft.write(f, d[20000:])
26
27 f = open(dir1 + "/all_train_labels.ft")
28 d = ft.read(f)
29 f = open(dir2 + "valid_labels.ft", 'wb')
30 ft.write(f, d[:20000])
31 f = open(dir2 + "train_labels.ft", 'wb')
32 ft.write(f, d[20000:])
33
34 for i in ["train", "valid", "test"]:
35 os.chmod(dir2 + i + "_data.ft", 0744)
36 os.chmod(dir2 + i + "_labels.ft", 0744)
37
38
39