view scripts/ocr_divide.py @ 137:728e232eaf45

Added script to separate OCR data in train, validation and test sets (raw data)
author boulanni <nicolas_boulanger@hotmail.com>
date Sat, 20 Feb 2010 02:12:57 -0500
parents
children 2b6a28e4cadc
line wrap: on
line source

#!/usr/bin/env python

'''
creation des ensembles train, valid et test OCR
ensemble valid est trainorig[:20000]
ensemble test est trainorig[20000:40000]
ensemble train est trainorig[40000:]
trainorig est deja shuffled
'''

from pylearn.io import filetensor as ft
import numpy, os

dir1 = '/data/lisa/data/ocr_breuel/filetensor/'
dir2 = "/data/lisa/data/ift6266h10/"

f = open(dir1 + 'unlv-corrected-2010-02-01-shuffled.ft')
d = ft.read(f)
f = open(dir2 + "ocr_valid_data.ft", 'wb')
ft.write(f, d[:20000])
f = open(dir2 + "ocr_test_data.ft", 'wb')
ft.write(f, d[20000:40000])
f = open(dir2 + "ocr_train_data.ft", 'wb')
ft.write(f, d[40000:])

f = open(dir1 + 'unlv-corrected-2010-02-01-labels-shuffled.ft')
d = ft.read(f)
f = open(dir2 + "ocr_valid_labels.ft", 'wb')
ft.write(f, d[:20000])
f = open(dir2 + "ocr_test_labels.ft", 'wb')
ft.write(f, d[20000:40000])
f = open(dir2 + "ocr_train_labels.ft", 'wb')
ft.write(f, d[40000:])

for i in ["train", "valid", "test"]:
    os.chmod(dir2 + "ocr_" + i + "_data.ft", 0744)
    os.chmod(dir2 + "ocr_" + i + "_labels.ft", 0744)