Last active
September 14, 2016 02:06
-
-
Save iamaaditya/fca491f1aa32ccc2e1c3e6c163126b62 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" This program takes a file, and splits it into given percentage by line number, but uses | |
randomization to select the files | |
USAGE: python randomize_split.py <file_name> <split_percentage_for_test_eg_10> | |
@author: aaditya prakash""" | |
from __future__ import division | |
import sys | |
import random | |
file = open(sys.argv[1]).read().splitlines() | |
split_percent = float(sys.argv[2]) | |
assert split_percent > 1, "give percentage as range from 1 to 100" | |
file_len = len(file) | |
file_len_range = range(file_len) | |
test_split_index = random.sample(file_len_range, int(split_percent*file_len/100)) | |
train_split_index = list(set(file_len_range) - set(test_split_index)) | |
file_train = open("train_" + sys.argv[1], 'w') | |
file_test = open("test_" + sys.argv[1], 'w') | |
file_train.write('\n'.join([file[i] for i in train_split_index])) | |
file_test.write('\n'.join([file[i] for i in test_split_index])) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment