Shuffle a parallel corpus without loosing the alignment.

corpusShuffler.py

# To run: python corpusShuffler -src sourceCourpus.txt -tdt targetCorpus.txt

import argparse
import random

parser = argparse.ArgumentParser(description='## CORPUS SHUFLER ##')
parser.add_argument(
    '-src', help='sorce language corpus to shuffle', required=True)
parser.add_argument(
    '-tgt', help='target language corpus to shuffle', required=True)
args = parser.parse_args()

src = open(args.src, 'r')
tgt = open(args.tgt, 'r')

srcOut = open(args.src + '_shuffled', 'w')
tgtOut = open(args.tgt + '_shuffled', 'w')

srcData = src.readlines()
tgtData = tgt.readlines()

random.seed(7)  # same seed for both files (to save the alignment)
random.shuffle(srcData)
random.seed(7)  # same seed for both files (to save the alignment)
random.shuffle(tgtData)

open(args.src + '_shuffled', 'w').writelines(srcData)
open(args.tgt + '_shuffled', 'w').writelines(tgtData)