TAU2019-028/train/split.py

22 lines
416 B
Python

import pandas as pd
europarl = pd.read_csv('news-commentary-v12-clean.tsv', sep='\t', names=['cs', 'en'], header=None)
cs = europarl['cs']
en = europarl['en']
file1 = open("./after_split/news-commentary-v12-clean.cs","w")
for row in cs:
file1.write(str(row) + "\n")
file1.close()
file2 = open("./after_split/news-commentary-v12-clean.en","w")
for row in en:
file2.write(str(row) + "\n")
file2.close()