transfix-mt/scripts/lemmatize_in.py

import nltk
import os

from nltk.stem import WordNetLemmatizer


wl = WordNetLemmatizer()

train_in_path = os.path.join(os.path.expanduser('~'), 'mt-summit-corpora/train/in.tsv')
train_expected_path = os.path.join(os.path.expanduser('~'), 'mt-summit-corpora/train/expected.tsv')

file_lemmatized = []
with open(train_in_path, 'r') as file:
    for line in file:
        if len(file_lemmatized) % 50000 == 0:
            print('lemmatizing file: ' + train_in_path + ': ' + str(len(file_lemmatized)), end='\r')
        line = nltk.word_tokenize(line)
        file_lemmatized.append(' '.join([wl.lemmatize(x) for x in line]))
print('\n')

with open(train_in_path + '.lemmatized', 'w') as file_write:
    for line in file_lemmatized:
        file_write.write(line + '\n')