30 lines
660 B
Python
30 lines
660 B
Python
|
from itertools import islice
|
||
|
|
import regex as re
|
||
|
|
import sys
|
||
|
|
from torchtext.vocab import build_vocab_from_iterator
|
||
|
|
import lzma
|
||
|
|
import scripts
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
def get_word_lines_from_file(file_name):
|
||
|
|
counter=0
|
||
|
|
with lzma.open(file_name, 'r') as fh:
|
||
|
|
for line in fh:
|
||
|
|
counter+=1
|
||
|
|
# if counter == 10000:
|
||
|
|
# break
|
||
|
|
line = line.decode("utf-8")
|
||
|
|
yield scripts.get_words_from_line(line)
|
||
|
|
|
||
|
|
|
||
|
|
vocab_size = scripts.vocab_size
|
||
|
|
|
||
|
|
vocab = build_vocab_from_iterator(
|
||
|
|
get_word_lines_from_file('train/in.tsv.xz'),
|
||
|
|
max_tokens = vocab_size,
|
||
|
|
specials = ['<unk>'])
|
||
|
|
|
||
|
|
import pickle
|
||
|
|
with open("vocab.pickle", 'wb') as handle:
|
||
|
|
pickle.dump(vocab, handle)
|