This file contains hidden or 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
import sys | |
def split_line(line): | |
cols = line.split("\t") | |
return cols | |
def get_words(cols): | |
words_ids = cols[4].split(" ") | |
words = [w.split("#")[0] for w in words_ids] | |
return words |