WordVector

import argparse
from nltk.stem import snowball
from nltk import pos_tag, word_tokenize
from nltk.corpus import wordnet


parser = argparse.ArgumentParser()
parser.add_argument("file")

options = parser.parse_args()

with open(options.file, 'r') as f:
        gum_text = f.read()


gum_docs = gum_text.split("\n")


frequencies = []

for document in gum_docs:
    tokenized = word_tokenize(document)
    tagged = pos_tag(tokenized)
    frequencies.append(tagged)
print(frequencies[0][0])