import numpy as np
import pandas as pd

import nltk
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
from nltk.stem import WordNetLemmatizer

from tqdm import tqdm
tqdm.pandas()

from preprocessor import fr

print("I")

t = pd.read_csv("yelp_review_polarity_csv/train.csv",
                header = None,
                names = ['c', 'r'])

print("R")

y = (t['c'] - 1)
r = t['r']

r = r.progress_apply(fr)

o = pd.DataFrame([y, r]).T

o.to_csv("prepped_train.csv")