#Construct a news articl classifier using Naive Bayes Classifier

import string
import math
import random



#This just returns a list of all the lines of text in
#the source file.  The source files are arranged so that
#each snippet of a news article occupies a single line.


def get_data(filename):
    linelist=[]
    f=open(filename,'r')
    for item in f:
        #item=item.replace("\u2019","'")
        linelist.append(item)
    return linelist


#takes a string and returns a cleaned-up list of words in the string.
#You will apply this in turn to each line of text in the source dataset.
def text_transform(text):
    stopwords={'ourselves', 'hers', 'between', 'yourself', 'but', 'again',\
       'there', 'about', 'once', 'during', 'out', 'very', 'having',\
       'with', 'they', 'own', 'an', 'be', 'some', 'for', 'do', 'its',\
       'yours', 'such', 'into', 'of', 'most', 'itself', 'other',\
       'off', 'is', 's', 'am', 'or', 'who', 'as', 'from', 'him', \
       'each', 'the', 'themselves', 'until', 'below', 'are', 'we', \
       'these', 'your', 'his', 'through', 'don', 'nor', 'me', 'were',\
       'her', 'more', 'himself', 'this', 'down', 'should', 'our', 'their',\
       'while', 'above', 'both', 'up', 'to', 'ours', 'had', 'she', 'all',\
       'no', 'when', 'at', 'any', 'before', 'them', 'same', 'and', 'been',\
       'have', 'in', 'will', 'on', 'does', 'yourselves', 'then', 'that',\
       'because', 'what', 'over', 'why', 'so', 'can', 'did', 'not', 'now',\
       'under', 'he', 'you', 'herself', 'has', 'just', 'where', 'too',\
       'only', 'myself', 'which', 'those', 'i', 'after', 'few', 'whom',\
       't', 'being', 'if', 'theirs', 'my', 'against', 'a', 'by', 'doing',\
       'it', 'how', 'further', 'was', 'here', 'than'}
    text = text.translate(str.maketrans('', '', string.punctuation))
    text = [word.lower() for word in text.split() if word.lower() not in stopwords ]
    return text