DanielOX

import nltk
import string
from collections import defaultdict

# Sample gutenberg corpus loaded from nltk.corpus

corpus = " ".join(nltk.corpus.gutenberg.words('austen-emma.txt'))

# Tokenize corpus into sentences 

DanielOX

from sklearn.feature_extraction.text import CountVectorizer

# corpus source [ https://en.wikipedia.org/wiki/Baseball ]

corpus = """Baseball is a bat-and-ball game played between two opposing teams who take turns batting and fielding. The game proceeds when a player on the fielding team, called the pitcher, throws a ball which a player on the batting team tries to hit with a bat. The objective of the offensive team (batting team) is to hit the ball into the field of play, allowing its players to run the bases, having them advance counter-clockwise around four bases to score what are called "runs". The objective of the defensive team (fielding team) is to prevent batters from becoming runners, and to prevent runners' advance around the bases.[2] A run is scored when a runner legally advances around the bases in order and touches home plate (the place where the player started as a batter). The team that scores the most runs by the end of the game is the winner."""

# Tokenize corpus into list of sentences beca

DanielOX

import pandas as pd
import re

# Path of Easypaisa archived message text file

easypaisa_file = './easypaisa.txt' 

with open(easypaisa_file) as f:
    data = f.read()
    transaction_message = []

DanielOX

import pandas as pd
import re

# uri of jazzcash archived messages 

jazzcash_file = "./jazzcash.txt"

# Iterate over and filter recieved cash and spam messages

with open(jazzcash_file) as f:

DanielOX