-
-
Save amankharwal/3d19b1fddb94c43f4ebeb1c9232f5721 to your computer and use it in GitHub Desktop.
This file contains 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 re | |
import pandas as pd | |
import numpy as np | |
import emoji | |
from collections import Counter | |
import matplotlib.pyplot as plt | |
from PIL import Image | |
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator | |
# Extract Time | |
def date_time(s): | |
pattern = '^([0-9]+)(\/)([0-9]+)(\/)([0-9]+), ([0-9]+):([0-9]+)[ ]?(AM|PM|am|pm)? -' | |
result = re.match(pattern, s) | |
if result: | |
return True | |
return False | |
# Find Authors or Contacts | |
def find_author(s): | |
s = s.split(":") | |
if len(s)==2: | |
return True | |
else: | |
return False | |
# Finding Messages | |
def getDatapoint(line): | |
splitline = line.split(' - ') | |
dateTime = splitline[0] | |
date, time = dateTime.split(", ") | |
message = " ".join(splitline[1:]) | |
if find_author(message): | |
splitmessage = message.split(": ") | |
author = splitmessage[0] | |
message = " ".join(splitmessage[1:]) | |
else: | |
author= None | |
return date, time, author, message |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment