System Setup

List of all the python libraries that are required

numpy
pandas
matplotlib
seaborn
wordcloud
emoji
jovian

import sys
!{sys.executable} -m pip install collections

Collecting collections
  ERROR: Could not find a version that satisfies the requirement collections (from versions: none)
ERROR: No matching distribution found for collections

import jovian
import re
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from wordcloud import WordCloud, STOPWORDS
import emoji
from collections import Counter

Data Preprocessing

Regex cheatsheet
https://www.rexegg.com/regex-quickstart.html

Regex test - live
https://regexr.com/

Datetime format
http://strftime.org/

Use a custom a regex and datatime format by reffering to the above links if you run into empty df or format errors. As the exports from whatsapp are not standardized.

def rawToDf(file, key):
    split_formats = {
        '12hr' : '\d{1,2}/\d{1,2}/\d{2,4},\s\d{1,2}:\d{2}\s[APap][mM]\s-\s',
        '24hr' : '\d{1,2}/\d{1,2}/\d{2,4},\s\d{1,2}:\d{2}\s-\s',
        'custom' : ''
    }
    datetime_formats = {
        '12hr' : '%d/%m/%y, %I:%M %p - ',
        '24hr' : '%d/%m/%y, %H:%M - ',
        'custom': ''
    }
    
    with open(file, 'r', encoding='utf-8') as raw_data:
        raw_string = ' '.join(raw_data.read().split('\n')) # converting the list split by newline char. as one whole string as there can be multi-line messages
        user_msg = re.split(split_formats[key], raw_string) [1:] # splits at all the date-time pattern, resulting in list of all the messages with user names
        date_time = re.findall(split_formats[key], raw_string) # finds all the date-time patterns
        
        df = pd.DataFrame({'date_time': date_time, 'user_msg': user_msg}) # exporting it to a df
        
    # converting date-time pattern which is of type String to type datetime,
    # format is to be specified for the whole string where the placeholders are extracted by the method 
    df['date_time'] = pd.to_datetime(df['date_time'], format=datetime_formats[key])
    
    # split user and msg 
    usernames = []
    msgs = []
    for i in df['user_msg']:
        a = re.split('([\w\W]+?):\s', i) # lazy pattern match to first {user_name}: pattern and spliting it aka each msg from a user
        if(a[1:]): # user typed messages
            usernames.append(a[1])
            msgs.append(a[2])
        else: # other notifications in the group(eg: someone was added, some left ...)
            usernames.append("grp_notif")
            msgs.append(a[0])

    # creating new columns         
    df['user'] = usernames
    df['msg'] = msgs

    # dropping the old user_msg col.
    df.drop('user_msg', axis=1, inplace=True)
    
    return df