chatvisualizer.py

import re
import regex
import pandas as pd
import numpy as np
import emoji
import plotly.express as px
from collections import Counter
import matplotlib.pyplot as plt
from os import path 
from PIL import Image
import datetime
import dateconv
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator


def startsWithDateAndTimeAndroid(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


def startsWithDateAndTimeios(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



def FindAuthor(s):
  s=s.split(":")
  if len(s)==2:
    return True
  else:
    return False


def getDataPointAndroid(line):   
    splitLine = line.split(' - ') 
    dateTime = splitLine[0]
    date, time = dateTime.split(', ') 
    message = ' '.join(splitLine[1:])
    if FindAuthor(message): 
        splitMessage = message.split(':') 
        author = splitMessage[0] 
        message = ' '.join(splitMessage[1:])
    else:
        author = None
    return date, time, author, message




def getDataPointios(line):
    splitLine = line.split('] ')
    dateTime = splitLine[0]
    if ',' in dateTime:
        date, time = dateTime.split(',')
    else:
        date, time = dateTime.split(' ')
    message = ' '.join(splitLine[1:])
    if FindAuthor(message):
        splitMessage = message.split(':')
        author = splitMessage[0]
        message = ' '.join(splitMessage[1:])
    else:
        author = None
    if time[5]==":":
        time = time[:5]+time[-3:]
    else:
        if 'AM' in time or 'PM' in time:
            time = time[:6]+time[-3:]
        else:
            time = time[:6]
    return date, time, author, message




def split_count(text):

    emoji_list = []
    data = regex.findall(r'\X', text)
    for word in data:
        if any(char in emoji.UNICODE_EMOJI for char in word):
            emoji_list.append(word)

    return emoji_list



parsedData = [] # List to keep track of data so it can be used by a Pandas dataframe
conversationPath = 'Group.txt' 
with open(conversationPath, encoding="utf-8") as fp:
    device=''
    first=fp.readline()
    print(first)
    if '[' in first:
      device='ios'
    else:
      device="android"
    fp.readline() 
    messageBuffer = [] 
    date, time, author = None, None, None #message contains 4 things-"date","time","author","message" 
    while True:
        line = fp.readline() 
        if not line: 
            break
        if device=="ios":
          line = line.strip()
          if startsWithDateAndTimeios(line):
            if len(messageBuffer) > 0:
              parsedData.append([date, time, author, ' '.join(messageBuffer)])
            messageBuffer.clear()
            date, time, author, message = getDataPointios(line)
            messageBuffer.append(message)
          else:
            line= (line.encode('ascii', 'ignore')).decode("utf-8")
            if startsWithDateAndTimeios(line):
              if len(messageBuffer) > 0:
                parsedData.append([date, time, author, ' '.join(messageBuffer)])
              messageBuffer.clear()
              date, time, author, message = getDataPointios(line)
              messageBuffer.append(message)
            else:
              messageBuffer.append(line)
        else:
          line = line.strip()
          if startsWithDateAndTimeAndroid(line): 
            if len(messageBuffer) > 0:
              parsedData.append([date, time, author, ' '.join(messageBuffer)])
            messageBuffer.clear()
            date, time, author, message = getDataPointAndroid(line)
            messageBuffer.append(message)
          else:
            messageBuffer.append(line)



if device =='android':
        df = pd.DataFrame(parsedData, columns=['Date','Time', 'Author', 'Message'])
        df["Date"] = pd.to_datetime(df["Date"])
        df = df.dropna()
        df["emoji"] = df["Message"].apply(split_count)
        ### Counting number of letters in each message
        df["Letter's"] = df['Message'].apply(lambda s : len(s))
        ### Counting number of word's in each message
        df["Word's"] = df['Message'].apply(lambda s : len(s.strip().split(' ')))
        URLPATTERN = r'(https?://\S+)'
        df['urlcount'] = df.Message.apply(lambda x: re.findall(URLPATTERN, x)).str.len()
        ### Function to count number of media in chat.
        MEDIAPATTERN = r' <Media omitted>'
        df['Media_Count'] = df.Message.apply(lambda x : re.findall(MEDIAPATTERN, x)).str.len()
        media = np.sum(df.Media_Count)
else:
        df = pd.DataFrame(parsedData, columns=['Date', 'Time', 'Author', 'Message']) # Initialising a pandas Dataframe.
        df = df.dropna()
        df["Date"] = df["Date"].apply(dateconv)
        df["Date"] = pd.to_datetime(df["Date"],format='%Y-%m-%d')
        df["emoji"] = df["Message"].apply(split_count)
        ### Counting number of letters in each message
        df["Letter's"] = df['Message'].apply(lambda s : len(s))
        ### Counting number of word's in each message
        df["Word's"] = df['Message'].apply(lambda s : len(s.split(' ')))
        URLPATTERN = r'(https?://\S+)'
        df['urlcount'] = df.Message.apply(lambda x: re.findall(URLPATTERN, x)).str.len()
        ### Function to count number of media in chat.
        MEDIAPATTERN = r'<Media omitted>'
        df['Media_Count'] = df.Message.apply(lambda x : re.findall(MEDIAPATTERN, x)).str.len()
        media = np.sum(df.Media_Count)




### Adding one more column of "Day" for better analysis, here we use datetime library which help us to do this task easily.
weeks = {
0 : 'Monday',
1 : 'Tuesday',
2 : 'Wednesday',
3 : 'Thrusday',
4 : 'Friday',
5 : 'Saturday',
6 : 'Sunday'
}

df["Day"] = df['Date'].dt.weekday.map(weeks)
# Rearrenging the columns for better understanding.
df = df[['Date', 'Day', 'Time','Author','Message', "emoji", "Letter's", "Word's", 'urlcount', 'Media_Count']]
# Change the datatype of the column "Day"
df['Day'] = df['Day'].astype('category')
# Looking newborn dataset
dfmain =  df





total_emojis_list = list([a for b in df.emoji for a in b])
emoji_dict = dict(Counter(total_emojis_list))
emoji_dict = sorted(emoji_dict.items(), key=lambda x: x[1], reverse=True)
emoji_df = pd.DataFrame(emoji_dict, columns=['emoji', 'count'])