!pip install jovian --upgrade --quiet
!pip install numpy --upgrade --quiet
!pip install pandas --upgrade --quiet
!pip install matplotlib --upgrade --quiet
!pip install seaborn --upgrade --quiet
!pip install wordcloud --upgrade --quiet
!pip install emoji  --upgrade --quiet

project_name = "whatsapp-chat-analysis-course-project-try"

import jovian

jovian.commit(project=project_name,enviroment=None,files=["Chat.txt"])

import os
import pandas as pd
import re
import datetime as time
import jovian
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import emoji
import re

whatsapp_df = pd.read_fwf('Chat.txt', header = None)

whatsapp_df

whatsapp_df.info()

whatsapp_df.shape

def txtTodf(txt_file):
    '''Convert WhatsApp chat log text file to a Pandas dataframe.'''
    
    # some regex to account for messages taking up multiple lines
    pat = re.compile(r'^(\d\d\/\d\d\/\d\d\d\d.*?)(?=^^\d\d\/\d\d\/\d\d\d\d|\Z)', re.S | re.M)
    with open(txt_file) as file:
        data = [m.group(1).strip().replace('\n', ' ') for m in pat.finditer(file.read())]

    user     = []; 
    message  = []; 
    datetime = []
    
    for row in data:

        # timestamp is before the first dash
        datetime.append(row.split(' - ')[0])

        # sender is between am/pm, dash and colon
        try:
            s = re.search('m - (.*?):', row).group(1)
            user.append(s)
        except:
            user.append('')

        # message content is after the first colon
        try:
            message.append(row.split(': ', 1)[1])
        except:
            message.append('')

    df = pd.DataFrame(zip(datetime, user, message), columns=['datetime', 'user', 'message'])
    df['datetime'] = pd.to_datetime(df.datetime, format='%d/%m/%Y, %I:%M %p')

    # remove events not associated with a sender
    df = df[df.user != ''].reset_index(drop=True)
    
    return df

whatsapp_df = txtTodf('Chat.txt')

whatsapp_df.head(10)

whatsapp_df.info()

jovian.commit(project=project_name)

# To understand the number od the image data
img = whatsapp_df[whatsapp_df['message'] == "<Media omitted>" ]
img.shape

# We will drop all the image file by using the Drop functions
whatsapp_df.drop(img.index, inplace=True)

whatsapp_df.head(10)

whatsapp_df.reset_index(inplace=True, drop=True)
whatsapp_df.shape

jovian.commit(project=project_name)

#Understand how many user and messages in this chat first
totalNumberofMessage = whatsapp_df.message.count()
username   = whatsapp_df["user"].unique()

print('The total of the number of message:',totalNumberofMessage)
print('User name that involve in the chat:',username)

userNumber = whatsapp_df.user.unique()
print("The total number of message from each of the users:\n")
for i in range(len(userNumber)):
    #Get one particular user name
    user_df = whatsapp_df[whatsapp_df['user'] == length[i]]
    
    #user_df will show the user message 
    name = print(f'User name: {length[i]}')
    
    #Get the total number of each user send
    messages = print('Messages', user_df.shape[0])
    
    print()

whatsapp_df.head(5)

sortHighestMessage = whatsapp_df.groupby("user")["message"].count().sort_values(ascending=False)

sortHighestMessage

#Copy one dataset
whatsapp_df1 = whatsapp_df.copy()

highestMessage = whatsapp_df1.groupby("user")["message"].count().sort_values(ascending = False).head(5)
highestMessage.drop(columns ="index",inplace=True)
highestMessage

#Formating
sns.set_style("darkgrid")
plt.rcParams['font.size'] = 10
plt.rcParams['figure.figsize'] = (12, 8)


#Creating a bar chart
sns.barplot()

# Improving Default Styles using Seaborn
sns.set_style("darkgrid")

# For better readablity;
import matplotlib
matplotlib.rcParams['font.size'] = 10
matplotlib.rcParams['figure.figsize'] = (12, 8)

# A bar plot for top 10 days
sns.barplot(top10days.date, top10days.message_count, palette="hls");

# Saving the plots
plt.savefig('top10_days.svg', format = 'svg')

def emojis(file):
    
    emoji_ctr = Counter()
    emojis_list = map(lambda x: ''.join(x.split()), emoji.UNICODE_EMOJI.keys())
    r = re.compile('|'.join(re.escape(p) for p in emojis_list))
    for idx, row in df.iterrows():
    if row["user"] == me:
        emojis_found = r.findall(row["msg"])
        for emoji_found in emojis_found:
            emoji_ctr[emoji_found] += 1
            
    return file

# We want to know each user send how many message and Emojis
amountOfChat = whatsapp_df.groupby("user")["message"].count()

length = whatsapp_df.user.unique()

for i in range(len(length)):
    #Get one particular user name
    user_df = whatsapp_df[whatsapp_df['user'] == length[i]]
    
    #user_df will show the user message 
    print('User:',user_df)
    
    #Get the total number of each user send
     print('Messages', user_df.shape[0])
        
    # emojis conists of total emojis
    emojis = sum(req_df['emoji'].str.len())
    
    print('Emojis Sent', emojis)
    
    #links consist of total links
    links = sum(req_df["urlcount"])   
    print('Links Sent', links)   

l = messages_df.Author.unique()

for i in range(len(l)):
  # Filtering out messages of particular user
  req_df= messages_df[messages_df["Author"] == l[i]]
  # req_df will contain messages of only one particular user
  print(f'Stats of {l[i]} -')
  # shape will print number of rows which indirectly means the number of messages
  print('Messages Sent', req_df.shape[0])
  #Word_Count contains of total words in one message. Sum of all words/ Total Messages will yield words per message
  words_per_message = (np.sum(req_df['Word_Count']))/req_df.shape[0]
  print('Words per message', words_per_message)
  #media conists of media messages
  media = media_messages_df[media_messages_df['Author'] == l[i]].shape[0]
  print('Media Messages Sent', media)
  # emojis conists of total emojis
  emojis = sum(req_df['emoji'].str.len())
  print('Emojis Sent', emojis)
  #links consist of total links
  links = sum(req_df["urlcount"])   
  print('Links Sent', links)   
  print()