preprocess.py

import re
import pandas as pd

def preprocess(data):
    data = data.replace('\u202f', '')
    # patt = r'\[\d{2}\/\d{2}\/\d{2},\s\d{2}:\d{2}:\d{2}]\s'

    pattern1 = r'\d{2}/\d{2}/\d{2}, \d{1,2}:\d{2}[ap]m -'
    pattern2 = r'\[\d{2}/\d{2}/\d{2}, \d{2}:\d{2}:\d{2}\]'
    pattern3 = r'\d{2}/\d{2}/\d{2}, \d{1,2}:\d{2} -'
    pattern4 = r'\d{1,2}/\d{1,2}/\d{2}, \d{2}:\d{2} -'
    pattern5 = r'\d{2}/\d{2}/\d{2}, \d{1,2}:\d{2}[AP]M -'
    pattern6 = r'\d{1,2}/\d{1,2}/\d{2}, \d{1,2}:\d{2} [APM]{2} -'

    # data = "30/06/21, 1:46pm - Gauri Mami turned off disappearing messages."

    result = []
    messages = []
    dates = []

    if re.search(pattern1, data):
        result.append(data)
        messages = re.split(pattern1, data)[1:]
        dates = re.findall(pattern1, data)
    #     dates[:10]

    if re.search(pattern2, data):
        result.append(data)
        messages = re.split(pattern2, data)[1:]
        dates = re.findall(pattern2, data)

    if re.search(pattern3, data):
        result.append(data)
        messages = re.split(pattern3, data)[1:]
        dates = re.findall(pattern3, data)
    

    if re.search(pattern4, data):
        result.append(data)
        messages = re.split(pattern4, data)[1:]
        dates = re.findall(pattern4, data)

    if re.search(pattern5, data):
        result.append(data)
        messages = re.split(pattern5, data)[1:]
        dates = re.findall(pattern5, data)

    if re.search(pattern6, data):
        result.append(data)
        messages = re.split(pattern6, data)[1:]
        dates = re.findall(pattern6, data)
    
    if not result:
        result = None





    # messages = re.split(patt, data)[1:]

    # dates = re.findall(patt, data)

    df = pd.DataFrame({'date': dates, 'messageog': messages})
    
    df['date'] = df['date'].astype(str).str.replace('[', '', regex=False)
    df['date'] = df['date'].astype(str).str.replace(']', '', regex=False)
    df['date'] = df['date'].astype(str).str.replace('-', '', regex=False)

    df['date'] = pd.to_datetime(df['date'])
    # df['date'][0]
    df = df[1:]

    df['messageog'] = df['messageog'].astype(str)  # Convert column to string type
    df['messageog'] = df['messageog'].fillna('')
    df['sender'] = ''

    df[['sender', 'message']] = df['messageog'].str.split(':', n=1, expand=True)

    df = df[['date', 'sender', 'message']]

    df['year'] = df['date'].dt.year
    df['day'] = df['date'].dt.day
    df['hour'] = df['date'].dt.hour
    df['minute'] = df['date'].dt.minute
    df['second'] = df['date'].dt.second
    df['month'] = df['date'].dt.month_name()
    # df = df.loc[df['sender'] != group_name]
    df = df.loc[df['sender'] != '\u202a+91\xa095456\xa017572\u202c']

    df = df.loc[~df['sender'].str.contains('changed the subject')]
    df = df.loc[~df['sender'].str.contains('message')]
    df = df.loc[~df['sender'].str.contains('added')]
    df = df.loc[~df['sender'].str.contains('created group')]
    df = df.loc[~df['sender'].str.contains('left')]
    df = df.loc[~df['sender'].str.contains('removed')]
    df = df.loc[~df['sender'].str.contains('admin')]
    df = df.loc[~df['sender'].str.contains('changed')]
    df = df.loc[~df['sender'].str.contains('encrypted')]


    
    df = df[['date', 'sender', 'message']]

    return df