preprocessor.py

import re
import pandas as pd

import dateutil.parser

def preprocess(data):
    messages = []
    dates = []
    for line in data.splitlines():  # Assuming data is line-based
        try:
            date_obj = dateutil.parser.parse(line.split(',')[0])  # Assuming date is in first part
            messages.append(line.split(',')[1])  # Assuming message is in second part
            dates.append(date_obj)  # Keep as datetime object
        except (ValueError, IndexError):
            pass  # Handle parsing errors or missing data silently (optional)
    df = pd.DataFrame({'user_message': messages, 'date': dates})
    return df

    
    users = []
    messages = []
    for message in df['user_message']:
        entry = re.split('([\w\W]+?):\s', message)
        if entry[1:]:  # user name
            users.append(entry[1])
            messages.append(" ".join(entry[2:]))
        else:
            users.append('group_notification')
            messages.append(entry[0])

    df['user'] = users
    df['message'] = messages
    df.drop(columns=['user_message'], inplace=True)

    df['only_date'] = df['date'].dt.date
    df['year'] = df['date'].dt.year
    df['month_num'] = df['date'].dt.month
    df['month'] = df['date'].dt.month_name()
    df['day'] = df['date'].dt.day
    df['day_name'] = df['date'].dt.day_name()
    df['hour'] = df['date'].dt.hour
    df['minute'] = df['date'].dt.minute

    period = []
    for hour in df[['day_name', 'hour']]['hour']:
        if hour == 23:
            period.append(str(hour) + "-" + str('00'))
        elif hour == 0:
            period.append(str('00') + "-" + str(hour + 1))
        else:
            period.append(str(hour) + "-" + str(hour + 1))

    df['period'] = period

    return df