preprocessor.py

import re
import pandas as pd
from nltk.corpus import stopwords
import nltk

nltk.download('stopwords')

def preprocess(data):
    pattern = '\d{1,2}/\d{1,2}/\d{2,4},\s\d{1,2}:\d{2}\s-\s'

    messages = re.split(pattern, data)[1:]
    dates = re.findall(pattern, data)

    df = pd.DataFrame({'user_message': messages, 'message_date': dates})
    # convert message_date type
    df['message_date'] = pd.to_datetime(df['message_date'], format='%d/%m/%Y, %H:%M - ')

    df.rename(columns={'message_date': 'date'}, inplace=True)

    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)

    # Additional preprocessing
    stop_words_en = set(stopwords.words('english'))
    stop_words_fr = set(stopwords.words('french'))
    combined_stop_words = stop_words_en.union(stop_words_fr)

    def clean_message(message):
        # Remove messages containing '<Media ...>'
        if '<Médias omis>' in message:
            return ''
        # Remove words with less than 4 characters
        words = [word for word in message.split() if len(word) >= 4]
        # Remove stopwords
        words = [word for word in words if word.lower() not in combined_stop_words]
        return ' '.join(words)

    df['message'] = df['message'].apply(clean_message)
    df = df[df['message'] != '']  # Remove empty messages

    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