data-preprocessing/generate_traffic_data.py

import random
from datetime import datetime, timedelta

def generate_data(start_time: datetime, end_time: datetime, window_size: int):
    """
    Generate random traffic volume data for a given time range and window size.
    """
    traffic_data = []
    current_time = start_time

    while current_time < end_time:
        # Generate random traffic volume data for the current window
        traffic_volume = random.randint(0, 100)
        traffic_data.append({
            'time': current_time.strftime("%Y-%m-%d %H:%M:%S"),
            'volume': traffic_volume
        })
        current_time += timedelta(minutes=window_size)

    return traffic_data

if __name__ == "__main__":
    start_time = datetime(2023, 10, 1, 8, 0, 0)  # October 1, 2023, 08:00:00
    end_time = datetime(2023, 10, 1, 10, 0, 0)  # October 1, 2023, 10:00:00
    window_size = 15  # 15-minute window

    traffic_data = generate_data(start_time, end_time, window_size)

    with open('data/traffic_data.csv', 'w') as f:
        f.write("time,volume\n")
        for data in traffic_data:
            f.write(f"{data['time']},{data['volume']}\n")