generate_mock_data.py

import pandas as pd
import numpy as np
import datetime

def generate_mock_data(filename='Voltacore_EV_Battery_Demo_Data.xlsx', num_weeks=104):
    """
    Generates a realistic mock dataset for the Voltacore case study.
    """
    dates = pd.date_range(end=datetime.datetime.today(), periods=num_weeks, freq='W-MON')
    
    data = []
    base_sales = 5000
    
    for date in dates:
        # Seasonality
        month = date.month
        seasonality = 1.0 + 0.2 * np.sin(2 * np.pi * month / 12)
        
        # Trend
        trend = 1.0 + (0.05 * (np.random.rand() - 0.5)) # Small random trend
        
        # Events
        is_holiday = 1 if month == 12 or month == 1 else 0
        is_promo = 1 if np.random.rand() > 0.8 else 0
        
        # Sales Calculation
        sales = base_sales * seasonality * trend
        if is_holiday: sales *= 1.3
        if is_promo: sales *= 1.5
        
        # Noise
        sales += np.random.normal(0, 200)
        
        # Inventory (Simulate overstock/understock)
        inventory = sales * (1.0 + (np.random.rand() - 0.5) * 0.4) 
        
        # Fuel Price
        fuel_price = 100 + (np.random.rand() * 50)
        
        row = {
            'Date': date,
            'Weekly_Sales_Units': int(sales),
            'Unit_Price_USD': 150 + np.random.uniform(-5, 5),
            'Unit_Cost_USD': 100 + np.random.uniform(-2, 2),
            'Current_Inventory_Units': int(inventory),
            'Transport_Distance_km': 1000 + np.random.normal(0, 200),
            'Fuel_Price_Index': fuel_price,
            'Holiday_Flag': is_holiday,
            'Promotion_Flag': is_promo
        }
        data.append(row)
        
    df = pd.DataFrame(data)
    df.to_excel(filename, index=False)
    print(f"Generated {filename}")

if __name__ == "__main__":
    generate_mock_data()