more archives and update docker

# Dockerfile

FROM python:3.11-slim

FROM python:3.12-slim

WORKDIR /app

"""

Simulation-based Data Generator for Supply Chain Forecasting Educational App

Uses the full supply chain simulation to generate realistic data for 3 watch models.

This generates more realistic data compared to the simple data_generator.py as it

uses the complete simulation with all supply chain entities and dynamics.

"""

import sys

import os

import json

import numpy as np

from typing import Dict, List

# Add parent directory to path to import supply_chain_sim

sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from supply_chain_sim import gen_data

def get_training_data(dataset: Dict, training_years: int = 10) -> Dict:

    """

    Extract training data (first N years) from full dataset

    Args:

        dataset: Full dataset

        training_years: Number of years to include in training set

    Returns:

        Dictionary with training data only

    """

    training_months = training_years * 12

    training_data = {

        'metadata': dataset['metadata'].copy(),

        'historical_data': dataset['historical_data'][:training_months]

    }

    training_data['metadata']['years'] = training_years

    training_data['metadata']['total_months'] = training_months

    training_data['metadata']['note'] = f"Training data: first {training_years} years"

    return training_data

def get_test_data(dataset: Dict, test_year: int = 11) -> List[Dict]:

    """

    Extract test data (year to predict)

    Args:

        dataset: Full dataset

        test_year: Year number to extract (1-based)

    Returns:

        List of monthly data for the test year

    """

    start_idx = (test_year - 1) * 12

    end_idx = test_year * 12

    return dataset['historical_data'][start_idx:end_idx]

def save_dataset(dataset: Dict, filepath: str):

    """Save dataset to JSON file"""

    # Create directory if it doesn't exist

    os.makedirs(os.path.dirname(filepath), exist_ok=True)

    with open(filepath, 'w') as f:

        json.dump(dataset, f, indent=2)

    print(f"✓ Dataset saved to {filepath}")

def main():

    """Generate and save the simulation-based dataset"""

    print("=" * 60)

    print("SIMULATION-BASED DATA GENERATOR FOR FORECAST APP")

    print("=" * 60)

    print("\nGenerating Supply Chain Dataset using full simulation...")

    print("-" * 60)

    # Configure the simulation

    config = {

        'seed': 42,

        'years': 11,

        'scenario': 'basic',

        'n_customers': 50_000,

        'n_retailers': 6,

        'n_suppliers': 5,

        'n_warehouses': 2

    }

    print(f"\nConfiguration:")

    print(f"  • Seed: {config['seed']}")

    print(f"  • Years: {config['years']}")

    print(f"  • Scenario: {config['scenario']}")

    print(f"  • Customers: {config['n_customers']}")

    print(f"  • Retailers: {config['n_retailers']}")

    print()

    # Generate full 11-year dataset using simulation

    full_dataset = gen_data(config)

    print("\n" + "-" * 60)

    print("Saving datasets...")

    print("-" * 60)

    # Save full dataset

    save_dataset(full_dataset, 'data/sim_supply_chain_data_full.json')

    # Save training data (10 years)

    training_data = get_training_data(full_dataset, training_years=10)

    save_dataset(training_data, 'data/sim_supply_chain_data_training.json')

    # Save test data (year 11)

    test_data = get_test_data(full_dataset, test_year=11)

    with open('data/sim_supply_chain_data_test.json', 'w') as f:

        json.dump(test_data, f, indent=2)

    print(f"✓ Dataset saved to data/sim_supply_chain_data_test.json")

    print("\n" + "-" * 60)

    print("Dataset Generation Complete!")

    print("-" * 60)

    print(f"Total months: {len(full_dataset['historical_data'])}")

    print(f"Training months: {len(training_data['historical_data'])}")

    print(f"Test months: {len(test_data)}")

    # Print sample statistics

    print("\n" + "=" * 60)

    print("Sample Statistics (Year 1):")

    print("=" * 60)

    year1_data = full_dataset['historical_data'][:12]

    for watch in full_dataset['metadata']['watches']:

        watch_id = watch['id']

        watch_name = watch['name']

        demands = [m['watches'][watch_id-1]['demand'] for m in year1_data]

        revenues = [m['watches'][watch_id-1]['revenue'] for m in year1_data]

        print(f"\n{watch_name}:")

        print(f"  Avg Monthly Demand: {np.mean(demands):.1f} units")

        print(f"  Avg Monthly Revenue: CHF {np.mean(revenues):,.2f}")

        print(f"  Annual Revenue: CHF {np.sum(revenues):,.2f}")

    print("\n" + "=" * 60)

    print("✓ All files generated successfully!")

    print("=" * 60)

    print("\nGenerated files:")

    print("  • data/sim_supply_chain_data_full.json")

    print("  • data/sim_supply_chain_data_training.json")

    print("  • data/sim_supply_chain_data_test.json")

    print()

if __name__ == "__main__":

    main()