main.py

import matplotlib.pyplot as plt
import numpy as np

from src.data_loader import load_prices
from src.returns import log_returns, annualized_vol
from src.risk import var, cvar, var99, cvar99, var999, cvar999
from src.portfolio import min_variance
from src.simulation import monte_carlo
from src.utils import sharpe_ratio, validate_prices


def main():
    # ----------------------------
    # 1. Load market data
    # ----------------------------
    tickers = ["UBSFY", "CEIN", "DIS"]
    prices = load_prices(tickers, "2021-02-01", "2026-01-23")

    validate_prices(prices)
    print("Prices loaded:\n", prices.head(), "\n")

    # ----------------------------
    # 2. Returns & volatility
    # ----------------------------
    returns = log_returns(prices)
    vol = annualized_vol(returns)

    print("Annualized Volatility:")
    print(vol, "\n")

    # ----------------------------
    # 3. Risk metrics
    # ----------------------------
    portfolio_returns = returns.mean(axis=1)

    print("VaR (5%):", var(portfolio_returns))
    print("CVaR (5%):", cvar(portfolio_returns), "\n")
    print("VaR (99%):", var99(portfolio_returns))
    print("CVaR (99%):", cvar99(portfolio_returns), "\n")
    print("VaR (99.9%):", var999(portfolio_returns))
    print("CVaR (99.9%):", cvar999(portfolio_returns), "\n")

    # ----------------------------
    # 4. Portfolio optimization
    # ----------------------------
    cov_matrix = returns.cov() * 252
    weights = min_variance(cov_matrix.values)

    print("Min Variance Portfolio Weights:")
    for t, w in zip(tickers, weights):
        print(f"{t}: {w:.2%}")
    print()

    # ----------------------------
    # 5. Sharpe ratio
    # ----------------------------
    sharpe = sharpe_ratio(portfolio_returns)
    print("Portfolio Sharpe Ratio:", round(sharpe, 2), "\n")

    # ----------------------------
    # 6. Monte Carlo simulation
    # ----------------------------
    mu = portfolio_returns.mean()
    sigma = portfolio_returns.std()

    paths = monte_carlo(mu, sigma, days=252, sims=1000)

    plt.plot(paths, alpha=0.1)
    plt.title("Monte Carlo Portfolio Simulation")
    plt.xlabel("Days")
    plt.ylabel("Portfolio Value")
    plt.show()


if __name__ == "__main__":
    main()