factor_prices = load_factors_dataset()
X_full, F_full = prices_to_returns(prices, factor_prices)


X_tr, X_te, F_tr, F_te = train_test_split(
   X_full, F_full, test_size=0.33, shuffle=False
)


fm = MeanRisk(
   objective_function=ObjectiveFunction.MAXIMIZE_RATIO,
   risk_measure=RiskMeasure.VARIANCE,
   prior_estimator=FactorModel(),
)
fm.fit(X_tr, F_tr)
ptf_fm = fm.predict(X_te); ptf_fm.name = "Factor Model"
print(f"\nFactor-model Sharpe: {ptf_fm.annualized_sharpe_ratio:.3f}")


pipe = Pipeline([
   ("preselect",   SelectKExtremes(k=8, highest=True)),
   ("optimize",    MeanRisk(
       objective_function=ObjectiveFunction.MAXIMIZE_RATIO,
       risk_measure=RiskMeasure.VARIANCE)),
])
pipe.fit(X_train)
ptf_pipe = pipe.predict(X_test); ptf_pipe.name = "Top-8 + Max Sharpe"


wf_model = MeanRisk(
   objective_function=ObjectiveFunction.MAXIMIZE_RATIO,
   risk_measure=RiskMeasure.VARIANCE,
)
mp_portfolio = cross_val_predict(
   wf_model, X,
   cv=WalkForward(train_size=252*2, test_size=63),
   n_jobs=-1,
)
mp_portfolio.name = "Walk-Forward Max Sharpe"
print(f"\nWalk-forward portfolio  Sharpe={mp_portfolio.annualized_sharpe_ratio:.3f}  "
     f"CalmarRatio={mp_portfolio.calmar_ratio:.3f}")
mp_portfolio.plot_cumulative_returns().show()


tuned = MeanRisk(
   objective_function=ObjectiveFunction.MAXIMIZE_RATIO,
   risk_measure=RiskMeasure.VARIANCE,
   prior_estimator=EmpiricalPrior(mu_estimator=EWMu(alpha=0.1)),
)
grid = GridSearchCV(
   estimator=tuned,
   cv=WalkForward(train_size=252*2, test_size=63),
   n_jobs=-1,
   param_grid={
       "l2_coef": [0.0, 0.01, 0.1],
       "prior_estimator__mu_estimator__alpha": [0.05, 0.1, 0.2, 0.5],
   },
)
grid.fit(X_train)
print("\nBest params:", grid.best_params_)
print(f"Best CV score (Sharpe): {grid.best_score_:.3f}")


ptf_tuned = grid.best_estimator_.predict(X_test); ptf_tuned.name = "Tuned Max Sharpe"


final = Population([
   *baseline_population,
   ptf_min_var, ptf_max_sharpe,
   ptf_rb_var, ptf_rb_cvar,
   ptf_hrp, ptf_nco,
   ptf_robust, ptf_gerber,
   ptf_constr, ptf_bl, ptf_fm,
   ptf_pipe, ptf_tuned,
])


_full = final.summary()
_wanted_final = [
   "Annualized Mean", "Annualized Standard Deviation",
   "Annualized Sharpe Ratio", "Annualized Sortino Ratio",
   "CVaR at 95%", "Maximum Drawdown", "Max Drawdown",
]
_have_final = [r for r in _wanted_final if r in _full.index]
summary = _full.loc[_have_final].T.sort_values(
   "Annualized Sharpe Ratio", ascending=False
)


print("\n" + "=" * 80)
print("FINAL HORSE RACE — sorted by Sharpe (out-of-sample test set)")
print("=" * 80)
print(summary.to_string())


final.plot_cumulative_returns().show()


final.plot_composition().show()


ptf_rb_var.plot_contribution(measure=RiskMeasure.VARIANCE).show()


print("\nDone. Try swapping risk measures, adding constraints, or wiring in")
print("your own returns DataFrame — every estimator follows the sklearn API.")