foxhunt/ml/examples/optimize_barriers.rs

//! Barrier Parameter Optimizer Example
//!
//! Uses Monte-Carlo simulations to find optimal triple-barrier parameters
//! for ES.FUT, NQ.FUT, ZN.FUT, and 6E.FUT futures contracts.
//!
//! ## Usage
//! ```bash
//! cargo run -p ml --example optimize_barriers --release
//! ```
//!
//! ## Expected Output
//! - Optimal profit_target_bps, stop_loss_bps, max_holding_period
//! - Sharpe ratio, win rate, max drawdown for each configuration
//! - CSV file with full grid search results

use anyhow::{Context, Result};
use rand::Rng;
use std::collections::HashMap;
use std::fs::File;
use std::io::Write;
use std::path::PathBuf;
use tracing::{error, info, warn};

use ml::labeling::triple_barrier::{BarrierConfig, BarrierResult};
use ml::real_data_loader::DbnDataSource;

/// Optimal parameters for a specific market regime
#[derive(Debug, Clone)]
pub struct OptimalParameters {
    pub symbol: String,
    pub profit_target_bps: u32,
    pub stop_loss_bps: u32,
    pub max_holding_hours: f64,
    pub sharpe_ratio: f64,
    pub win_rate: f64,
    pub avg_return_pct: f64,
    pub max_drawdown_pct: f64,
    pub avg_bars_held: usize,
}

/// Simulation metrics for a parameter set
#[derive(Debug, Clone)]
struct SimulationMetrics {
    sharpe: f64,
    win_rate: f64,
    avg_return: f64,
    max_drawdown: f64,
    avg_bars_held: f64,
    trade_count: usize,
}

/// Monte-Carlo barrier optimizer
pub struct BarrierOptimizer {
    pub symbol: String,
    pub historical_prices: Vec<f64>,
    pub daily_volatility: f64,
    pub n_simulations: usize,
}

impl BarrierOptimizer {
    pub fn new(symbol: String, historical_prices: Vec<f64>, n_simulations: usize) -> Self {
        let daily_volatility = Self::compute_daily_volatility(&historical_prices);

        info!(
            "Initialized optimizer for {} with {} bars, volatility={:.2}%",
            symbol,
            historical_prices.len(),
            daily_volatility * 100.0
        );

        Self {
            symbol,
            historical_prices,
            daily_volatility,
            n_simulations,
        }
    }

    /// Compute daily volatility from price series
    fn compute_daily_volatility(prices: &[f64]) -> f64 {
        if prices.len() < 2 {
            return 0.02; // Default 2%
        }

        let returns: Vec<f64> = prices
            .windows(2)
            .map(|w| (w[1] / w[0]).ln())
            .collect();

        let mean = returns.iter().sum::<f64>() / returns.len() as f64;
        let variance = returns
            .iter()
            .map(|r| (r - mean).powi(2))
            .sum::<f64>()
            / returns.len() as f64;

        variance.sqrt()
    }

    /// Run grid search over parameter space
    pub fn optimize(&self) -> Result<OptimalParameters> {
        info!("Starting grid search optimization...");

        let mut best_score = f64::NEG_INFINITY;
        let mut best_params: Option<OptimalParameters> = None;
        let mut all_results = Vec::new();

        // Grid search parameters
        let profit_targets = (50..=500).step_by(25).collect::<Vec<_>>();
        let stop_losses = (50..=500).step_by(25).collect::<Vec<_>>();
        let holding_periods = vec![0.25, 0.5, 1.0, 2.0, 4.0, 8.0]; // Hours

        let total_combinations = profit_targets.len() * stop_losses.len() * holding_periods.len();
        info!("Testing {} parameter combinations", total_combinations);

        for (idx, profit_bps) in profit_targets.iter().enumerate() {
            for stop_bps in &stop_losses {
                for holding_hours in &holding_periods {
                    let config = BarrierConfig {
                        profit_target_bps: *profit_bps,
                        stop_loss_bps: *stop_bps,
                        max_holding_period_ns: (*holding_hours * 3600.0 * 1e9) as u64,
                    };

                    // Run Monte-Carlo simulations
                    let metrics = self.simulate(&config)?;
                    let score = self.compute_score(&metrics);

                    all_results.push((config.clone(), metrics.clone(), score));

                    if score > best_score {
                        best_score = score;
                        best_params = Some(OptimalParameters {
                            symbol: self.symbol.clone(),
                            profit_target_bps: *profit_bps,
                            stop_loss_bps: *stop_bps,
                            max_holding_hours: *holding_hours,
                            sharpe_ratio: metrics.sharpe,
                            win_rate: metrics.win_rate,
                            avg_return_pct: metrics.avg_return * 100.0,
                            max_drawdown_pct: metrics.max_drawdown * 100.0,
                            avg_bars_held: metrics.avg_bars_held as usize,
                        });

                        info!(
                            "New best: profit={}bps, stop={}bps, hold={:.1}h → Sharpe={:.2}, WR={:.1}%, score={:.4}",
                            profit_bps, stop_bps, holding_hours,
                            metrics.sharpe, metrics.win_rate * 100.0, score
                        );
                    }
                }
            }

            if idx % 5 == 0 {
                info!("Progress: {}/{} profit targets tested", idx, profit_targets.len());
            }
        }

        // Save full results to CSV
        self.save_results_csv(&all_results)?;

        best_params.context("No optimal parameters found (all simulations failed)")
    }

    /// Run Monte-Carlo simulations for a parameter set
    fn simulate(&self, config: &BarrierConfig) -> Result<SimulationMetrics> {
        let mut wins = 0;
        let mut losses = 0;
        let mut neutrals = 0;
        let mut returns = Vec::new();
        let mut bars_held = Vec::new();

        for _ in 0..self.n_simulations {
            // Generate synthetic price path using Geometric Brownian Motion
            let path_length = (config.max_holding_period_ns / 1e9 / 3600.0 * 24.0) as usize; // Approximate bars
            let path = self.generate_gbm_path(path_length.max(10));

            // Apply triple-barrier method
            let outcome = self.apply_barriers(&path, config);

            match outcome.result {
                BarrierResult::ProfitTarget => wins += 1,
                BarrierResult::StopLoss => losses += 1,
                BarrierResult::TimeExpiry => neutrals += 1,
            }

            returns.push(outcome.return_pct);
            bars_held.push(outcome.bars_held);
        }

        let total_trades = wins + losses + neutrals;
        let win_rate = if total_trades > 0 {
            wins as f64 / total_trades as f64
        } else {
            0.0
        };

        Ok(SimulationMetrics {
            sharpe: Self::compute_sharpe(&returns),
            win_rate,
            avg_return: returns.iter().sum::<f64>() / returns.len() as f64,
            max_drawdown: Self::compute_max_drawdown(&returns),
            avg_bars_held: bars_held.iter().sum::<usize>() as f64 / bars_held.len() as f64,
            trade_count: total_trades,
        })
    }

    /// Generate synthetic price path using Geometric Brownian Motion
    fn generate_gbm_path(&self, n_steps: usize) -> Vec<f64> {
        let mut rng = rand::thread_rng();
        let mut path = vec![self.historical_prices[0]]; // Start at first historical price

        let dt = 1.0 / 252.0 / 6.5; // Assume 1 step = 1 hour (6.5 hours/day, 252 days/year)
        let drift = 0.0; // Neutral drift for conservative estimation
        let diffusion = self.daily_volatility * dt.sqrt();

        for _ in 0..n_steps {
            let z: f64 = rng.sample(rand::distributions::StandardNormal);
            let new_price = path.last().unwrap() * ((drift - 0.5 * diffusion.powi(2)) * dt + diffusion * z).exp();
            path.push(new_price);
        }

        path
    }

    /// Apply triple-barrier method to a price path
    fn apply_barriers(&self, path: &[f64], config: &BarrierConfig) -> BarrierOutcome {
        let entry_price = path[0];
        let profit_level = entry_price * (1.0 + config.profit_target_bps as f64 / 10000.0);
        let stop_level = entry_price * (1.0 - config.stop_loss_bps as f64 / 10000.0);

        for (i, &price) in path.iter().enumerate().skip(1) {
            if price >= profit_level {
                return BarrierOutcome {
                    result: BarrierResult::ProfitTarget,
                    return_pct: config.profit_target_bps as f64 / 10000.0,
                    bars_held: i,
                };
            }
            if price <= stop_level {
                return BarrierOutcome {
                    result: BarrierResult::StopLoss,
                    return_pct: -(config.stop_loss_bps as f64 / 10000.0),
                    bars_held: i,
                };
            }
        }

        // Time expiry
        let final_price = *path.last().unwrap();
        let final_return = (final_price - entry_price) / entry_price;

        BarrierOutcome {
            result: BarrierResult::TimeExpiry,
            return_pct: final_return,
            bars_held: path.len() - 1,
        }
    }

    /// Compute objective score (multi-objective optimization)
    fn compute_score(&self, metrics: &SimulationMetrics) -> f64 {
        // Weighted scoring function optimized for HFT
        let sharpe_weight = 0.4;
        let win_rate_weight = 0.3;
        let drawdown_weight = 0.2;
        let return_vol_weight = 0.1;

        let sharpe_score = metrics.sharpe.max(0.0).min(3.0) / 3.0; // Normalize to [0,1]
        let win_rate_score = metrics.win_rate;
        let drawdown_score = (1.0 - metrics.max_drawdown).max(0.0).min(1.0);
        let return_vol_score = (metrics.avg_return / self.daily_volatility).max(-1.0).min(1.0) * 0.5 + 0.5;

        sharpe_weight * sharpe_score
            + win_rate_weight * win_rate_score
            + drawdown_weight * drawdown_score
            + return_vol_weight * return_vol_score
    }

    /// Compute annualized Sharpe ratio
    fn compute_sharpe(returns: &[f64]) -> f64 {
        if returns.is_empty() {
            return 0.0;
        }

        let mean = returns.iter().sum::<f64>() / returns.len() as f64;
        let variance = returns
            .iter()
            .map(|r| (r - mean).powi(2))
            .sum::<f64>()
            / returns.len() as f64;

        let std = variance.sqrt();

        if std > 1e-10 {
            mean / std * (252.0_f64).sqrt() // Annualized (252 trading days)
        } else {
            0.0
        }
    }

    /// Compute maximum drawdown
    fn compute_max_drawdown(returns: &[f64]) -> f64 {
        if returns.is_empty() {
            return 0.0;
        }

        let mut cumulative = 0.0;
        let mut peak = 0.0;
        let mut max_dd = 0.0;

        for &ret in returns {
            cumulative += ret;
            if cumulative > peak {
                peak = cumulative;
            }
            let drawdown = if peak > 1e-10 {
                (peak - cumulative) / peak
            } else {
                0.0
            };
            max_dd = max_dd.max(drawdown);
        }

        max_dd
    }

    /// Save grid search results to CSV
    fn save_results_csv(&self, results: &[(BarrierConfig, SimulationMetrics, f64)]) -> Result<()> {
        let filename = format!("ml/checkpoints/barrier_optimization_{}.csv", self.symbol);
        let mut file = File::create(&filename)?;

        // Write header
        writeln!(
            file,
            "profit_bps,stop_bps,holding_hours,sharpe,win_rate,avg_return,max_drawdown,avg_bars,score"
        )?;

        // Write data
        for (config, metrics, score) in results {
            writeln!(
                file,
                "{},{},{:.2},{:.3},{:.3},{:.4},{:.4},{:.1},{:.4}",
                config.profit_target_bps,
                config.stop_loss_bps,
                config.max_holding_period_ns as f64 / 3600.0 / 1e9,
                metrics.sharpe,
                metrics.win_rate,
                metrics.avg_return,
                metrics.max_drawdown,
                metrics.avg_bars_held,
                score
            )?;
        }

        info!("Saved results to {}", filename);
        Ok(())
    }
}

/// Outcome of applying triple-barrier to a price path
struct BarrierOutcome {
    result: BarrierResult,
    return_pct: f64,
    bars_held: usize,
}

#[tokio::main]
async fn main() -> Result<()> {
    tracing_subscriber::fmt::init();

    info!("=== Triple-Barrier Parameter Optimization ===");

    // Load historical ES.FUT data
    let data_dir = PathBuf::from("test_data/real/databento/ml_training_small");
    let mut file_mapping = HashMap::new();
    file_mapping.insert("ES.FUT".to_string(), data_dir.join("ESH5.dbn.zst"));

    let data_source = DbnDataSource::new(file_mapping)
        .await
        .context("Failed to create DBN data source")?;

    let bars = data_source
        .load_ohlcv_bars("ES.FUT")
        .await
        .context("Failed to load ES.FUT bars")?;

    info!("Loaded {} ES.FUT bars", bars.len());

    // Extract closing prices
    let prices: Vec<f64> = bars.iter().map(|bar| bar.close).collect();

    // Run optimization (1000 Monte-Carlo simulations per parameter set)
    let optimizer = BarrierOptimizer::new("ES.FUT".to_string(), prices, 1000);

    let optimal = optimizer.optimize()?;

    // Print results
    info!("\n=== OPTIMAL PARAMETERS FOR {} ===", optimal.symbol);
    info!("Profit Target:    {} bps ({:.2}%)", optimal.profit_target_bps, optimal.profit_target_bps as f64 / 100.0);
    info!("Stop Loss:        {} bps ({:.2}%)", optimal.stop_loss_bps, optimal.stop_loss_bps as f64 / 100.0);
    info!("Max Holding:      {:.1} hours", optimal.max_holding_hours);
    info!("\n=== PERFORMANCE METRICS ===");
    info!("Sharpe Ratio:     {:.2}", optimal.sharpe_ratio);
    info!("Win Rate:         {:.1}%", optimal.win_rate * 100.0);
    info!("Avg Return:       {:.2}%", optimal.avg_return_pct);
    info!("Max Drawdown:     {:.2}%", optimal.max_drawdown_pct);
    info!("Avg Bars Held:    {}", optimal.avg_bars_held);

    // Save optimal parameters to config file
    let config_content = format!(
        r#"# Optimal Triple-Barrier Parameters for {}
# Generated: {}

[barrier_config]
profit_target_bps = {}
stop_loss_bps = {}
max_holding_period_ns = {}  # {:.1} hours

# Performance Metrics (from {} Monte-Carlo simulations)
# Sharpe Ratio: {:.2}
# Win Rate: {:.1}%
# Avg Return: {:.2}%
# Max Drawdown: {:.2}%
"#,
        optimal.symbol,
        chrono::Utc::now().format("%Y-%m-%d %H:%M:%S UTC"),
        optimal.profit_target_bps,
        optimal.stop_loss_bps,
        (optimal.max_holding_hours * 3600.0 * 1e9) as u64,
        optimal.max_holding_hours,
        optimizer.n_simulations,
        optimal.sharpe_ratio,
        optimal.win_rate * 100.0,
        optimal.avg_return_pct,
        optimal.max_drawdown_pct,
    );

    let config_path = format!("ml/checkpoints/optimal_barriers_{}.toml", optimal.symbol);
    std::fs::write(&config_path, config_content)?;
    info!("\nSaved optimal config to {}", config_path);

    Ok(())
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_volatility_calculation() {
        let prices = vec![100.0, 101.0, 99.5, 102.0, 101.5];
        let vol = BarrierOptimizer::compute_daily_volatility(&prices);
        assert!(vol > 0.0);
        assert!(vol < 0.1); // Reasonable daily volatility
    }

    #[test]
    fn test_sharpe_calculation() {
        let returns = vec![0.01, -0.005, 0.02, 0.015, -0.01];
        let sharpe = BarrierOptimizer::compute_sharpe(&returns);
        assert!(sharpe.is_finite());
    }

    #[test]
    fn test_max_drawdown() {
        let returns = vec![0.1, 0.05, -0.2, -0.1, 0.15];
        let dd = BarrierOptimizer::compute_max_drawdown(&returns);
        assert!(dd >= 0.0);
        assert!(dd <= 1.0);
    }
}