foxhunt/ml/examples/validate_features_1_50.rs

//! Wave C Features 1-50 Validation Script (Agent F1)
//!
//! This script validates the first 50 features from the 256-feature extraction system:
//! - Features 0-4: OHLCV (open, high, low, close, volume)
//! - Features 5-14: Technical Indicators (RSI, EMA, MACD, Bollinger, ATR)
//! - Features 15-49: Price Patterns & Volume Analysis
//!
//! Expected behavior:
//! - Load real DBN data (ES.FUT)
//! - Extract features 0-49 from the 256-feature extraction system
//! - Validate no NaN/Inf values
//! - Measure extraction latency (<1ms per bar target)
//! - Report pass/fail status

use anyhow::{Context, Result};
use chrono::{TimeZone, Utc};
use dbn::decode::{DbnDecoder, DecodeRecordRef};
use dbn::OhlcvMsg;
use ml::features::extraction::OHLCVBar;
use std::time::Instant;

fn main() -> Result<()> {
    println!("=== Agent F1: Features 1-50 Validation Report ===\n");

    // Stage 1: Load real DBN data
    println!("### Stage 1: Loading DBN Data");
    let dbn_path = "/home/jgrusewski/Work/foxhunt/test_data/real/databento/ml_training/ES.FUT_ohlcv-1m_2024-03-25.dbn";

    println!("  - File: {}", dbn_path);

    let mut decoder = DbnDecoder::from_file(dbn_path)
        .with_context(|| format!("Failed to open DBN file: {}", dbn_path))?;

    // Decode OHLCV records
    let mut bars = Vec::new();
    let mut record_count = 0;

    while let Some(record_ref) = decoder
        .decode_record_ref()
        .context("Failed to decode DBN record")?
    {
        if let Some(ohlcv) = record_ref.get::<OhlcvMsg>() {
            record_count += 1;

            // Convert timestamp
            let ts_nanos = ohlcv.hd.ts_event as i64;
            let secs = ts_nanos / 1_000_000_000;
            let nanos = (ts_nanos % 1_000_000_000) as u32;
            let timestamp = Utc
                .timestamp_opt(secs, nanos)
                .single()
                .ok_or_else(|| anyhow::anyhow!("Invalid timestamp: {}", ts_nanos))?;

            // Convert prices (fixed-point to f64)
            let bar = OHLCVBar {
                timestamp,
                open: ohlcv.open as f64 / 1_000_000_000.0,
                high: ohlcv.high as f64 / 1_000_000_000.0,
                low: ohlcv.low as f64 / 1_000_000_000.0,
                close: ohlcv.close as f64 / 1_000_000_000.0,
                volume: ohlcv.volume as f64,
            };

            bars.push(bar);
        }
    }

    println!("  - Total records loaded: {}", record_count);
    println!("  - Total bars: {}\n", bars.len());

    if bars.len() < 50 {
        anyhow::bail!(
            "Insufficient data: {} bars (need at least 50 for warmup)",
            bars.len()
        );
    }

    // Stage 2: Feature Extraction Configuration
    println!("### Stage 2: Feature Extraction Setup");
    println!("  - System: 256-feature extraction (extraction.rs)");
    println!("  - Target features: 0-49 (first 50 features)");
    println!("  - Warmup period: 50 bars\n");

    // Stage 3: Extract features using the existing feature extraction system
    println!("### Stage 3: Feature Extraction");
    let start = Instant::now();
    let features = ml::features::extraction::extract_ml_features(&bars[..])?;
    let total_extraction_time = start.elapsed();

    println!("  - Total bars processed: {}", bars.len());
    println!("  - Feature vectors generated: {}", features.len());
    println!("  - Total extraction time: {:?}", total_extraction_time);

    if features.is_empty() {
        anyhow::bail!("No features extracted (warmup period too long?)");
    }

    // Calculate per-bar latency
    let avg_latency_per_bar = total_extraction_time.as_micros() as f64 / features.len() as f64;
    println!("  - Average latency per bar: {:.2}μs", avg_latency_per_bar);
    println!("  - Target: <1000μs (1ms) per bar");

    let latency_status = if avg_latency_per_bar < 1000.0 {
        "PASS ✓"
    } else {
        "FAIL ✗"
    };
    println!("  - Latency status: {}\n", latency_status);

    // Stage 4: Validation - Check features 0-49
    println!("### Stage 4: Feature Validation (Features 0-49)");

    let mut nan_count = 0;
    let mut inf_count = 0;
    let mut valid_count = 0;
    let mut feature_stats = vec![FeatureStats::default(); 50];

    for feature_vec in &features {
        for i in 0..50.min(feature_vec.len()) {
            let val = feature_vec[i];

            if val.is_nan() {
                nan_count += 1;
            } else if val.is_infinite() {
                inf_count += 1;
            } else {
                valid_count += 1;
                feature_stats[i].update(val);
            }
        }
    }

    let total_values = features.len() * 50;
    println!("  - Total values checked: {}", total_values);
    println!(
        "  - Valid values: {} ({:.2}%)",
        valid_count,
        valid_count as f64 / total_values as f64 * 100.0
    );
    println!(
        "  - NaN values: {} ({:.2}%)",
        nan_count,
        nan_count as f64 / total_values as f64 * 100.0
    );
    println!(
        "  - Inf values: {} ({:.2}%)",
        inf_count,
        inf_count as f64 / total_values as f64 * 100.0
    );

    let validation_status = if nan_count == 0 && inf_count == 0 {
        "PASS ✓"
    } else {
        "FAIL ✗"
    };
    println!("  - Validation status: {}\n", validation_status);

    // Stage 5: Feature Statistics
    println!("### Stage 5: Feature Statistics (First 10 Features)");
    println!("  Idx | Min         | Max         | Mean        | StdDev");
    println!("  ----|-------------|-------------|-------------|-------------");

    for i in 0..10.min(feature_stats.len()) {
        let stats = &feature_stats[i];
        println!(
            "  {:3} | {:11.6} | {:11.6} | {:11.6} | {:11.6}",
            i,
            stats.min,
            stats.max,
            stats.mean(),
            stats.stddev()
        );
    }
    println!();

    // Stage 6: Feature Names
    println!("### Features Validated (Indices 0-49)");
    println!("  - Features 0-4: OHLCV (open, high, low, close, volume)");
    println!("  - Features 5-14: Technical Indicators (RSI, EMA fast/slow, MACD, MACD signal, MACD histogram, BB middle/upper/lower, ATR)");
    println!("  - Features 15-74: Price Patterns (returns, MA ratios, high/low analysis, trend detection, support/resistance, etc.)");
    println!("  - Features 0-49 represent foundational features from the 256-feature extraction system\n");

    // Final Report
    println!("### Validation Results");
    println!("  - Total features tested: 50/50");
    let features_passing = if nan_count == 0 && inf_count == 0 {
        50
    } else {
        50 - ((nan_count + inf_count) / features.len()).min(50)
    };
    println!("  - Features passing: {}/50", features_passing);
    println!("  - Features with issues: {}/50", 50 - features_passing);
    println!();

    // Performance Metrics
    println!("### Performance Metrics");
    println!(
        "  - Average extraction latency: {:.2}μs per bar",
        avg_latency_per_bar
    );
    println!("  - Target: <1000μs (1ms) per bar");
    println!("  - Status: {}", latency_status);
    println!();

    // Issues Found (if any)
    if nan_count > 0 || inf_count > 0 {
        println!("### Issues Found");
        if nan_count > 0 {
            println!(
                "  1. NaN values detected: {} occurrences across {} feature vectors",
                nan_count,
                features.len()
            );
        }
        if inf_count > 0 {
            println!(
                "  2. Inf values detected: {} occurrences across {} feature vectors",
                inf_count,
                features.len()
            );
        }
        println!();
    }

    // Final Status
    println!("### Status");
    let final_status = if nan_count == 0 && inf_count == 0 && avg_latency_per_bar < 1000.0 {
        "COMPLETE ✓"
    } else if nan_count > 0 || inf_count > 0 {
        "BLOCKED - Invalid values detected ✗"
    } else {
        "PARTIAL - Latency target not met ⚠"
    };
    println!("  {}", final_status);

    Ok(())
}

#[derive(Debug, Clone, Default)]
struct FeatureStats {
    min: f64,
    max: f64,
    sum: f64,
    sum_sq: f64,
    count: usize,
}

impl FeatureStats {
    fn update(&mut self, val: f64) {
        if self.count == 0 {
            self.min = val;
            self.max = val;
        } else {
            self.min = self.min.min(val);
            self.max = self.max.max(val);
        }
        self.sum += val;
        self.sum_sq += val * val;
        self.count += 1;
    }

    fn mean(&self) -> f64 {
        if self.count == 0 {
            0.0
        } else {
            self.sum / self.count as f64
        }
    }

    fn stddev(&self) -> f64 {
        if self.count == 0 {
            0.0
        } else {
            let mean = self.mean();
            let variance = (self.sum_sq / self.count as f64) - (mean * mean);
            variance.max(0.0).sqrt()
        }
    }
}