- Created data/examples/download_ml_training_data.rs using reqwest + Databento HTTP API - Downloaded 90 days × 4 symbols (ES.FUT, NQ.FUT, ZN.FUT, 6E.FUT) - Files saved to test_data/real/databento/ml_training/ - Total: 360 files, 15 MB compressed DBN format - Used existing Rust pattern from download_nq_fut.rs - API key loaded from .env file - 100% success rate (360/360 files) - Ready for ML training benchmarks Next: Create simplified training benchmark for RTX 3050 Ti GPU measurements
122 lines
4.8 KiB
Rust
122 lines
4.8 KiB
Rust
//! Validate CL.FUT DBN data file
|
|
//!
|
|
//! Inspects the downloaded CL.FUT data and reports statistics.
|
|
|
|
use std::fs::File;
|
|
use std::io::BufReader;
|
|
|
|
#[tokio::main]
|
|
async fn main() -> Result<(), Box<dyn std::error::Error>> {
|
|
println!("━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━");
|
|
println!(" CL.FUT Data Validation");
|
|
println!("━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━");
|
|
println!();
|
|
|
|
let file_path = "test_data/real/databento/CL.FUT_ohlcv-1m_2024-01-02.dbn";
|
|
|
|
println!("📂 File: {}", file_path);
|
|
|
|
// Check file exists and get size
|
|
let metadata = std::fs::metadata(file_path)?;
|
|
let size = metadata.len();
|
|
println!("📊 Size: {} bytes ({:.2} KB, {:.2} MB)", size, size as f64 / 1024.0, size as f64 / 1_048_576.0);
|
|
println!();
|
|
|
|
// Open file and create DBN decoder
|
|
let file = File::open(file_path)?;
|
|
let mut reader = BufReader::new(file);
|
|
|
|
// Read DBN metadata
|
|
let metadata = dbn::decode::MetadataDecoder::new(&mut reader)?.decode()?;
|
|
|
|
println!("📋 Metadata:");
|
|
println!(" Dataset: {}", metadata.dataset);
|
|
println!(" Schema: {}", metadata.schema);
|
|
println!(" Start: {}", metadata.start);
|
|
println!(" End: {}", metadata.end);
|
|
println!(" Symbols: {}", metadata.symbols.join(", "));
|
|
println!(" Stype In: {}", metadata.stype_in);
|
|
println!();
|
|
|
|
// Create record decoder
|
|
let mut decoder = dbn::decode::RecordDecoder::new(&mut reader, None, None, false)?;
|
|
|
|
let mut bar_count = 0;
|
|
let mut min_price = f64::MAX;
|
|
let mut max_price = f64::MIN;
|
|
let mut total_volume = 0.0;
|
|
|
|
// Read all records
|
|
while let Some(record) = decoder.decode_record::<dbn::OhlcvMsg>()? {
|
|
bar_count += 1;
|
|
|
|
// Track price range
|
|
let open = record.open as f64 / 1_000_000_000.0; // Convert from fixed point
|
|
let high = record.high as f64 / 1_000_000_000.0;
|
|
let low = record.low as f64 / 1_000_000_000.0;
|
|
let close = record.close as f64 / 1_000_000_000.0;
|
|
let volume = record.volume as f64;
|
|
|
|
if low < min_price { min_price = low; }
|
|
if high > max_price { max_price = high; }
|
|
total_volume += volume;
|
|
|
|
// Print first few bars for inspection
|
|
if bar_count <= 3 {
|
|
println!("📊 Bar {}: O={:.2} H={:.2} L={:.2} C={:.2} V={:.0}",
|
|
bar_count, open, high, low, close, volume);
|
|
}
|
|
}
|
|
|
|
println!();
|
|
println!("━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━");
|
|
println!(" Statistics:");
|
|
println!("━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━");
|
|
println!(" Total Bars: {}", bar_count);
|
|
println!(" Price Range: ${:.2} - ${:.2}", min_price, max_price);
|
|
println!(" Total Volume: {:.0}", total_volume);
|
|
println!(" Avg Volume: {:.0}", total_volume / bar_count as f64);
|
|
println!();
|
|
|
|
// Estimate cost
|
|
let size_gb = size as f64 / 1_073_741_824.0;
|
|
let cost_low = size_gb * 0.50;
|
|
let cost_high = size_gb * 2.00;
|
|
|
|
println!("💰 Cost Estimate:");
|
|
println!(" Size (GB): {:.10}", size_gb);
|
|
println!(" Estimated: ${:.6} - ${:.6}", cost_low, cost_high);
|
|
println!();
|
|
|
|
// Validate expectations
|
|
println!("✅ Validation:");
|
|
|
|
// CL.FUT typically has 390-400 bars per trading day (6.5 hours * 60 min)
|
|
let expected_bars = 390;
|
|
if bar_count >= expected_bars - 50 && bar_count <= expected_bars + 50 {
|
|
println!(" ✓ Bar count reasonable ({} bars, expected ~{})", bar_count, expected_bars);
|
|
} else {
|
|
println!(" ⚠ Bar count unexpected ({} bars, expected ~{})", bar_count, expected_bars);
|
|
}
|
|
|
|
// CL.FUT (Crude Oil) typically trades in $70-$85 range in Jan 2024
|
|
if min_price >= 60.0 && max_price <= 100.0 {
|
|
println!(" ✓ Price range reasonable (${:.2} - ${:.2})", min_price, max_price);
|
|
} else {
|
|
println!(" ⚠ Price range unexpected (${:.2} - ${:.2})", min_price, max_price);
|
|
}
|
|
|
|
if total_volume > 0.0 {
|
|
println!(" ✓ Volume data present");
|
|
} else {
|
|
println!(" ⚠ No volume data");
|
|
}
|
|
|
|
println!();
|
|
println!("━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━");
|
|
println!(" Validation Complete!");
|
|
println!("━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━");
|
|
|
|
Ok(())
|
|
}
|