e8a68ee39f
- 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
79 lines
2.4 KiB
JSON
79 lines
2.4 KiB
JSON
{
|
|
"source": "CryptoDataDownload",
|
|
"analysis_date": "2025-10-12 21:45:14",
|
|
"btc_usd": {
|
|
"download_url": "https://www.cryptodatadownload.com/cdd/Bitstamp_BTCUSD_2024_minute.csv",
|
|
"exchange": "Bitstamp",
|
|
"date_tested": "2025-10-12",
|
|
"date_range": "2024-01-01 00:00:00 to 2024-12-31 23:59:00",
|
|
"row_count": 509364,
|
|
"expected_rows": 527040,
|
|
"completeness_pct": 96.65,
|
|
"ohlcv_violations": 0,
|
|
"ohlcv_details": {
|
|
"high_low_violations": 0,
|
|
"negative_price_violations": 0,
|
|
"negative_volume_violations": 0
|
|
},
|
|
"outliers_count": 0,
|
|
"outliers_pct": 0.0,
|
|
"zero_volume_count": 17002,
|
|
"zero_volume_pct": 3.34,
|
|
"gaps_detected": 237,
|
|
"price_stats": {
|
|
"min_price": 38505.0,
|
|
"max_price": 108364.0,
|
|
"avg_price": 65864.742419959,
|
|
"median_price": 64208.0
|
|
},
|
|
"volume_stats": {
|
|
"total_volume": 782868.21542265,
|
|
"avg_volume": 1.5369523865499917,
|
|
"median_volume": 0.20804604,
|
|
"max_volume": 339.94147069,
|
|
"volume_column": "Volume BTC"
|
|
}
|
|
},
|
|
"eth_usd": {
|
|
"download_url": "https://www.cryptodatadownload.com/cdd/Bitstamp_ETHUSD_2024_minute.csv",
|
|
"exchange": "Bitstamp",
|
|
"date_tested": "2025-10-12",
|
|
"date_range": "2024-01-01 00:00:00 to 2024-12-31 23:59:00",
|
|
"row_count": 516678,
|
|
"expected_rows": 527040,
|
|
"completeness_pct": 98.03,
|
|
"ohlcv_violations": 0,
|
|
"ohlcv_details": {
|
|
"high_low_violations": 0,
|
|
"negative_price_violations": 0,
|
|
"negative_volume_violations": 0
|
|
},
|
|
"outliers_count": 0,
|
|
"outliers_pct": 0.0,
|
|
"zero_volume_count": 58191,
|
|
"zero_volume_pct": 11.26,
|
|
"gaps_detected": 216,
|
|
"price_stats": {
|
|
"min_price": 2101.0,
|
|
"max_price": 4108.4,
|
|
"avg_price": 3044.925190040993,
|
|
"median_price": 3089.6
|
|
},
|
|
"volume_stats": {
|
|
"total_volume": 2501771.49996842,
|
|
"avg_volume": 4.84203217471698,
|
|
"median_volume": 0.343518015,
|
|
"max_volume": 2272.74800954,
|
|
"volume_column": "Volume ETH"
|
|
}
|
|
},
|
|
"overall_quality_score": 8.0,
|
|
"recommendation": "VERY GOOD: Recommended for production use. Minor quality issues present but acceptable.",
|
|
"notes": [
|
|
"Data is in reverse chronological order (newest first)",
|
|
"Full year 2024 coverage (366 days - leap year)",
|
|
"Free access via direct CSV download",
|
|
"No API key required",
|
|
"Daily updates available"
|
|
]
|
|
} |