f1892a22d4
Wire MBP-10 order book data through ImbalanceBarSampler into the DQN training pipeline. No fallback — explicit data_source config: "mbp10" (imbalance bars from 10-level order book) or "ohlcv" (1-minute candles). Fails loudly if chosen source's data doesn't exist. Pipeline: MBP-10 .dbn.zst → trade extraction (action=='T', native side classification) → adaptive ImbalanceBarSampler (EWMA threshold) → OHLCVBar → existing feature extraction. Production: data_source="mbp10", smoketest/localdev: data_source="ohlcv". 8 files, +483/-48 lines. 3 new tests for trade extraction and pipeline. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
75 lines
3.0 KiB
Rust
75 lines
3.0 KiB
Rust
//! Feature Engineering for Foxhunt ML models
|
|
//!
|
|
//! Core feature extractors: technical indicators, price patterns, volume analysis,
|
|
//! microstructure proxies, OFI (Order Flow Imbalance), normalization, and more.
|
|
|
|
#![allow(clippy::module_name_repetitions)]
|
|
#![allow(clippy::integer_division)]
|
|
#![deny(
|
|
clippy::unwrap_used,
|
|
clippy::expect_used,
|
|
clippy::panic
|
|
)]
|
|
#![allow(clippy::shadow_reuse, clippy::shadow_same, clippy::shadow_unrelated)] // Tensor ops: let x = x.relu() is idiomatic
|
|
#![allow(clippy::non_ascii_literal)] // Math symbols in ML documentation and error messages
|
|
#![allow(clippy::partial_pub_fields)] // ML config structs: some fields are pub API, some internal
|
|
#![allow(clippy::same_name_method)] // Intentional: inherent methods shadow trait defaults for ML-specific behavior
|
|
#![allow(clippy::indexing_slicing)] // Tensor/matrix indexing with bounds guaranteed by construction
|
|
#![allow(clippy::similar_names)] // ML naming: min_val/max_val, state/states are conventional
|
|
|
|
// Re-export core types at crate root for internal use
|
|
pub use ml_core::MLError;
|
|
pub use ml_core::types::OHLCVBar;
|
|
|
|
// Public modules (21 total)
|
|
pub mod adx_features;
|
|
pub mod alternative_bars;
|
|
pub mod bar_resampler;
|
|
pub mod barrier_optimization;
|
|
pub mod config;
|
|
pub mod ewma;
|
|
pub mod feature_extraction;
|
|
pub mod mbp10_loader;
|
|
pub mod microstructure;
|
|
pub mod microstructure_features;
|
|
pub mod normalization;
|
|
pub mod ofi_calculator;
|
|
pub mod pipeline;
|
|
pub mod position_features;
|
|
pub mod price_features;
|
|
pub mod regime_adx;
|
|
pub mod statistical_features;
|
|
pub mod time_features;
|
|
pub mod trades_loader;
|
|
pub mod types;
|
|
pub mod volume_features;
|
|
|
|
// Re-exports
|
|
pub use config::{FeatureConfig, FeatureGroup, FeatureIndices, FeaturePhase};
|
|
pub use alternative_bars::{
|
|
DollarBarSampler, ImbalanceBarSampler, RunBarSampler, TickBarSampler, VolumeBarSampler,
|
|
};
|
|
pub use barrier_optimization::{BarrierOptimizer, BarrierParams, OptimizationResult};
|
|
pub use ewma::{AdaptiveThreshold, EWMACalculator};
|
|
pub use price_features::PriceFeatureExtractor;
|
|
pub use volume_features::VolumeFeatureExtractor;
|
|
pub use adx_features::AdxFeatureExtractor;
|
|
pub use regime_adx::RegimeADXFeatures;
|
|
pub use microstructure_features::{
|
|
BuySellImbalance, HighLowSpread, InterArrivalTime, KyleLambda, MicrostructureFeature,
|
|
PriceImpact, TickCount, VarianceRatio, VolumeWeightedSpread,
|
|
};
|
|
pub use time_features::TimeFeatureExtractor;
|
|
pub use statistical_features::StatisticalFeatureExtractor;
|
|
pub use normalization::{FeatureNormalizer, NormalizationStats, RingBuffer};
|
|
pub use pipeline::{FeatureExtractionPipeline, PipelinePerformance};
|
|
pub use position_features::PositionFeatures;
|
|
pub use ofi_calculator::{OFICalculator, OFIFeatures};
|
|
pub use mbp10_loader::{
|
|
extract_trades_from_dbn_file, extract_trades_from_snapshots, get_recent_snapshots,
|
|
get_snapshots_for_timestamp, load_mbp10_snapshots_sync, mbp10_to_imbalance_bars,
|
|
Mbp10Trade,
|
|
};
|
|
pub use trades_loader::{get_trades_for_bar, load_trades_sync, DbnTrade};
|
|
pub use bar_resampler::BarResampler;
|