d06c99b0e1
- Fix format_push_string: write!() instead of push_str(&format!()) (25 sites) - Fix str_to_string: .to_owned() instead of .to_string() on &str (6 sites) - Fix unseparated_literal_suffix: add _ separator (6 sites) - Fix multiple_inherent_impl: merge split impl blocks in TGGN, TFT, OFI (3) - Fix else_if_without_else: add exhaustive else clauses (3 sites) - Fix if_then_some_else_none: use .then().transpose() (1 site) - Fix unwrap_in_result: replace expect() with match + ? (2 sites) - Fix wildcard_enum_match_arm: enumerate Storage variants explicitly (2) - Fix decimal_literal_representation: use hex for power-of-2 constants (5) - Fix rc_buffer: Arc<Vec<T>> → Arc<[T]> for OFI features - Fix needless_range_loop: convert to iterator patterns (17 sites) - Fix used_underscore_binding: remove prefix on used vars (6 sites) - Fix doc list item indentation (7 sites) - Allow too_many_arguments on ML training functions (4) - Allow multiple_unsafe_ops_per_block on CUDA FFI functions (3) - Allow upper_case_acronyms on SLSTM/MLSTM model names (2) - Add ML-crate pedantic allows: shadow, similar_names, type_complexity, indexing_slicing, partial_pub_fields, non_ascii_literal, same_name_method (following existing ml-labeling/ml-universe pattern) Result: cargo clippy --workspace -- -D warnings passes with zero warnings. All 2758+ lib tests pass (2 pre-existing backtesting failures unchanged). Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
ml
10-model ML ensemble for the Foxhunt HFT system, built on Candle v0.9.1.
Models
- DQN (Rainbow) — deep Q-network with prioritized replay, dueling heads, noisy nets
- PPO — proximal policy optimization with GAE, LSTM policies, clip-higher
- TFT — temporal fusion transformer for multi-horizon forecasting
- Mamba2 — state space model for sequence prediction
- Liquid Networks — biologically inspired networks for non-stationary data
- TLOB — transformer-based limit order book analysis
- KAN — Kolmogorov-Arnold networks
- xLSTM — extended LSTM architecture
- TGGN — temporal graph neural network
- Diffusion — diffusion-based generative model
Key Modules
ensemble— model ensemble coordination and confidence aggregationhyperopt— PSO-based hyperparameter optimization with per-model adapterstrainers— unified training loops (DQN, PPO, supervised)inference—InferenceAdaptertrait for predictioncheckpoint— model checkpointing and restorationevaluation— walk-forward evaluation pipeline
Usage
use ml::dqn::DQN;
use ml::ppo::PpoTrainer;