jgrusewski
a5ea8713b6
feat(dqn): Branching DQN + KernelWeightPack + metrics propagation
...
Branching DQN (Tavakoli et al., 2018):
- 3 independent advantage heads (exposure=5, order=3, urgency=3) in CUDA kernel
- `use_branching` as hyperopt-tunable parameter (index 11 in 29D space)
- Branch weight pointers packed into KernelWeightPack struct
KernelWeightPack refactor:
- 87→38 CUDA kernel params by packing 48 weight pointers into 384-byte #[repr(C)] struct
- UNPACK_WEIGHT_PTRS macro in CUDA header for clean kernel-side access
- Single .arg(&weight_pack) replaces 48 individual .arg() calls
Hyperopt metrics in JSON output:
- Added `metrics: Option<serde_json::Value>` to TrialResult<P>
- `extract_metrics()` trait method with default None (DQN overrides)
- JSON output now includes per-trial backtest metrics (Sharpe, Sortino,
Calmar, Omega, drawdown, win_rate, trades) + top-level best_metrics
Prometheus backtest gauges (Rust-side, no CUDA):
- 8 new gauges: foxhunt_hyperopt_best_{sharpe,sortino,calmar,omega,
max_drawdown_pct,win_rate,total_trades,total_return_pct}
Dynamic episode scaling:
- Removed hardcoded 256 episode cap on small GPUs
- VRAM budget calculation in optimal_n_episodes() handles scaling naturally
- Removed stale .min(256) in PPO trainer
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-11 00:46:53 +01:00
jgrusewski
d06c99b0e1
fix(clippy): achieve zero warnings across entire workspace
...
- 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 >
2026-03-10 13:18:57 +01:00
jgrusewski
fca2495a73
fix(clippy): add doc backticks and const fn across ML crates
...
- Add backticks to type names in doc comments (doc_markdown)
- Mark eligible functions as const fn (missing_const_for_fn)
No behavior changes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-10 11:51:31 +01:00
jgrusewski
7ef92983f9
fix(clippy): apply cargo clippy --fix across workspace
...
Mechanical auto-fixes: redundant borrows, clone on Copy, or_insert_with,
single-char push_str, get(0) → first(), needless borrow, let_and_return.
150 files, no behavior changes.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-10 11:17:51 +01:00
jgrusewski
d313486dc2
refactor(ml): split monolith into 9 sub-crates + delete dead code
...
Extract 9 new sub-crates from the ml monolith to enable parallel
compilation across the workspace:
New crates (this commit):
- ml-features (282 tests): feature engineering, 21 modules
- ml-labeling (45 tests): triple barrier, meta-labeling, fractional diff
- ml-ensemble (116 tests): ensemble coordination, voting, confidence
- ml-hyperopt (47 tests): core PSO/TPE optimizer, parameter space
- ml-checkpoint (41 tests): checkpoint persistence, compression, signing
- ml-regime (68 tests): CUSUM, Bayesian changepoint, regime classification
- ml-data-validation (67 tests): FDR correction, CPCV, data quality
- ml-risk (33 tests): neural VaR, Kelly criterion, circuit breakers
- ml-validation (43 tests): statistical validation, walk-forward, DSR
Extended existing crates:
- ml-dqn: added evaluation/ (backtesting engine, metrics, reports)
and checkpoint implementation
- ml-supervised: added checkpoint implementations
- ml-core: added shared types needed by new sub-crates
Pattern: each module in ml/ becomes a thin facade (pub use subcrate::*)
with bridge modules staying in ml for cross-model adapter code.
Dead code deleted (~7K lines):
- 13 undeclared files in microstructure/ (never compiled)
- 7 undeclared files + tests/ in risk/ (never compiled)
- parquet_io, cache_service, cache_storage, minio_integration (unused)
- extraction_wave_d_impl.rs (bare fn outside impl block)
All 2,746 sub-crate tests + 951 ml tests pass.
Full workspace builds clean.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-08 15:17:22 +01:00
