epistasis-v2 1.0.0__tar.gz

epistasis_v2-1.0.0/Cargo.lock

@@ -0,0 +1,323 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "autocfg"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
+
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+
+[[package]]
+name = "crossbeam-deque"
+version = "0.8.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51"
+dependencies = [
+ "crossbeam-epoch",
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-epoch"
+version = "0.9.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
+dependencies = [
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-utils"
+version = "0.8.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
+
+[[package]]
+name = "either"
+version = "1.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
+
+[[package]]
+name = "epistasis-core"
+version = "0.1.0"
+dependencies = [
+ "ndarray",
+ "numpy",
+ "pyo3",
+ "rayon",
+]
+
+[[package]]
+name = "heck"
+version = "0.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea"
+
+[[package]]
+name = "indoc"
+version = "2.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "79cf5c93f93228cf8efb3ba362535fb11199ac548a09ce117c9b1adc3030d706"
+dependencies = [
+ "rustversion",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "52ff2c0fe9bc6cb6b14a0592c2ff4fa9ceb83eea9db979b0487cd054946a2b8f"
+
+[[package]]
+name = "matrixmultiply"
+version = "0.3.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a06de3016e9fae57a36fd14dba131fccf49f74b40b7fbdb472f96e361ec71a08"
+dependencies = [
+ "autocfg",
+ "rawpointer",
+]
+
+[[package]]
+name = "memoffset"
+version = "0.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "488016bfae457b036d996092f6cb448677611ce4449e970ceaf42695203f218a"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "ndarray"
+version = "0.16.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "882ed72dce9365842bf196bdeedf5055305f11fc8c03dee7bb0194a6cad34841"
+dependencies = [
+ "matrixmultiply",
+ "num-complex",
+ "num-integer",
+ "num-traits",
+ "portable-atomic",
+ "portable-atomic-util",
+ "rawpointer",
+ "rayon",
+]
+
+[[package]]
+name = "num-complex"
+version = "0.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73f88a1307638156682bada9d7604135552957b7818057dcef22705b4d509495"
+dependencies = [
+ "num-traits",
+]
+
+[[package]]
+name = "num-integer"
+version = "0.1.46"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7969661fd2958a5cb096e56c8e1ad0444ac2bbcd0061bd28660485a44879858f"
+dependencies = [
+ "num-traits",
+]
+
+[[package]]
+name = "num-traits"
+version = "0.2.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "numpy"
+version = "0.23.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b94caae805f998a07d33af06e6a3891e38556051b8045c615470a71590e13e78"
+dependencies = [
+ "libc",
+ "ndarray",
+ "num-complex",
+ "num-integer",
+ "num-traits",
+ "pyo3",
+ "rustc-hash",
+]
+
+[[package]]
+name = "once_cell"
+version = "1.21.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9f7c3e4beb33f85d45ae3e3a1792185706c8e16d043238c593331cc7cd313b50"
+
+[[package]]
+name = "portable-atomic"
+version = "1.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c33a9471896f1c69cecef8d20cbe2f7accd12527ce60845ff44c153bb2a21b49"
+
+[[package]]
+name = "portable-atomic-util"
+version = "0.2.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c2a106d1259c23fac8e543272398ae0e3c0b8d33c88ed73d0cc71b0f1d902618"
+dependencies = [
+ "portable-atomic",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "pyo3"
+version = "0.23.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7778bffd85cf38175ac1f545509665d0b9b92a198ca7941f131f85f7a4f9a872"
+dependencies = [
+ "cfg-if",
+ "indoc",
+ "libc",
+ "memoffset",
+ "once_cell",
+ "portable-atomic",
+ "pyo3-build-config",
+ "pyo3-ffi",
+ "pyo3-macros",
+ "unindent",
+]
+
+[[package]]
+name = "pyo3-build-config"
+version = "0.23.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94f6cbe86ef3bf18998d9df6e0f3fc1050a8c5efa409bf712e661a4366e010fb"
+dependencies = [
+ "once_cell",
+ "target-lexicon",
+]
+
+[[package]]
+name = "pyo3-ffi"
+version = "0.23.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e9f1b4c431c0bb1c8fb0a338709859eed0d030ff6daa34368d3b152a63dfdd8d"
+dependencies = [
+ "libc",
+ "pyo3-build-config",
+]
+
+[[package]]
+name = "pyo3-macros"
+version = "0.23.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fbc2201328f63c4710f68abdf653c89d8dbc2858b88c5d88b0ff38a75288a9da"
+dependencies = [
+ "proc-macro2",
+ "pyo3-macros-backend",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "pyo3-macros-backend"
+version = "0.23.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fca6726ad0f3da9c9de093d6f116a93c1a38e417ed73bf138472cf4064f72028"
+dependencies = [
+ "heck",
+ "proc-macro2",
+ "pyo3-build-config",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.45"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "rawpointer"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "60a357793950651c4ed0f3f52338f53b2f809f32d83a07f72909fa13e4c6c1e3"
+
+[[package]]
+name = "rayon"
+version = "1.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fb39b166781f92d482534ef4b4b1b2568f42613b53e5b6c160e24cfbfa30926d"
+dependencies = [
+ "either",
+ "rayon-core",
+]
+
+[[package]]
+name = "rayon-core"
+version = "1.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "22e18b0f0062d30d4230b2e85ff77fdfe4326feb054b9783a3460d8435c8ab91"
+dependencies = [
+ "crossbeam-deque",
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "rustc-hash"
+version = "2.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "94300abf3f1ae2e2b8ffb7b58043de3d399c73fa6f4b73826402a5c457614dbe"
+
+[[package]]
+name = "rustversion"
+version = "1.0.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b39cdef0fa800fc44525c84ccb54a029961a8215f9619753635a9c0d2538d46d"
+
+[[package]]
+name = "syn"
+version = "2.0.117"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "target-lexicon"
+version = "0.12.16"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "61c41af27dd6d1e27b1b16b489db798443478cef1f06a660c96db617ba5de3b1"
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.24"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
+
+[[package]]
+name = "unindent"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7264e107f553ccae879d21fbea1d6724ac785e8c3bfc762137959b5802826ef3"

epistasis_v2-1.0.0/Cargo.toml

@@ -0,0 +1,13 @@
+[workspace]
+members = ["crates/epistasis-core"]
+resolver = "2"
+
+[workspace.package]
+version = "0.1.0"
+edition = "2021"
+license = "Unlicense"
+repository = "https://github.com/lperezmo/epistasis-v2"
+
+[profile.release]
+lto = "thin"
+codegen-units = 1

epistasis_v2-1.0.0/PKG-INFO

@@ -0,0 +1,119 @@
+Metadata-Version: 2.4
+Name: epistasis-v2
+Version: 1.0.0
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Rust
+Classifier: License :: Public Domain
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Dist: numpy>=1.23
+Requires-Dist: pandas>=2.0
+Requires-Dist: scipy>=1.11
+Requires-Dist: scikit-learn>=1.3
+Requires-Dist: lmfit>=1.2
+Requires-Dist: emcee>=3.1
+Requires-Dist: matplotlib>=3.7
+Requires-Dist: gpmap-v2>=1.0.0
+Summary: High-performance Python library for fitting high-order epistatic interactions in genotype-phenotype maps.
+Keywords: epistasis,genotype-phenotype,genetics,genomics,bioinformatics
+Author-email: Luis Perez <lperezmo@users.noreply.github.com>
+License: Unlicense
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
+Project-URL: Homepage, https://github.com/lperezmo/epistasis-v2
+Project-URL: Issues, https://github.com/lperezmo/epistasis-v2/issues
+Project-URL: Repository, https://github.com/lperezmo/epistasis-v2
+
+# epistasis-v2
+
+High-performance Python library for fitting high-order epistatic interactions in genotype-phenotype maps. A clean-break rewrite of [harmslab/epistasis](https://github.com/harmslab/epistasis).
+
+**Status: alpha.** Phase 1 port complete; Phase 2 Rust kernel and Phase 3 FWHT / sparse paths still to come.
+
+## What changed from v1
+
+- Rust hot-path kernels via PyO3 (`epistasis._core`) instead of a shipped Cython `.c` blob.
+- `uv` + `maturin` build. `pyproject.toml` only; no `setup.py`.
+- Python 3.10 through 3.13. Older interpreters dropped.
+- Type hints on the public API; `mypy --strict` in CI.
+- Composition over `@use_sklearn` MRO injection. Concrete models hold an sklearn estimator as an attribute and forward calls explicitly, which unlocks modern sklearn (>=1.2) that broke the v1 trick when `normalize=` was removed.
+- Walsh-Hadamard fast-path for Hadamard-encoded OLS fits (Phase 3, not yet landed).
+- Sparse design matrix path for Lasso / ElasticNet at high order (Phase 3).
+- Coordinated rewrite of the [gpmap](https://github.com/harmslab/gpmap) dependency as [gpmap-v2](https://github.com/lperezmo/gpmap-v2). Consumes `binary_packed` (uint8 2D) and `encoding_table` with `site_index` instead of the deprecated `genotype_index`.
+- No backward compatibility with v1. Pin the v1 package if you need that behavior.
+
+## Repository layout
+
+```
+epistasis-v2/
+├── pyproject.toml          uv + maturin build, ruff + mypy + pytest config
+├── Cargo.toml              Rust workspace
+├── python/epistasis/       Python source (installed as `epistasis`)
+├── crates/epistasis-core/  Rust crate, exposed as `epistasis._core`
+├── tests/                  pytest suite
+├── benches/                pytest-benchmark + criterion (Phase 2+)
+├── docs/                   Sphinx docs (Phase 5)
+├── .github/workflows/      CI (lint, test, matrix) + release (semantic-release, maturin wheels, PyPI OIDC)
+├── CHANGELOG.md            generated by python-semantic-release
+└── CONTRIBUTING.md         commit conventions, dev workflow
+```
+
+## Installation (dev)
+
+Requires Python >= 3.10 and a Rust toolchain. `gpmap-v2` is pulled from PyPI.
+
+```bash
+uv sync
+uv run maturin develop --release
+uv run pytest
+```
+
+For lint and type-check:
+
+```bash
+uv run ruff check .
+uv run ruff format --check .
+uv run mypy python/epistasis
+```
+
+## Current progress
+
+Phase 0 (scaffold) and Phase 1 (port) complete.
+
+Ported modules:
+
+- `epistasis.mapping` (sites, coefficients, `EpistasisMap`)
+- `epistasis.matrix` (encoded vectors, design matrix, NumPy backend)
+- `epistasis.exceptions` (`EpistasisError`, `XMatrixError`, `FittingError`)
+- `epistasis.utils` (`genotypes_to_X`)
+- `epistasis.models.base` (`AbstractEpistasisModel`, `EpistasisBaseModel`)
+- `epistasis.models.linear` (`EpistasisLinearRegression` with analytic coefficient standard errors, `EpistasisRidge`, `EpistasisLasso`, `EpistasisElasticNet`)
+- `epistasis.models.nonlinear` (`EpistasisNonlinearRegression`, `FunctionMinimizer`; `power` and `spline` variants deferred)
+- `epistasis.models.classifiers` (`EpistasisLogisticRegression`; LDA, QDA, Gaussian Process, and GMM deferred)
+- `epistasis.simulate` (`simulate_linear_gpm`, `simulate_random_linear_gpm`)
+- `epistasis.stats` (Pearson, R^2, RMSD, SS residuals, AIC, `split_gpm`)
+- `epistasis.validate` (`k_fold`, `holdout`)
+- `epistasis.sampling.bayesian` (`BayesianSampler` via emcee 3)
+
+Pending:
+
+- Rust kernels for `build_model_matrix`, `encode_vectors`, FWHT fast path (Phase 2)
+- Sparse design matrix path for Lasso / ElasticNet (Phase 3)
+- `power.py` and `spline.py` nonlinear variants
+- Remaining classifier implementations if demand surfaces
+- ReadTheDocs build
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md). Commits follow [Conventional Commits](https://www.conventionalcommits.org/); releases and the changelog are automated by `python-semantic-release`.
+
+## License
+
+Unlicense (public domain). See [UNLICENSE](UNLICENSE).
+

epistasis_v2-1.0.0/README.md

@@ -0,0 +1,86 @@
+# epistasis-v2
+
+High-performance Python library for fitting high-order epistatic interactions in genotype-phenotype maps. A clean-break rewrite of [harmslab/epistasis](https://github.com/harmslab/epistasis).
+
+**Status: alpha.** Phase 1 port complete; Phase 2 Rust kernel and Phase 3 FWHT / sparse paths still to come.
+
+## What changed from v1
+
+- Rust hot-path kernels via PyO3 (`epistasis._core`) instead of a shipped Cython `.c` blob.
+- `uv` + `maturin` build. `pyproject.toml` only; no `setup.py`.
+- Python 3.10 through 3.13. Older interpreters dropped.
+- Type hints on the public API; `mypy --strict` in CI.
+- Composition over `@use_sklearn` MRO injection. Concrete models hold an sklearn estimator as an attribute and forward calls explicitly, which unlocks modern sklearn (>=1.2) that broke the v1 trick when `normalize=` was removed.
+- Walsh-Hadamard fast-path for Hadamard-encoded OLS fits (Phase 3, not yet landed).
+- Sparse design matrix path for Lasso / ElasticNet at high order (Phase 3).
+- Coordinated rewrite of the [gpmap](https://github.com/harmslab/gpmap) dependency as [gpmap-v2](https://github.com/lperezmo/gpmap-v2). Consumes `binary_packed` (uint8 2D) and `encoding_table` with `site_index` instead of the deprecated `genotype_index`.
+- No backward compatibility with v1. Pin the v1 package if you need that behavior.
+
+## Repository layout
+
+```
+epistasis-v2/
+├── pyproject.toml          uv + maturin build, ruff + mypy + pytest config
+├── Cargo.toml              Rust workspace
+├── python/epistasis/       Python source (installed as `epistasis`)
+├── crates/epistasis-core/  Rust crate, exposed as `epistasis._core`
+├── tests/                  pytest suite
+├── benches/                pytest-benchmark + criterion (Phase 2+)
+├── docs/                   Sphinx docs (Phase 5)
+├── .github/workflows/      CI (lint, test, matrix) + release (semantic-release, maturin wheels, PyPI OIDC)
+├── CHANGELOG.md            generated by python-semantic-release
+└── CONTRIBUTING.md         commit conventions, dev workflow
+```
+
+## Installation (dev)
+
+Requires Python >= 3.10 and a Rust toolchain. `gpmap-v2` is pulled from PyPI.
+
+```bash
+uv sync
+uv run maturin develop --release
+uv run pytest
+```
+
+For lint and type-check:
+
+```bash
+uv run ruff check .
+uv run ruff format --check .
+uv run mypy python/epistasis
+```
+
+## Current progress
+
+Phase 0 (scaffold) and Phase 1 (port) complete.
+
+Ported modules:
+
+- `epistasis.mapping` (sites, coefficients, `EpistasisMap`)
+- `epistasis.matrix` (encoded vectors, design matrix, NumPy backend)
+- `epistasis.exceptions` (`EpistasisError`, `XMatrixError`, `FittingError`)
+- `epistasis.utils` (`genotypes_to_X`)
+- `epistasis.models.base` (`AbstractEpistasisModel`, `EpistasisBaseModel`)
+- `epistasis.models.linear` (`EpistasisLinearRegression` with analytic coefficient standard errors, `EpistasisRidge`, `EpistasisLasso`, `EpistasisElasticNet`)
+- `epistasis.models.nonlinear` (`EpistasisNonlinearRegression`, `FunctionMinimizer`; `power` and `spline` variants deferred)
+- `epistasis.models.classifiers` (`EpistasisLogisticRegression`; LDA, QDA, Gaussian Process, and GMM deferred)
+- `epistasis.simulate` (`simulate_linear_gpm`, `simulate_random_linear_gpm`)
+- `epistasis.stats` (Pearson, R^2, RMSD, SS residuals, AIC, `split_gpm`)
+- `epistasis.validate` (`k_fold`, `holdout`)
+- `epistasis.sampling.bayesian` (`BayesianSampler` via emcee 3)
+
+Pending:
+
+- Rust kernels for `build_model_matrix`, `encode_vectors`, FWHT fast path (Phase 2)
+- Sparse design matrix path for Lasso / ElasticNet (Phase 3)
+- `power.py` and `spline.py` nonlinear variants
+- Remaining classifier implementations if demand surfaces
+- ReadTheDocs build
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md). Commits follow [Conventional Commits](https://www.conventionalcommits.org/); releases and the changelog are automated by `python-semantic-release`.
+
+## License
+
+Unlicense (public domain). See [UNLICENSE](UNLICENSE).

epistasis_v2-1.0.0/crates/epistasis-core/Cargo.toml

@@ -0,0 +1,16 @@
+[package]
+name = "epistasis-core"
+version.workspace = true
+edition.workspace = true
+license.workspace = true
+repository.workspace = true
+
+[lib]
+name = "epistasis_core"
+crate-type = ["cdylib"]
+
+[dependencies]
+pyo3 = { version = "0.23", features = ["extension-module", "abi3-py310"] }
+numpy = "0.23"
+ndarray = { version = "0.16", features = ["rayon"] }
+rayon = "1.10"

epistasis_v2-1.0.0/crates/epistasis-core/src/lib.rs

@@ -0,0 +1,20 @@
+//! epistasis-core: Rust hot-path kernels for epistasis-v2.
+//!
+//! This crate is exposed to Python as `epistasis._core` via PyO3.
+//! Phase 0 scaffold: no kernels implemented yet. Phase 2 adds
+//! `build_model_matrix`, `encode_vectors`, and the Walsh-Hadamard
+//! transform fast path.
+
+use pyo3::prelude::*;
+
+/// Returns the crate version. Smoke test for the Python-Rust bridge.
+#[pyfunction]
+fn version() -> &'static str {
+    env!("CARGO_PKG_VERSION")
+}
+
+#[pymodule]
+fn _core(m: &Bound<'_, PyModule>) -> PyResult<()> {
+    m.add_function(wrap_pyfunction!(version, m)?)?;
+    Ok(())
+}