scm2cpp-lasso 0.10.0__tar.gz → 0.12.0__tar.gz

{scm2cpp_lasso-0.10.0/src/scm2cpp_lasso.egg-info → scm2cpp_lasso-0.12.0}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: scm2cpp-lasso
-Version: 0.10.0
-Summary: scikit-learn estimators (lasso, elastic net, ridge, ARD, SVM, SVR, logistic regression, Huber, NMF, Gaussian mixture, FastICA, PCA, graphical lasso, RANSAC, SGD, OMP, LARS) translated from Scheme to C++ by scm2cpp; GPU batch solver included
+Version: 0.12.0
+Summary: scikit-learn estimators (lasso, elastic net, ridge, ARD, SVM, SVR, logistic regression, GLMs, Huber, Theil-Sen, F-score selection, RFE, NMF, Gaussian mixture, FastICA, PCA, graphical lasso, RANSAC, SGD, OMP, LARS) translated from Scheme to C++ by scm2cpp; GPU batch solver included
 Author: Hirotaka Niitsuma
 License: MIT
 Project-URL: Homepage, https://github.com/niitsuma/scm2cpp
@@ -690,6 +690,49 @@ L1LinearSVM(C=1.0).fit(X, y).coef_
 Speed, from the repository README's table: SGD 1.2-3x, ARD 1.6-1.9x
 (3x with the Gram hoisted), LassoLarsIC 8-20x, the L1 SVM 1.1-1.5x.
 
+## GLMs, CV and Theil-Sen: `LBFGSPoissonRegressor`, `LBFGSGammaRegressor`, `LBFGSTweedieRegressor`, `LBFGSLogisticRegressionCV`, `GramLarsCV`, `GramLassoLarsCV`, `GramOMPCV`, `WeiszfeldTheilSen`
+
+- The GLMs are `PoissonRegressor`, `GammaRegressor` and
+  `TweedieRegressor` (solver "lbfgs"), over the same L-BFGS-B as
+  `LBFGSLogisticRegression`.
+- The CV classes reproduce `LogisticRegressionCV`, `LarsCV`,
+  `LassoLarsCV` and `OrthogonalMatchingPursuitCV`: the same folds (KFold
+  / StratifiedKFold without shuffling), the same choice of C, alpha or
+  number of columns, and the same refit.
+- `WeiszfeldTheilSen` is `TheilSenRegressor` on scikit-learn's own
+  subsets.
+
+```python
+from scm2cpp_lasso import LBFGSPoissonRegressor, LBFGSLogisticRegressionCV, GramLassoLarsCV
+LBFGSPoissonRegressor(alpha=1e-3).fit(X, counts).predict(X_new)
+LBFGSLogisticRegressionCV().fit(X, labels).C_
+GramLassoLarsCV().fit(X, y).alpha_
+```
+
+Speed, from the repository README's table: the GLMs 1.1-6x, the CV
+estimators 1.6-6.6x, Theil-Sen 1.3-1.8x (its subset drawing dominates).
+
+## Feature selection: `f_regression`, `f_classif`, `SelectKBest`, `SelectPercentile`, `GramRFE`
+
+scikit-learn's univariate F statistics and its selectors over them,
+and `RFE` around `Ridge` / `LinearRegression`, translated.
+`f_regression` also takes an n x q array of targets: the q results in
+one product, on the device when one answers.
+
+```python
+from scm2cpp_lasso import SelectKBest, GramRFE, f_regression
+SelectKBest("f_regression", k=20).fit(X, y).get_support()
+GramRFE(alpha=1.0, n_features_to_select=10).fit(X, y).ranking_
+F, p = f_regression(X, Y)          # Y: n x q, every target at once
+```
+
+The same scores, ranking and features as scikit-learn. RFE is 80-1,000x
+faster (one Gram and one Cholesky factor, downdated, instead of a refit
+per round), and f_regression over many targets 30-50x. The Gram-route
+estimators (`GramLassoLarsIC`, `GramLarsCV`, `GramLassoLarsCV`,
+`GramLars`, `GramLassoLars`, `CovPCA`) form a large X'X on the device
+when one answers. `SCM2CPP_NO_DEVICE=1` keeps everything on the CPU.
+
 ## Logistic regression with L1
 
 `CovLogistic` solves L1-penalized logistic regression by

scm2cpp_lasso-0.10.0/PKG-INFO → scm2cpp_lasso-0.12.0/README.md

@@ -1,21 +1,3 @@
-Metadata-Version: 2.4
-Name: scm2cpp-lasso
-Version: 0.10.0
-Summary: scikit-learn estimators (lasso, elastic net, ridge, ARD, SVM, SVR, logistic regression, Huber, NMF, Gaussian mixture, FastICA, PCA, graphical lasso, RANSAC, SGD, OMP, LARS) translated from Scheme to C++ by scm2cpp; GPU batch solver included
-Author: Hirotaka Niitsuma
-License: MIT
-Project-URL: Homepage, https://github.com/niitsuma/scm2cpp
-Project-URL: Source, https://github.com/niitsuma/scm2cpp/tree/master/python/scm2cpp-lasso
-Keywords: lasso,elastic-net,ridge,svm,logistic-regression,coordinate-descent,cuda,compiler
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: C++
-Classifier: Topic :: Scientific/Engineering :: Mathematics
-Classifier: Intended Audience :: Science/Research
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-Requires-Dist: numpy>=1.17
-
 # scm2cpp-lasso
 
 *[Japanese (README.ja.md)](README.ja.md)*
@@ -690,6 +672,49 @@ L1LinearSVM(C=1.0).fit(X, y).coef_
 Speed, from the repository README's table: SGD 1.2-3x, ARD 1.6-1.9x
 (3x with the Gram hoisted), LassoLarsIC 8-20x, the L1 SVM 1.1-1.5x.
 
+## GLMs, CV and Theil-Sen: `LBFGSPoissonRegressor`, `LBFGSGammaRegressor`, `LBFGSTweedieRegressor`, `LBFGSLogisticRegressionCV`, `GramLarsCV`, `GramLassoLarsCV`, `GramOMPCV`, `WeiszfeldTheilSen`
+
+- The GLMs are `PoissonRegressor`, `GammaRegressor` and
+  `TweedieRegressor` (solver "lbfgs"), over the same L-BFGS-B as
+  `LBFGSLogisticRegression`.
+- The CV classes reproduce `LogisticRegressionCV`, `LarsCV`,
+  `LassoLarsCV` and `OrthogonalMatchingPursuitCV`: the same folds (KFold
+  / StratifiedKFold without shuffling), the same choice of C, alpha or
+  number of columns, and the same refit.
+- `WeiszfeldTheilSen` is `TheilSenRegressor` on scikit-learn's own
+  subsets.
+
+```python
+from scm2cpp_lasso import LBFGSPoissonRegressor, LBFGSLogisticRegressionCV, GramLassoLarsCV
+LBFGSPoissonRegressor(alpha=1e-3).fit(X, counts).predict(X_new)
+LBFGSLogisticRegressionCV().fit(X, labels).C_
+GramLassoLarsCV().fit(X, y).alpha_
+```
+
+Speed, from the repository README's table: the GLMs 1.1-6x, the CV
+estimators 1.6-6.6x, Theil-Sen 1.3-1.8x (its subset drawing dominates).
+
+## Feature selection: `f_regression`, `f_classif`, `SelectKBest`, `SelectPercentile`, `GramRFE`
+
+scikit-learn's univariate F statistics and its selectors over them,
+and `RFE` around `Ridge` / `LinearRegression`, translated.
+`f_regression` also takes an n x q array of targets: the q results in
+one product, on the device when one answers.
+
+```python
+from scm2cpp_lasso import SelectKBest, GramRFE, f_regression
+SelectKBest("f_regression", k=20).fit(X, y).get_support()
+GramRFE(alpha=1.0, n_features_to_select=10).fit(X, y).ranking_
+F, p = f_regression(X, Y)          # Y: n x q, every target at once
+```
+
+The same scores, ranking and features as scikit-learn. RFE is 80-1,000x
+faster (one Gram and one Cholesky factor, downdated, instead of a refit
+per round), and f_regression over many targets 30-50x. The Gram-route
+estimators (`GramLassoLarsIC`, `GramLarsCV`, `GramLassoLarsCV`,
+`GramLars`, `GramLassoLars`, `CovPCA`) form a large X'X on the device
+when one answers. `SCM2CPP_NO_DEVICE=1` keeps everything on the CPU.
+
 ## Logistic regression with L1
 
 `CovLogistic` solves L1-penalized logistic regression by

{scm2cpp_lasso-0.10.0 → scm2cpp_lasso-0.12.0}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "scm2cpp-lasso"
-version = "0.10.0"
-description = "scikit-learn estimators (lasso, elastic net, ridge, ARD, SVM, SVR, logistic regression, Huber, NMF, Gaussian mixture, FastICA, PCA, graphical lasso, RANSAC, SGD, OMP, LARS) translated from Scheme to C++ by scm2cpp; GPU batch solver included"
+version = "0.12.0"
+description = "scikit-learn estimators (lasso, elastic net, ridge, ARD, SVM, SVR, logistic regression, GLMs, Huber, Theil-Sen, F-score selection, RFE, NMF, Gaussian mixture, FastICA, PCA, graphical lasso, RANSAC, SGD, OMP, LARS) translated from Scheme to C++ by scm2cpp; GPU batch solver included"
 readme = "README.md"
 requires-python = ">=3.8"
 license = {text = "MIT"}
@@ -31,4 +31,4 @@ package-dir = {"" = "src"}
 where = ["src"]
 
 [tool.setuptools.package-data]
-scm2cpp_lasso = ["_generated/*.hpp", "_generated/*.cpp", "_generated/derived_*/*.hpp", "_generated/derived_*/*.cpp", "_generated/nmf_*/*.hpp", "_generated/nmf_*/*.cpp", "_generated/gramops_*/*.hpp", "_generated/gramops_*/*.cpp", "*.cu"]
+scm2cpp_lasso = ["_generated/*.hpp", "_generated/*.cpp", "_generated/derived_*/*.hpp", "_generated/derived_*/*.cpp", "_generated/nmf_*/*.hpp", "_generated/nmf_*/*.cpp", "_generated/gramops_*/*.hpp", "_generated/gramops_*/*.cpp", "_generated/accel_*/*.hpp", "_generated/accel_*/*.cpp", "*.cu"]

{scm2cpp_lasso-0.10.0 → scm2cpp_lasso-0.12.0}/setup.py

@@ -211,4 +211,13 @@ if _cuda is not None:
         extra_compile_args=CXXFLAGS + ["-O3", "-fstrict-overflow"],
     ))
 
+    extensions.append(Extension(
+        "scm2cpp_lasso._accel_cublas",
+        sources=[GEN_REL + "/accel_cublas/accel_capi.cpp"],
+        include_dirs=[GEN_REL + "/accel_cublas", GEN_REL, str(_cuda / "include")],
+        library_dirs=[str(_cuda / "lib64"), str(_cuda / "lib")],
+        libraries=["cublas", "cudart"],
+        extra_compile_args=CXXFLAGS + ["-O3", "-fstrict-overflow"],
+    ))
+
 setup(ext_modules=extensions, cmdclass={"build_ext": BuildWithCuda})