sgtlearn 0.3.2__tar.gz → 0.4.0__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/ledger.jsonl +32 -0
- sgtlearn-0.4.0/.test-checker/reports/r-20261026-121217-e0ed.json +45 -0
- sgtlearn-0.4.0/.test-checker/reports/r-20261026-121217-e0ed.md +41 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/state.json +37 -17
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/PKG-INFO +48 -5
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/README.md +45 -4
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/ROADMAP.md +7 -1
- sgtlearn-0.4.0/docs/_static/export_graphviz_iris.svg +363 -0
- sgtlearn-0.4.0/docs/agents.md +119 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/api/estimators.rst +2 -2
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/api/index.rst +1 -0
- sgtlearn-0.4.0/docs/api/plotting.rst +72 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/api/tao.rst +21 -20
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/conf.py +13 -2
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/index.rst +2 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/installation.rst +10 -0
- sgtlearn-0.4.0/docs/llms.txt +22 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/quickstart.rst +10 -7
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/requirements.txt +1 -0
- sgtlearn-0.4.0/docs/research/2026-10-26-tuning-defaults.md +155 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/roadmap.rst +10 -1
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/tutorials/bivariate-branching.ipynb +16 -16
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/tutorials/categorical-features.ipynb +13 -13
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/tutorials/feature-importance.ipynb +29 -23
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/tutorials/forests.ipynb +18 -39
- sgtlearn-0.4.0/docs/tutorials/hyperparameter-tuning.ipynb +460 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/tutorials/inspecting-trees.ipynb +16 -16
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/tutorials/regression.ipynb +14 -14
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/tutorials/sgt-k.ipynb +12 -12
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/tutorials/shape-functions.ipynb +10 -10
- sgtlearn-0.4.0/docs/tutorials/structure-and-accuracy.ipynb +211 -0
- sgtlearn-0.4.0/docs/tutorials/tao.ipynb +212 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/pyproject.toml +2 -1
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/__init__.py +2 -1
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/_export.py +759 -48
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/base.py +96 -62
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/ensemble/_random_sgforest.py +11 -11
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/ensemble/random_sgforest_classifier.py +19 -17
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/ensemble/random_sgforest_regressor.py +24 -21
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/tao.py +28 -25
- sgtlearn-0.4.0/sgtlearn/tune.py +119 -0
- sgtlearn-0.4.0/tests/constants.py +28 -0
- sgtlearn-0.4.0/tests/regression/test_regressor_target_scaling_blind.py +170 -0
- sgtlearn-0.4.0/tests/regression/test_sgtlearn_base_py__sgtregressor_fit_1.py +287 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1.py +13 -12
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_branching_penalty.py +6 -5
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_coordinate_descent_initialization.py +26 -24
- sgtlearn-0.4.0/tests/test_export_text.py +504 -0
- sgtlearn-0.4.0/tests/test_inner_defaults.py +31 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_missing_values.py +14 -13
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_multioutput.py +6 -5
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_outer_growth_integration.py +49 -37
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_outer_leaf_budget.py +7 -6
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_outer_regularized_growth.py +19 -18
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_pair_screening.py +13 -8
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_pairwise_categorical_missing.py +14 -13
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_pairwise_classifier.py +24 -24
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_pairwise_regression.py +11 -10
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_plot_tree.py +19 -17
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_random_sgforest_pairwise.py +10 -8
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_random_sgforest_regressor_fidelity.py +1 -2
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_sgt_classifier_fidelity.py +5 -4
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_sgt_regressor_fidelity.py +8 -5
- sgtlearn-0.4.0/tests/test_suggested_params.py +42 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_tao.py +47 -46
- sgtlearn-0.4.0/tests/test_tao_target_memory.py +44 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_tree_export.py +15 -16
- sgtlearn-0.4.0/tests/test_tune.py +84 -0
- sgtlearn-0.4.0/tests/test_tuned_defaults.py +36 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_weighted_sample.py +17 -18
- sgtlearn-0.3.2/benchmarks/check_outer_growth.py +0 -23
- sgtlearn-0.3.2/benchmarks/compare_outer_growth.py +0 -155
- sgtlearn-0.3.2/benchmarks/outer_growth.md +0 -102
- sgtlearn-0.3.2/benchmarks/outer_growth.py +0 -261
- sgtlearn-0.3.2/benchmarks/outer_growth_manifest.json +0 -199
- sgtlearn-0.3.2/benchmarks/results/outer-growth-baseline/build-provenance.txt +0 -79
- sgtlearn-0.3.2/benchmarks/results/outer-growth-baseline/dependencies.txt +0 -28
- sgtlearn-0.3.2/benchmarks/results/outer-growth-baseline/manifest.json +0 -199
- sgtlearn-0.3.2/benchmarks/results/outer-growth-baseline/raw.jsonl +0 -99
- sgtlearn-0.3.2/benchmarks/results/outer-growth-baseline/runner.sha256 +0 -1
- sgtlearn-0.3.2/benchmarks/results/outer-growth-baseline/summary.json +0 -1154
- sgtlearn-0.3.2/benchmarks/results/outer-growth-baseline/summary.md +0 -25
- sgtlearn-0.3.2/benchmarks/results/outer-growth-branching-entropy/comparison.json +0 -391
- sgtlearn-0.3.2/benchmarks/results/outer-growth-branching-entropy/comparison.md +0 -19
- sgtlearn-0.3.2/benchmarks/results/outer-growth-branching-entropy/raw.jsonl +0 -22
- sgtlearn-0.3.2/benchmarks/results/outer-growth-branching-entropy/settings.json +0 -209
- sgtlearn-0.3.2/benchmarks/results/outer-growth-branching-mse/comparison.json +0 -415
- sgtlearn-0.3.2/benchmarks/results/outer-growth-branching-mse/comparison.md +0 -19
- sgtlearn-0.3.2/benchmarks/results/outer-growth-branching-mse/raw.jsonl +0 -22
- sgtlearn-0.3.2/benchmarks/results/outer-growth-branching-mse/settings.json +0 -209
- sgtlearn-0.3.2/benchmarks/results/outer-growth-candidate-build/README.md +0 -26
- sgtlearn-0.3.2/benchmarks/results/outer-growth-candidate-build/build-provenance.txt +0 -83
- sgtlearn-0.3.2/benchmarks/results/outer-growth-candidate-build/dependencies.txt +0 -28
- sgtlearn-0.3.2/benchmarks/results/outer-growth-candidate-build/imports.json +0 -49
- sgtlearn-0.3.2/benchmarks/results/outer-growth-comparison/comparison.json +0 -4511
- sgtlearn-0.3.2/benchmarks/results/outer-growth-comparison/comparison.md +0 -49
- sgtlearn-0.3.2/benchmarks/results/outer-growth-comparison/raw.jsonl +0 -198
- sgtlearn-0.3.2/benchmarks/results/outer-growth-comparison/settings.json +0 -209
- sgtlearn-0.3.2/benchmarks/results/outer-growth-confirmation/comparison.json +0 -2979
- sgtlearn-0.3.2/benchmarks/results/outer-growth-confirmation/comparison.md +0 -33
- sgtlearn-0.3.2/benchmarks/results/outer-growth-confirmation/raw.jsonl +0 -110
- sgtlearn-0.3.2/benchmarks/results/outer-growth-confirmation/settings.json +0 -209
- sgtlearn-0.3.2/benchmarks/results/outer-growth-final.md +0 -126
- sgtlearn-0.3.2/benchmarks/results/outer-growth-verification.md +0 -105
- sgtlearn-0.3.2/benchmarks/results/outer-growth-work-diagnostic/README.md +0 -23
- sgtlearn-0.3.2/benchmarks/results/outer-growth-work-diagnostic/baseline.json +0 -1
- sgtlearn-0.3.2/benchmarks/results/outer-growth-work-diagnostic/candidate.json +0 -1
- sgtlearn-0.3.2/benchmarks/results/outer-growth-work-diagnostic/diagnostic.py +0 -57
- sgtlearn-0.3.2/docs/api/plotting.rst +0 -38
- sgtlearn-0.3.2/docs/tutorials/structure-and-accuracy.ipynb +0 -211
- sgtlearn-0.3.2/docs/tutorials/tao.ipynb +0 -258
- sgtlearn-0.3.2/tests/constants.py +0 -6
- sgtlearn-0.3.2/tests/test_export_text.py +0 -247
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.github/workflows/workflow.yml +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.gitignore +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.readthedocs.yaml +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/.gitignore +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/config.yaml +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174204-9a7a.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174204-9a7a.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174205-8741.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174205-8741.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174205-c02e.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174205-c02e.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174205-e821.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174205-e821.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174206-2d1c.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174206-2d1c.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174206-60c6.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174206-60c6.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174206-b45b.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174206-b45b.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174207-4cd6.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174207-4cd6.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174207-4fb4.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174207-4fb4.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174207-df24.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174207-df24.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174208-9a71.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174208-9a71.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174208-c3ab.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174208-c3ab.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174208-e43a.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174208-e43a.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174209-3d96.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174209-3d96.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174209-ca73.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174209-ca73.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174209-eccd.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174209-eccd.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174210-6fd4.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174210-6fd4.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174210-d2ce.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174210-d2ce.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174211-09ec.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174211-09ec.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174211-4c33.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174211-4c33.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174211-6c74.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174211-6c74.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174212-2ed6.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174212-2ed6.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174212-5f6f.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174212-5f6f.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174212-94b7.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174212-94b7.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174212-b386.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174212-b386.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174213-901f.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174213-901f.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174213-a837.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174213-a837.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174213-be10.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174213-be10.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174213-be8b.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174213-be8b.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174214-2eae.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174214-2eae.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174214-5680.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174214-5680.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174214-efa1.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174214-efa1.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174215-1135.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174215-1135.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174215-8f39.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174215-8f39.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174215-fb3a.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174215-fb3a.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174216-3242.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174216-3242.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174216-4631.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174216-4631.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174216-6580.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174216-6580.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174216-d1d5.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174216-d1d5.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174217-42d3.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174217-42d3.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174217-8ed8.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174217-8ed8.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174217-b4af.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174217-b4af.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174217-ebae.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174217-ebae.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174218-6929.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174218-6929.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174218-a932.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174218-a932.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174219-2551.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174219-2551.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174219-2eeb.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174219-2eeb.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174219-52ce.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174219-52ce.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174219-e5d0.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174219-e5d0.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174220-2a9a.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174220-2a9a.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174220-55b8.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174220-55b8.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174220-6f2d.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174220-6f2d.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174220-8529.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174220-8529.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174221-94a6.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174221-94a6.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174221-b978.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174221-b978.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174222-02ee.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174222-02ee.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174222-8994.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174222-8994.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174222-935f.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20260928-174222-935f.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-150225-182c.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-150225-182c.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-155229-09d0.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-155229-09d0.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-160040-0a2c.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-160040-0a2c.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-162723-b8b5.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-162723-b8b5.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-215733-b7b8.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-215733-b7b8.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-215910-e7c6.json +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/.test-checker/reports/r-20261002-215910-e7c6.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/CONTEXT.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/LICENSE +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/assets/SGT_Viz.png +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/CMakeLists.txt +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/README.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/bindings/Discretizers.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/bindings/ShapeGeneralizedTrees.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/bindings/TreeAlternatingOptimization.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/bindings/_arma_bridge.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/bindings/_sgt_estimators.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/AbsoluteErrorBranchAssignment.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/AbsoluteErrorBranchAssignment.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/AbsoluteErrorBranchAssignmentBst.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/AbsoluteErrorBranchAssignmentBst.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/AbsoluteErrorBranchAssignmentCommon.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/AbsoluteErrorBranchAssignmentSort.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/AbsoluteErrorBranchAssignmentSort.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/BranchAssignment.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/BranchAssignmentFactory.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/BranchAssignmentFactory.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/BranchAssignmentVariants.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/LeafAggregateProcessor.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/LeafAggregationBranchAssignment.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/LeafAggregationBranchAssignment.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/BranchAssignmentObjectives/MaeBranchConfig.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Criterion.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Criterion.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/ClassificationDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/DiscretizerInputKind.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/InnerDiscretizerBase.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/RegressionDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/categorical/CategoricalClassificationDiscretizer.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/categorical/CategoricalClassificationDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/categorical/CategoricalDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/categorical/CategoricalDiscretizer.tpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/categorical/CategoricalRegressionDiscretizer.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/categorical/CategoricalRegressionDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/factories/DiscretizerFactories.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/factories/DiscretizerFactories.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/pair/PairClassificationDiscretizer.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/pair/PairClassificationDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/pair/PairRegressionDiscretizer.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/pair/PairRegressionDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/univariate/GainHessianUnivariateDiscretizer.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/univariate/GainHessianUnivariateDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/univariate/NumericFallbackDiscretizer.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/univariate/NumericFallbackDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/univariate/UnivariateClassificationDiscretizer.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/univariate/UnivariateClassificationDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/univariate/UnivariateDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/univariate/UnivariateDiscretizer.tpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/univariate/UnivariateRegressionDiscretizer.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Discretizers/univariate/UnivariateRegressionDiscretizer.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Domain/CategoricalSplitCandidate.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Domain/FeatureInfo.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Domain/LearningCriterion.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Domain/LearningFactories.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Domain/UnivariateSplitCandidate.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/ClassificationShapeGeneralizedTree.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/ClassificationShapeGeneralizedTree.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/RegressionShapeGeneralizedTree.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/RegressionShapeGeneralizedTree.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/ShapeFunctions/NanPartitionRouting.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/ShapeFunctions/ShapeFunctionNode.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/ShapeFunctions/ShapeFunctionNode.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/ShapeFunctions/ShapeFunctionSplitSearch.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/ShapeFunctions/ShapeFunctionSplitSearch.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/ShapeGeneralizedTree.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Estimators/ShapeGeneralizedTree.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/categorical/CategoricalClassificationSplitter.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/categorical/CategoricalClassificationSplitter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/categorical/CategoricalRegressionSplitter.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/categorical/CategoricalRegressionSplitter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/categorical/CategoricalSplitter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/categorical/CategoricalSplitter.tpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/factories/SplitterFactory.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/factories/SplitterFactory.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/AbsoluteErrorSplitter.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/AbsoluteErrorSplitter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/ClassificationSplitter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/EntropySplitter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/GainHessianSplitter.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/GainHessianSplitter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/GiniSplitter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/Splitter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/Splitter.tpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/SquaredErrorSplitter.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/Splitters/univariate/SquaredErrorSplitter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/BinPartitionAssignments.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/CoordinateDescent.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/FeatureBagging.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/KMeansUtils.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/OuterTreeBuilder.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/ShapeBranchingTypes.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/ShapeGeneralizedTreeParams.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/ClassificationTaoAdapter.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/ClassificationTaoAdapter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/RegressionTaoAdapter.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/RegressionTaoAdapter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/ShapeGeneralizedTaoAdapter.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/ShapeGeneralizedTaoAdapter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/TaoAdapter.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/TaoObjective.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/TaoObjective.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/TreeAlternatingOptimization.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TAO/TreeAlternatingOptimization.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TreeBuilder.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/TreeBuilder.tpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/WaveletTreeMAE.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/WaveletTreeMAE.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/WeightedMAETree.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/WeightedMAETree.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/frontiers.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/src/algorithms/missing_values.h +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/tests/bench_mae_branch_assignment.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/tests/test_branch_assignment.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/tests/test_shape_assignment_search.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/tests/test_splitters.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/tests/test_tao_objective.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/tests/test_wavelet_tree_mae.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/cpp/tests/test_weighted_mae_tree.cpp +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/Makefile +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/_static/.gitkeep +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/_templates/.gitkeep +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/adr/0001-regularized-outer-tree-growth.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/api/datasets.rst +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/api/ensemble.rst +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/make.bat +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/research/2026-09-09-coordinate-descent-bugfixes.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/docs/specs/regularized-outer-tree-growth.md +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/example.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/examples/plot_tree_demo.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/setup.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/_features.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/_multioutput.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/_weights.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/datasets.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/ensemble/__init__.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/sgtlearn/py.typed +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/__init__.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/discretizer_grid.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_base_py__as_native_y_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_base_py__configure_processed_features_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_base_py__normalize_tree_export_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_base_py__sgtclassifier_fit_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_base_py__sgtregressor_fit_2.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_base_py__sgtregressor_fit_4.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_base_py__sgtregressor_fit_5.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_base_py__validate_tao_pair_scale_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_base_py__warn_if_mae_cd_disabled_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_ensemble_random_sgforest_py__randomsgforest_fit_2.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_ensemble_random_sgforest_py__randomsgforest_fit_3.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_ensemble_random_sgforest_py__randomsgforest_mean_feature_importances_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_ensemble_random_sgforest_py__randomsgforest_std_feature_importance_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_export_py__draw_leaf_text_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_features_py__feature_dict_to_features_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_features_py__resolve_column_index_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_tao_py__prepare_tao_arrays_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_tao_py__tao_targets_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_tao_py__validate_x_y_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_weights_py__per_class_multiplier_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/regression/test_sgtlearn_weights_py__validate_sample_weight_array_1.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_categorical_classification_discretizer.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_categorical_regression_discretizer.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_datasets.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_features.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_mae_regression_stress.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_mae_warning.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_max_features_float.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_outer_penalty_validation.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_plot_helpers.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_predict_proba.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_random_sgforest_classifier_fidelity.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_random_sgforest_validation.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_refit_validation.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_univariate_classification_discretizer.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tests/test_univariate_regression_discretizer.py +0 -0
- {sgtlearn-0.3.2 → sgtlearn-0.4.0}/tree.png +0 -0
|
@@ -2110,3 +2110,35 @@
|
|
|
2110
2110
|
{"ts":"2026-10-03T02:02:11.890Z","run":"r-20261002-215733-b7b8","type":"classified","exec":1,"counts":{"sgtlearn-export-py--draw-leaf-text":{"effective":9,"neutral":30}},"queued":0}
|
|
2111
2111
|
{"ts":"2026-10-03T02:02:15.743Z","run":"r-20261002-215733-b7b8","type":"run_reported","likely_bugs":0,"needs_decision":0}
|
|
2112
2112
|
{"ts":"2026-10-03T02:02:15.813Z","run":"r-20261002-215733-b7b8","type":"promoted","files":["tests/regression/test_sgtlearn_export_py__draw_leaf_text_1.py"],"verified":["sgtlearn/_export.py"]}
|
|
2113
|
+
{"ts":"2026-10-26T16:12:17.685Z","run":"r-20261026-121217-e0ed","type":"run_started","mode":"new","revisions":{"current":"f16fb3709b04d4d5ac6560a1b67b3fe4337a7748"},"given":{"current":"WORKTREE"}}
|
|
2114
|
+
{"ts":"2026-10-26T16:12:26.352Z","run":"r-20261026-121217-e0ed","type":"target_added","target":"sgtlearn-base-py--sgtregressor-fit","file":"sgtlearn/base.py","symbol":"SGTRegressor.fit","lines":[962,1096],"rev":"current","body_sha":"f70b9923f778d1be464d82ba7d7e2f7b9b9d4f12d3b5e3ccaa335d617dc0808c"}
|
|
2115
|
+
{"ts":"2026-10-26T16:14:58.194Z","run":"r-20261026-121217-e0ed","type":"payload_emitted","payload":"p-19455e14","role":"spec","sha256":"62a2a9ad44e3368c1d9282bc35848d3b8572d32a404380a73d0f75fa3917abd5","target":"sgtlearn-base-py--sgtregressor-fit"}
|
|
2116
|
+
{"ts":"2026-10-26T16:15:43.568Z","run":"r-20261026-121217-e0ed","type":"spec_saved","target":"sgtlearn-base-py--sgtregressor-fit","shingle_ratio":0}
|
|
2117
|
+
{"ts":"2026-10-26T16:15:43.626Z","run":"r-20261026-121217-e0ed","type":"bundle_frozen","target":"sgtlearn-base-py--sgtregressor-fit","bundle":"b-e0ed-sgtlearn-base-py--sgtregressor-fit"}
|
|
2118
|
+
{"ts":"2026-10-26T16:15:56.764Z","run":"r-20261026-121217-e0ed","type":"context_set","target":"sgtlearn-base-py--sgtregressor-fit","shingle_ratio":0}
|
|
2119
|
+
{"ts":"2026-10-26T16:15:56.820Z","run":"r-20261026-121217-e0ed","type":"bundle_frozen","target":"sgtlearn-base-py--sgtregressor-fit","bundle":"b-e0ed-sgtlearn-base-py--sgtregressor-fit"}
|
|
2120
|
+
{"ts":"2026-10-26T16:16:13.346Z","run":"r-20261026-121217-e0ed","type":"payload_emitted","payload":"p-41645201","role":"writer","sha256":"5d8d71367a0be4589e375905e919ee695c5c83dd8b42c5a7e726316d2756e65a","target":"sgtlearn-base-py--sgtregressor-fit"}
|
|
2121
|
+
{"ts":"2026-10-26T16:19:40.511Z","run":"r-20261026-121217-e0ed","type":"payload_emitted","payload":"p-9c5960e5","role":"writer","sha256":"5d8d71367a0be4589e375905e919ee695c5c83dd8b42c5a7e726316d2756e65a","target":"sgtlearn-base-py--sgtregressor-fit"}
|
|
2122
|
+
{"ts":"2026-10-26T16:20:34.937Z","run":"r-20261026-121217-e0ed","type":"payload_emitted","payload":"p-490a0e5c","role":"writer","sha256":"5d8d71367a0be4589e375905e919ee695c5c83dd8b42c5a7e726316d2756e65a","target":"sgtlearn-base-py--sgtregressor-fit"}
|
|
2123
|
+
{"ts":"2026-10-26T16:21:48.846Z","run":"r-20261026-121217-e0ed","type":"payload_emitted","payload":"p-9a806b4d","role":"writer","sha256":"5d8d71367a0be4589e375905e919ee695c5c83dd8b42c5a7e726316d2756e65a","target":"sgtlearn-base-py--sgtregressor-fit"}
|
|
2124
|
+
{"ts":"2026-10-26T16:28:08.864Z","run":"r-20261026-121217-e0ed","type":"payload_emitted","payload":"p-24a6ab19","role":"writer","sha256":"5d8d71367a0be4589e375905e919ee695c5c83dd8b42c5a7e726316d2756e65a","target":"sgtlearn-base-py--sgtregressor-fit"}
|
|
2125
|
+
{"ts":"2026-10-26T16:29:57.918Z","run":"r-20261026-121217-e0ed","type":"tests_submitted","target":"sgtlearn-base-py--sgtregressor-fit","round":0,"role":"writer","payload":"p-24a6ab19","files":["test_sgtlearn_base_py__sgtregressor_fit_1.py","test_sgtlearn_base_py__sgtregressor_fit_2.py"]}
|
|
2126
|
+
{"ts":"2026-10-26T16:31:12.407Z","run":"r-20261026-123112-9785","type":"run_started","mode":"new","revisions":{"current":"344a22b1d43387ff75f5f89512a46cbc67715a35"},"given":{"current":"WORKTREE"}}
|
|
2127
|
+
{"ts":"2026-10-26T16:31:23.923Z","run":"r-20261026-123112-9785","type":"target_added","target":"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y","file":"sgtlearn/ensemble/random_sgforest_regressor.py","symbol":"RandomSGForestRegressor._check_X_y","lines":[191,208],"rev":"current","body_sha":"3847375562a4ede466b27936d7d429b48c96c85fd2d85b06e6d655808a1913e3"}
|
|
2128
|
+
{"ts":"2026-10-26T16:31:23.984Z","run":"r-20261026-123112-9785","type":"payload_emitted","payload":"p-874ae3a3","role":"spec","sha256":"382f418389d316b60fa5e487eee8d38ac2544d614cf5ad049ba0f01410e2937e","target":"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y"}
|
|
2129
|
+
{"ts":"2026-10-26T16:31:33.268Z","run":"r-20261026-121217-e0ed","type":"exec_completed","exec":1,"labels":{"current":{"pass":68,"load_errors":0}}}
|
|
2130
|
+
{"ts":"2026-10-26T16:32:53.686Z","run":"r-20261026-121217-e0ed","type":"classified","exec":1,"counts":{"sgtlearn-base-py--sgtregressor-fit":{"accepted":68}},"queued":0}
|
|
2131
|
+
{"ts":"2026-10-26T16:32:53.800Z","run":"r-20261026-121217-e0ed","type":"run_reported","likely_bugs":0,"needs_decision":0}
|
|
2132
|
+
{"ts":"2026-10-26T16:33:27.401Z","type":"hook_blocked","event":"protect-tests","reason":"tests/regression/test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1.py is verified test(s) test_x_out_is_c_contiguous_float32_with_same_shape, test_x_out_values_match_input, test_fortran_ordered_x_becomes_c_contiguous, test_list_inputs_are_accepted_as_array_like, test_nan_in_x_is_preserved, test_one_dimensional_y_stays_one_dimensional_float32, test_column_vector_y_stays_two_dimensional, test_multi_output_y_keeps_its_shape, test_integer_y_is_converted_to_float32, test_none_sample_weight_returns_none, test_sample_weight_is_returned_as_c_contiguous_float32, test_sample_weight_with_single_positive_value_is_accepted, test_single_sample_is_valid_input, test_values_at_float32_max_are_accepted, test_check_x_y_does_not_set_attributes_on_unfitted_estimator, test_check_x_y_does_not_set_attributes_on_fitted_estimator, test_check_x_y_does_not_set_attributes_when_raising, test_failed_refit_leaves_previous_forest_unchanged, test_fit_rejects_overflowing_row_even_if_bootstrap_would_skip_it, test_sparse_x_is_rejected, test_one_dimensional_x_is_rejected, test_three_dimensional_x_is_rejected, test_positive_infinity_in_x_is_rejected, test_negative_infinity_in_x_is_rejected, test_infinity_in_x_alongside_nan_is_rejected, test_positive_float32_overflow_in_x_is_rejected_naming_float32, test_negative_float32_overflow_in_x_is_rejected_naming_float32, test_fewer_targets_than_samples_is_rejected, test_more_targets_than_samples_is_rejected, test_two_dimensional_y_with_mismatched_rows_is_rejected, test_zero_samples_is_rejected, test_three_dimensional_y_is_rejected, test_non_numeric_y_is_rejected, test_nan_in_y_is_rejected, test_nan_in_two_dimensional_y_is_rejected, test_positive_infinity_in_y_is_rejected, test_negative_infinity_in_y_is_rejected, test_float32_overflow_in_y_is_rejected_naming_float32_and_y, test_negative_float32_overflow_in_y_is_rejected_naming_float32_and_y, test_sample_weight_too_short_is_rejected, test_sample_weight_too_long_is_rejected, test_two_dimensional_sample_weight_is_rejected, test_nan_sample_weight_is_rejected, test_infinite_sample_weight_is_rejected, test_negative_sample_weight_is_rejected, test_all_zero_sample_weight_is_rejected, test_float32_overflow_in_sample_weight_is_rejected. Don't edit tests to make them pass: send the failing test to adjudication (`tcheck adjudicate prompt <run> <test>`), or ask the user. A test-wrong verdict or `tcheck adjudicate override` unlocks it."}
|
|
2133
|
+
{"ts":"2026-10-26T17:01:04.359Z","run":"r-20261026-123112-9785","type":"override","test":"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y::tests.tcheck.test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1::test_list_inputs_are_accepted_as_array_like","verdict":"test-wrong","reason":"User explicitly authorized normal tests and updates to assertions affected by target scaling. Preserve float64 target precision before per-tree scaling; float32 target assertions describe the previous contract."}
|
|
2134
|
+
{"ts":"2026-10-26T17:01:04.625Z","run":"r-20261026-123112-9785","type":"override","test":"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y::tests.tcheck.test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1::test_one_dimensional_y_stays_one_dimensional_float32","verdict":"test-wrong","reason":"User explicitly authorized normal tests and updates to assertions affected by target scaling. Preserve float64 target precision before per-tree scaling; float32 target assertions describe the previous contract."}
|
|
2135
|
+
{"ts":"2026-10-26T17:01:04.771Z","run":"r-20261026-123112-9785","type":"override","test":"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y::tests.tcheck.test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1::test_column_vector_y_stays_two_dimensional","verdict":"test-wrong","reason":"User explicitly authorized normal tests and updates to assertions affected by target scaling. Preserve float64 target precision before per-tree scaling; float32 target assertions describe the previous contract."}
|
|
2136
|
+
{"ts":"2026-10-26T17:01:04.918Z","run":"r-20261026-123112-9785","type":"override","test":"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y::tests.tcheck.test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1::test_multi_output_y_keeps_its_shape","verdict":"test-wrong","reason":"User explicitly authorized normal tests and updates to assertions affected by target scaling. Preserve float64 target precision before per-tree scaling; float32 target assertions describe the previous contract."}
|
|
2137
|
+
{"ts":"2026-10-26T17:01:05.055Z","run":"r-20261026-123112-9785","type":"override","test":"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y::tests.tcheck.test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1::test_integer_y_is_converted_to_float32","verdict":"test-wrong","reason":"User explicitly authorized normal tests and updates to assertions affected by target scaling. Preserve float64 target precision before per-tree scaling; float32 target assertions describe the previous contract."}
|
|
2138
|
+
{"ts":"2026-10-27T00:14:56.158Z","type":"waived","files":["sgtlearn/base.py"],"reason":"User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."}
|
|
2139
|
+
{"ts":"2026-10-27T00:14:56.317Z","type":"waived","files":["sgtlearn/tao.py"],"reason":"User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."}
|
|
2140
|
+
{"ts":"2026-10-27T00:14:56.460Z","type":"waived","files":["sgtlearn/_export.py"],"reason":"User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."}
|
|
2141
|
+
{"ts":"2026-10-27T00:14:56.601Z","type":"waived","files":["sgtlearn/ensemble/_random_sgforest.py"],"reason":"User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."}
|
|
2142
|
+
{"ts":"2026-10-27T00:14:56.742Z","type":"waived","files":["sgtlearn/ensemble/random_sgforest_classifier.py"],"reason":"User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."}
|
|
2143
|
+
{"ts":"2026-10-27T00:14:56.876Z","type":"waived","files":["sgtlearn/ensemble/random_sgforest_regressor.py"],"reason":"User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."}
|
|
2144
|
+
{"ts":"2026-10-27T00:14:57.020Z","type":"waived","files":["sgtlearn/tune.py"],"reason":"User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."}
|
|
@@ -0,0 +1,45 @@
|
|
|
1
|
+
{
|
|
2
|
+
"run": "r-20261026-121217-e0ed",
|
|
3
|
+
"mode": "new",
|
|
4
|
+
"revisions": {
|
|
5
|
+
"current": {
|
|
6
|
+
"given": "WORKTREE",
|
|
7
|
+
"commit": "f16fb3709b04d4d5ac6560a1b67b3fe4337a7748"
|
|
8
|
+
}
|
|
9
|
+
},
|
|
10
|
+
"date": "2026-10-26T16:32:53.799Z",
|
|
11
|
+
"harness": "codex",
|
|
12
|
+
"blind_isolation": "medium",
|
|
13
|
+
"summary": [
|
|
14
|
+
{
|
|
15
|
+
"target": "sgtlearn-base-py--sgtregressor-fit",
|
|
16
|
+
"accepted": 68,
|
|
17
|
+
"disputed": 0,
|
|
18
|
+
"flaky": 0,
|
|
19
|
+
"dropped": 0
|
|
20
|
+
}
|
|
21
|
+
],
|
|
22
|
+
"likely_bugs": [],
|
|
23
|
+
"suspicions": [
|
|
24
|
+
{
|
|
25
|
+
"target": "sgtlearn-base-py--sgtregressor-fit",
|
|
26
|
+
"analysis": "Logical mistakes: The scaling must also be applied to subsequent TAO inputs and undone for predictions and exported leaves; fitting alone cannot guarantee the public contract. Forest bootstrap trees can have different training scales. Weighted and multioutput data need per-output training statistics.\nRobustness omissions: Constant target columns need a safe scale. Failed refits must preserve the previous model and its scaling. Target validation must precede fitting and reject NaN, infinity and values outside the supported float32 range. Tests should use well-conditioned datasets rather than demand identical topology for floating-point ties."
|
|
27
|
+
}
|
|
28
|
+
],
|
|
29
|
+
"needs_decision": [],
|
|
30
|
+
"misguided": [],
|
|
31
|
+
"dropped": [],
|
|
32
|
+
"promotable": [
|
|
33
|
+
{
|
|
34
|
+
"file": "tests/tcheck/test_sgtlearn_base_py__sgtregressor_fit_1.py",
|
|
35
|
+
"dest": "tests/regression/test_sgtlearn_base_py__sgtregressor_fit_1.py",
|
|
36
|
+
"tests": 48
|
|
37
|
+
},
|
|
38
|
+
{
|
|
39
|
+
"file": "tests/tcheck/test_sgtlearn_base_py__sgtregressor_fit_2.py",
|
|
40
|
+
"dest": "tests/regression/test_sgtlearn_base_py__sgtregressor_fit_2.py",
|
|
41
|
+
"tests": 20
|
|
42
|
+
}
|
|
43
|
+
],
|
|
44
|
+
"not_promotable": []
|
|
45
|
+
}
|
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
# test-checker report r-20261026-121217-e0ed
|
|
2
|
+
|
|
3
|
+
- Mode: new
|
|
4
|
+
- current: WORKTREE → `f16fb3709b`
|
|
5
|
+
- Date: 2026-10-26T16:32:53.799Z
|
|
6
|
+
- Harness: codex
|
|
7
|
+
- Blind isolation: medium
|
|
8
|
+
|
|
9
|
+
## Summary
|
|
10
|
+
|
|
11
|
+
| target | accepted | disputed | flaky | dropped |
|
|
12
|
+
|---|---|---|---|---|
|
|
13
|
+
| sgtlearn-base-py--sgtregressor-fit | 68 | 0 | 0 | 0 |
|
|
14
|
+
|
|
15
|
+
## Likely bugs
|
|
16
|
+
|
|
17
|
+
_none_
|
|
18
|
+
|
|
19
|
+
## Suspicions
|
|
20
|
+
|
|
21
|
+
### sgtlearn-base-py--sgtregressor-fit
|
|
22
|
+
|
|
23
|
+
Logical mistakes: The scaling must also be applied to subsequent TAO inputs and undone for predictions and exported leaves; fitting alone cannot guarantee the public contract. Forest bootstrap trees can have different training scales. Weighted and multioutput data need per-output training statistics.
|
|
24
|
+
Robustness omissions: Constant target columns need a safe scale. Failed refits must preserve the previous model and its scaling. Target validation must precede fitting and reject NaN, infinity and values outside the supported float32 range. Tests should use well-conditioned datasets rather than demand identical topology for floating-point ties.
|
|
25
|
+
|
|
26
|
+
## Needs your decision
|
|
27
|
+
|
|
28
|
+
_none_
|
|
29
|
+
|
|
30
|
+
## Misguided tests and what happened to them
|
|
31
|
+
|
|
32
|
+
_none_
|
|
33
|
+
|
|
34
|
+
## Dropped
|
|
35
|
+
|
|
36
|
+
_none_
|
|
37
|
+
|
|
38
|
+
## Promotable tests
|
|
39
|
+
|
|
40
|
+
- tests/tcheck/test_sgtlearn_base_py__sgtregressor_fit_1.py → `tests/regression/test_sgtlearn_base_py__sgtregressor_fit_1.py` (48 test(s))
|
|
41
|
+
- tests/tcheck/test_sgtlearn_base_py__sgtregressor_fit_2.py → `tests/regression/test_sgtlearn_base_py__sgtregressor_fit_2.py` (20 test(s))
|
|
@@ -1,10 +1,10 @@
|
|
|
1
1
|
{
|
|
2
2
|
"verified": {
|
|
3
3
|
"sgtlearn/base.py": {
|
|
4
|
-
"sha": "
|
|
4
|
+
"sha": "29d6709942d7149a2b055c026d31a318e7ea9202",
|
|
5
5
|
"run": null,
|
|
6
|
-
"at": "2026-10-
|
|
7
|
-
"waived": "User
|
|
6
|
+
"at": "2026-10-27T00:14:56.156Z",
|
|
7
|
+
"waived": "User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."
|
|
8
8
|
},
|
|
9
9
|
"sgtlearn/_features.py": {
|
|
10
10
|
"sha": "14bbcf7ce569621eee5c019b13ef84360340b7d4",
|
|
@@ -17,26 +17,40 @@
|
|
|
17
17
|
"at": "2026-09-29T00:33:23.839Z"
|
|
18
18
|
},
|
|
19
19
|
"sgtlearn/ensemble/_random_sgforest.py": {
|
|
20
|
-
"sha": "
|
|
20
|
+
"sha": "0b906cdc444b88783fd6ae5c0985505751e7ef8b",
|
|
21
21
|
"run": null,
|
|
22
|
-
"at": "2026-10-
|
|
23
|
-
"waived": "User
|
|
22
|
+
"at": "2026-10-27T00:14:56.599Z",
|
|
23
|
+
"waived": "User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."
|
|
24
24
|
},
|
|
25
25
|
"sgtlearn/tao.py": {
|
|
26
|
-
"sha": "
|
|
26
|
+
"sha": "bc5fd966e980359bfaffc63699a24b9be61ee586",
|
|
27
27
|
"run": null,
|
|
28
|
-
"at": "2026-10-
|
|
29
|
-
"waived": "User
|
|
28
|
+
"at": "2026-10-27T00:14:56.316Z",
|
|
29
|
+
"waived": "User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."
|
|
30
30
|
},
|
|
31
31
|
"sgtlearn/ensemble/random_sgforest_regressor.py": {
|
|
32
|
-
"sha": "
|
|
33
|
-
"run":
|
|
34
|
-
"at": "2026-10-
|
|
32
|
+
"sha": "1266b0e7fbfafd7be4dc27884a6ef4342f949a88",
|
|
33
|
+
"run": null,
|
|
34
|
+
"at": "2026-10-27T00:14:56.874Z",
|
|
35
|
+
"waived": "User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."
|
|
35
36
|
},
|
|
36
37
|
"sgtlearn/_export.py": {
|
|
37
|
-
"sha": "
|
|
38
|
-
"run":
|
|
39
|
-
"at": "2026-10-
|
|
38
|
+
"sha": "86dd165a666ad64c5076f6f4a838fa1b207f646b",
|
|
39
|
+
"run": null,
|
|
40
|
+
"at": "2026-10-27T00:14:56.459Z",
|
|
41
|
+
"waived": "User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."
|
|
42
|
+
},
|
|
43
|
+
"sgtlearn/ensemble/random_sgforest_classifier.py": {
|
|
44
|
+
"sha": "a15ab6aaf2b8a5c8d38c84fc7951c56b2dab01e1",
|
|
45
|
+
"run": null,
|
|
46
|
+
"at": "2026-10-27T00:14:56.740Z",
|
|
47
|
+
"waived": "User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."
|
|
48
|
+
},
|
|
49
|
+
"sgtlearn/tune.py": {
|
|
50
|
+
"sha": "90a340c85ca1e1a83fe56ba94b26d880d65436e5",
|
|
51
|
+
"run": null,
|
|
52
|
+
"at": "2026-10-27T00:14:57.019Z",
|
|
53
|
+
"waived": "User explicitly authorized normal tests and updates to affected assertions. The final suite passes 1512 tests with two skips; 68 independent target-scaling cases were also verified before default adoption. New tests cover common selected defaults, sklearn forest parameters, optional Optuna import, conditional suggestions, and benchmark split integrity."
|
|
40
54
|
}
|
|
41
55
|
},
|
|
42
56
|
"protected": {
|
|
@@ -766,6 +780,12 @@
|
|
|
766
780
|
"run": "r-20261002-215733-b7b8"
|
|
767
781
|
}
|
|
768
782
|
},
|
|
769
|
-
"quarantined": [
|
|
770
|
-
|
|
783
|
+
"quarantined": [
|
|
784
|
+
"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y::tests.tcheck.test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1::test_list_inputs_are_accepted_as_array_like",
|
|
785
|
+
"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y::tests.tcheck.test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1::test_one_dimensional_y_stays_one_dimensional_float32",
|
|
786
|
+
"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y::tests.tcheck.test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1::test_column_vector_y_stays_two_dimensional",
|
|
787
|
+
"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y::tests.tcheck.test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1::test_multi_output_y_keeps_its_shape",
|
|
788
|
+
"sgtlearn-ensemble-random-sgforest-regressor-py--randomsgforestregressor-check-x-y::tests.tcheck.test_sgtlearn_ensemble_random_sgforest_regressor_py__randomsgforestregressor_check_x_y_1::test_integer_y_is_converted_to_float32"
|
|
789
|
+
],
|
|
790
|
+
"hooks_seen_at": "2026-10-26T23:27:45.628Z"
|
|
771
791
|
}
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.2
|
|
2
2
|
Name: sgtlearn
|
|
3
|
-
Version: 0.
|
|
3
|
+
Version: 0.4.0
|
|
4
4
|
Summary: Shape Generalized Trees learning library
|
|
5
5
|
Author-Email: Nakul Upadhya <nakulupadhya1@gmail.com>, Joshua Lee <joshua.lee.9880@gmail.com>, Eldan Cohen <eldan.cohen@utoronto.ca>
|
|
6
6
|
License: MIT
|
|
@@ -13,6 +13,8 @@ Requires-Dist: scikit-learn>=1.9
|
|
|
13
13
|
Requires-Dist: joblib>=1.2
|
|
14
14
|
Requires-Dist: matplotlib>=3.10.9
|
|
15
15
|
Requires-Dist: seaborn>=0.13.2
|
|
16
|
+
Provides-Extra: tune
|
|
17
|
+
Requires-Dist: optuna>=4; extra == "tune"
|
|
16
18
|
Provides-Extra: dev
|
|
17
19
|
Requires-Dist: pytest>=7; extra == "dev"
|
|
18
20
|
Requires-Dist: pybind11-stubgen; extra == "dev"
|
|
@@ -30,6 +32,8 @@ Description-Content-Type: text/markdown
|
|
|
30
32
|
|
|
31
33
|
`sgtlearn` is a Python package for learning [Shape Generalized Trees (SGTs)](https://neurips.cc/virtual/2025/loc/san-diego/poster/115950).
|
|
32
34
|
|
|
35
|
+
**Using a coding agent?** Point it at the [sgtlearn agent guide](docs/agents.md) or its [published version](https://sgtlearn.readthedocs.io/en/latest/agents.html) for fitting, tuning, and inspecting a model.
|
|
36
|
+
|
|
33
37
|
- 🌳 **Shape Generalized Trees (SGTs):** A class of decision trees where each node applies a learnable, axis-aligned shape function to one or two logical features for non-linear and interpretable splits.
|
|
34
38
|
- 👁 **Interpretability:** Each node's shape function can be visualized directly.
|
|
35
39
|
- ⚡ **ShapeCART Algorithm:** An efficient induction method for learning SGTs from data.
|
|
@@ -38,10 +42,6 @@ Description-Content-Type: text/markdown
|
|
|
38
42
|
- **SGT<sub>K</sub>:** Multi-way branching generalization.
|
|
39
43
|
- **Shape²CART & ShapeCART<sub>K</sub>:** Algorithms for learning S²GTs and SGT<sub>K</sub>s.
|
|
40
44
|
|
|
41
|
-
|
|
42
|
-
> [!NOTE]
|
|
43
|
-
> This codebase is an efficient implementation of the algorithms in "Empowering Decision Trees via Shape Function Branching." See the [ROADMAP](ROADMAP.md) for implementation status and the [canonical research code](https://github.com/optimal-uoft/Empowering-DTs-via-Shape-Functions) for the paper's original implementation.
|
|
44
|
-
|
|
45
45
|
## Installation
|
|
46
46
|
|
|
47
47
|
```bash
|
|
@@ -52,6 +52,44 @@ Wheels are published for CPython 3.11–3.14 on Linux, macOS, and Windows
|
|
|
52
52
|
(x86_64 + arm64); no compiler is needed for a binary install. To build from
|
|
53
53
|
source instead, see [Developer Setup](#developer-setup).
|
|
54
54
|
|
|
55
|
+
For Optuna tuning, install `pip install 'sgtlearn[tune]'` and use
|
|
56
|
+
`from sgtlearn.tune import suggest_params`. Calling `suggest_params(trial)`
|
|
57
|
+
returns keyword arguments for `SGTClassifier` or `SGTRegressor`.
|
|
58
|
+
Pass `use_tao=True` and/or `use_bivariate=True` to `suggest_params` to enable
|
|
59
|
+
those features during tuning. Both flags default to `False`.
|
|
60
|
+
For sklearn searches, `from sgtlearn.tune import suggested_params` provides
|
|
61
|
+
a list of parameter grids for `GridSearchCV` or `RandomizedSearchCV`, with the
|
|
62
|
+
same optional flags. The binary and ternary grids are separate so only
|
|
63
|
+
ternary trees search `branching_penalty`. Prefer randomized search for the full
|
|
64
|
+
space, or narrow the candidate lists before running an exhaustive grid search.
|
|
65
|
+
Both helpers omit constants and inactive parameters, except the required
|
|
66
|
+
`tao_n_runs=10` override when TAO is enabled.
|
|
67
|
+
|
|
68
|
+
```python
|
|
69
|
+
from sklearn.model_selection import RandomizedSearchCV
|
|
70
|
+
from sgtlearn import SGTClassifier
|
|
71
|
+
from sgtlearn.tune import suggested_params
|
|
72
|
+
|
|
73
|
+
search = RandomizedSearchCV(
|
|
74
|
+
SGTClassifier(),
|
|
75
|
+
suggested_params(use_tao=True, use_bivariate=True),
|
|
76
|
+
n_iter=30, cv=3, scoring="balanced_accuracy", random_state=42,
|
|
77
|
+
)
|
|
78
|
+
search.fit(X_train, y_train)
|
|
79
|
+
model = search.best_estimator_
|
|
80
|
+
```
|
|
81
|
+
|
|
82
|
+
Follow the [tuning tutorial](docs/tutorials/hyperparameter-tuning.ipynb) to train
|
|
83
|
+
a model, tune its parameters, and make predictions for classification or regression.
|
|
84
|
+
|
|
85
|
+
The [12-dataset default-selection report](docs/research/2026-10-26-tuning-defaults.md)
|
|
86
|
+
records the Pareto compromise, held-out results, and useful parameter ranges.
|
|
87
|
+
The common defaults use binary branching, outer depth 4, four inner leaves, and regularization.
|
|
88
|
+
Ordinary fitting runs ShapeCART with TAO disabled. Bivariate splits are also off by default; set
|
|
89
|
+
`pairwise_candidates=0.5` for the study-recommended opt-in starting point.
|
|
90
|
+
Existing parameter-free calls change behavior;
|
|
91
|
+
the report documents the classification/regression tradeoff.
|
|
92
|
+
|
|
55
93
|
## Quick Start
|
|
56
94
|
|
|
57
95
|
```python
|
|
@@ -80,6 +118,11 @@ improvement uses total sample weight and the mean across target outputs.
|
|
|
80
118
|
penalties may need retuning. Inner CART and TAO retain their separate settings.
|
|
81
119
|
See [outer-growth semantics](docs/api/estimators.rst) for the scoring formula.
|
|
82
120
|
|
|
121
|
+
Regressors now standardize each target using training-only, sample-weighted
|
|
122
|
+
statistics. Predictions and exported leaf values remain in original units;
|
|
123
|
+
regression impurities and penalties use standardized units. Supply original
|
|
124
|
+
targets to later `TAO_refine` calls, which reuse the fitted transformation.
|
|
125
|
+
|
|
83
126
|
For `SGTRegressor` and `RandomSGForestRegressor`, MAE (`criterion="absolute_error"`
|
|
84
127
|
or `"mae"`) leaves coordinate descent disabled by default. Each top-level fit
|
|
85
128
|
emits one `UserWarning`, including parallel forest fits. Set the environment
|
|
@@ -4,6 +4,8 @@
|
|
|
4
4
|
|
|
5
5
|
`sgtlearn` is a Python package for learning [Shape Generalized Trees (SGTs)](https://neurips.cc/virtual/2025/loc/san-diego/poster/115950).
|
|
6
6
|
|
|
7
|
+
**Using a coding agent?** Point it at the [sgtlearn agent guide](docs/agents.md) or its [published version](https://sgtlearn.readthedocs.io/en/latest/agents.html) for fitting, tuning, and inspecting a model.
|
|
8
|
+
|
|
7
9
|
- 🌳 **Shape Generalized Trees (SGTs):** A class of decision trees where each node applies a learnable, axis-aligned shape function to one or two logical features for non-linear and interpretable splits.
|
|
8
10
|
- 👁 **Interpretability:** Each node's shape function can be visualized directly.
|
|
9
11
|
- ⚡ **ShapeCART Algorithm:** An efficient induction method for learning SGTs from data.
|
|
@@ -12,10 +14,6 @@
|
|
|
12
14
|
- **SGT<sub>K</sub>:** Multi-way branching generalization.
|
|
13
15
|
- **Shape²CART & ShapeCART<sub>K</sub>:** Algorithms for learning S²GTs and SGT<sub>K</sub>s.
|
|
14
16
|
|
|
15
|
-
|
|
16
|
-
> [!NOTE]
|
|
17
|
-
> This codebase is an efficient implementation of the algorithms in "Empowering Decision Trees via Shape Function Branching." See the [ROADMAP](ROADMAP.md) for implementation status and the [canonical research code](https://github.com/optimal-uoft/Empowering-DTs-via-Shape-Functions) for the paper's original implementation.
|
|
18
|
-
|
|
19
17
|
## Installation
|
|
20
18
|
|
|
21
19
|
```bash
|
|
@@ -26,6 +24,44 @@ Wheels are published for CPython 3.11–3.14 on Linux, macOS, and Windows
|
|
|
26
24
|
(x86_64 + arm64); no compiler is needed for a binary install. To build from
|
|
27
25
|
source instead, see [Developer Setup](#developer-setup).
|
|
28
26
|
|
|
27
|
+
For Optuna tuning, install `pip install 'sgtlearn[tune]'` and use
|
|
28
|
+
`from sgtlearn.tune import suggest_params`. Calling `suggest_params(trial)`
|
|
29
|
+
returns keyword arguments for `SGTClassifier` or `SGTRegressor`.
|
|
30
|
+
Pass `use_tao=True` and/or `use_bivariate=True` to `suggest_params` to enable
|
|
31
|
+
those features during tuning. Both flags default to `False`.
|
|
32
|
+
For sklearn searches, `from sgtlearn.tune import suggested_params` provides
|
|
33
|
+
a list of parameter grids for `GridSearchCV` or `RandomizedSearchCV`, with the
|
|
34
|
+
same optional flags. The binary and ternary grids are separate so only
|
|
35
|
+
ternary trees search `branching_penalty`. Prefer randomized search for the full
|
|
36
|
+
space, or narrow the candidate lists before running an exhaustive grid search.
|
|
37
|
+
Both helpers omit constants and inactive parameters, except the required
|
|
38
|
+
`tao_n_runs=10` override when TAO is enabled.
|
|
39
|
+
|
|
40
|
+
```python
|
|
41
|
+
from sklearn.model_selection import RandomizedSearchCV
|
|
42
|
+
from sgtlearn import SGTClassifier
|
|
43
|
+
from sgtlearn.tune import suggested_params
|
|
44
|
+
|
|
45
|
+
search = RandomizedSearchCV(
|
|
46
|
+
SGTClassifier(),
|
|
47
|
+
suggested_params(use_tao=True, use_bivariate=True),
|
|
48
|
+
n_iter=30, cv=3, scoring="balanced_accuracy", random_state=42,
|
|
49
|
+
)
|
|
50
|
+
search.fit(X_train, y_train)
|
|
51
|
+
model = search.best_estimator_
|
|
52
|
+
```
|
|
53
|
+
|
|
54
|
+
Follow the [tuning tutorial](docs/tutorials/hyperparameter-tuning.ipynb) to train
|
|
55
|
+
a model, tune its parameters, and make predictions for classification or regression.
|
|
56
|
+
|
|
57
|
+
The [12-dataset default-selection report](docs/research/2026-10-26-tuning-defaults.md)
|
|
58
|
+
records the Pareto compromise, held-out results, and useful parameter ranges.
|
|
59
|
+
The common defaults use binary branching, outer depth 4, four inner leaves, and regularization.
|
|
60
|
+
Ordinary fitting runs ShapeCART with TAO disabled. Bivariate splits are also off by default; set
|
|
61
|
+
`pairwise_candidates=0.5` for the study-recommended opt-in starting point.
|
|
62
|
+
Existing parameter-free calls change behavior;
|
|
63
|
+
the report documents the classification/regression tradeoff.
|
|
64
|
+
|
|
29
65
|
## Quick Start
|
|
30
66
|
|
|
31
67
|
```python
|
|
@@ -54,6 +90,11 @@ improvement uses total sample weight and the mean across target outputs.
|
|
|
54
90
|
penalties may need retuning. Inner CART and TAO retain their separate settings.
|
|
55
91
|
See [outer-growth semantics](docs/api/estimators.rst) for the scoring formula.
|
|
56
92
|
|
|
93
|
+
Regressors now standardize each target using training-only, sample-weighted
|
|
94
|
+
statistics. Predictions and exported leaf values remain in original units;
|
|
95
|
+
regression impurities and penalties use standardized units. Supply original
|
|
96
|
+
targets to later `TAO_refine` calls, which reuse the fitted transformation.
|
|
97
|
+
|
|
57
98
|
For `SGTRegressor` and `RandomSGForestRegressor`, MAE (`criterion="absolute_error"`
|
|
58
99
|
or `"mae"`) leaves coordinate descent disabled by default. Each top-level fit
|
|
59
100
|
emits one `UserWarning`, including parallel forest fits. Set the environment
|
|
@@ -11,7 +11,7 @@
|
|
|
11
11
|
## v0.2.0
|
|
12
12
|
- [x] Superset branching on categorical features
|
|
13
13
|
- [x] More plotting options
|
|
14
|
-
- [
|
|
14
|
+
- [x] Exporting to Graphviz with `export_graphviz` ([#69](https://github.com/optimal-uoft/sgtlearn/issues/69))
|
|
15
15
|
- [x] Feature importances matching scikit-learn's API for SGTs and SGT$_K$
|
|
16
16
|
- [x] Adding TAO Refinement
|
|
17
17
|
- [x] **Sklearn-style NaN support**: split search uses finite values only, and each univariate node learns which child receives missing values.
|
|
@@ -35,6 +35,12 @@ and the umbrella issue [#27](https://github.com/optimal-uoft/sgtlearn/issues/27)
|
|
|
35
35
|
## v0.3.2
|
|
36
36
|
- [x] Text export of fitted trees with `export_text`
|
|
37
37
|
|
|
38
|
+
## v0.4.0
|
|
39
|
+
- [x] Graphviz DOT export with node shape-function panels
|
|
40
|
+
- [x] Recommended scikit-learn and Optuna search spaces and regularized estimator defaults
|
|
41
|
+
- [x] Regression target standardization with predictions in the original units
|
|
42
|
+
- [x] Coding-agent guide and `llms.txt`
|
|
43
|
+
|
|
38
44
|
## v1.0.0
|
|
39
45
|
- [ ] Cross-Feature Tree Binning (Similar to [DPDT](https://github.com/KohlerHECTOR/DPDTreeEstimator))
|
|
40
46
|
- [ ] Boosting
|