hgp-lib 0.0.1__tar.gz

hgp_lib-0.0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

hgp_lib-0.0.1/PKG-INFO

@@ -0,0 +1,180 @@
+Metadata-Version: 2.4
+Name: hgp-lib
+Version: 0.0.1
+Summary: hgp-lib: Hierarchical Genetic Programming Library for Generating Boolean Rules from Tabular Data
+Author-email: Ramona-Georgiana Albert <george.stoica@info.uaic.ro>, George Stoica <ramona-georgiana.albert@info.uaic.ro>
+Maintainer-email: Ramona-Georgiana Albert <george.stoica@info.uaic.ro>, George Stoica <ramona-georgiana.albert@info.uaic.ro>
+License-Expression: Apache-2.0
+Project-URL: Repository, https://github.com/fii-optim-lab/hgp-lib
+Project-URL: Issues, https://github.com/fii-optim-lab/hgp-lib/issues
+Keywords: explainable ai,xai,interpretable machine learning,rule-based classification,boolean rules,genetic programming,hierarchical genetic programming,evolutionary computation,glass-box model,binary classification
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+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: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Operating System :: OS Independent
+Classifier: Natural Language :: English
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: scikit-learn
+Requires-Dist: tqdm
+Requires-Dist: optuna
+Requires-Dist: optuna-dashboard
+Requires-Dist: matplotlib
+Provides-Extra: dev
+Requires-Dist: mkdocs; extra == "dev"
+Requires-Dist: mkdocstrings-python; extra == "dev"
+Requires-Dist: mkdocs-material; extra == "dev"
+Requires-Dist: mkdocs-bibtex; extra == "dev"
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: flake8; extra == "dev"
+Requires-Dist: ruff; extra == "dev"
+Requires-Dist: seaborn; extra == "dev"
+Requires-Dist: tables; extra == "dev"
+Requires-Dist: prettytable; extra == "dev"
+Requires-Dist: timed-decorator; extra == "dev"
+Dynamic: license-file
+
+# Hierarchical Genetic Programming Library
+
+A Python library for explainable rule-based classification.
+It evolves human-readable boolean rule trees via hierarchical genetic programming, with automatic binarization and parallel benchmarking.
+
+Full documentation: <https://fii-optim-lab.github.io/hgp-lib/>
+
+## What it does
+
+`hgp_lib` evolves boolean rules that classify tabular data.
+A rule is a tree of logical operators (`And`, `Or`) over literals, for example `And(age < 50, Or(income >= 30k, employed))`.
+Rules are readable, so a trained classifier can be inspected and explained.
+
+The method is genetic programming.
+A population of candidate rules is scored against the data, the best rules are selected, and crossover and mutation produce the next generation.
+Over many epochs the population converges toward rules with high fitness.
+Hierarchical GP extends this with child populations that evolve on sampled subsets of features, then combine into larger rules.
+
+Boolean GP operates on boolean data.
+Numeric and categorical columns are binarized first, so a numeric feature becomes a set of boolean bins.
+See [Data Preparation](https://fii-optim-lab.github.io/hgp-lib/guide/data-preparation/) for details.
+
+The model is a single boolean rule, so it is readable on its own and needs no separate explanation.
+See [Theory](https://fii-optim-lab.github.io/hgp-lib/theory/) for how the search works and [Interpretability](https://fii-optim-lab.github.io/hgp-lib/interpretability/) for why this matters.
+
+## Installation
+
+```bash
+pip install -e .
+```
+
+## Quickstart
+
+Binarize the data, train a rule with `GPTrainer`, then use it to predict and print it as plain logic.
+
+```python
+from hgp_lib.preprocessing import StandardBinarizer
+from hgp_lib.configs import BooleanGPConfig, TrainerConfig
+from hgp_lib.trainers import GPTrainer
+from hgp_lib.utils.metrics import fast_f1_score
+
+binarizer = StandardBinarizer(num_bins=5)
+train_bin = binarizer.fit_transform(train_data, train_labels)
+test_bin = binarizer.transform(test_data)
+
+gp = BooleanGPConfig(
+    score_fn=fast_f1_score,
+    train_data=train_bin.to_numpy(),
+    train_labels=train_labels,
+)
+history = GPTrainer(TrainerConfig(gp_config=gp, num_epochs=1000)).fit()
+
+rule = history.global_best_rule
+predictions = rule.evaluate(test_bin.to_numpy())
+column_names = dict(enumerate(train_bin.columns))
+print(rule.to_str(column_names))
+```
+
+The `column_names` map turns literal indices back into the binarized column names, so the printed rule reads as plain logic.
+The [Data Preparation](https://fii-optim-lab.github.io/hgp-lib/guide/data-preparation/) guide shows how to use `StandardBinarizer` without leaking data between splits.
+
+## Benchmarking
+
+`GPBenchmarker` runs multiple independent experiments and aggregates the results.
+Each run takes a stratified train/test split, performs k-fold cross-validation on the training set, and evaluates the best rule on the held-out test set.
+Runs execute in parallel by default.
+
+The benchmarker binarizes data internally, per fold, so you pass a raw `pandas.DataFrame` and skip manual binarization.
+
+```python
+import numpy as np
+import pandas as pd
+from hgp_lib.configs import BenchmarkerConfig, BooleanGPConfig, TrainerConfig
+from hgp_lib.benchmarkers import GPBenchmarker
+
+data = pd.DataFrame(...)  # raw features (bool / categorical / numeric)
+labels = np.array(...)    # 1-D target array
+
+gp_config = BooleanGPConfig(score_fn=score_fn)
+trainer_config = TrainerConfig(gp_config=gp_config, num_epochs=1000, val_every=100)
+config = BenchmarkerConfig(
+    data=data,
+    labels=labels,
+    trainer_config=trainer_config,
+    num_runs=30,
+    n_folds=5,
+    test_size=0.2,
+    n_jobs=-1,
+)
+result = GPBenchmarker(config).fit()
+
+test_scores = result.test_scores
+print(f"Test score: {np.mean(test_scores):.4f} ± {np.std(test_scores):.4f}")
+
+# Human-readable best rule
+print(result.best_rule.to_str(result.best_run.feature_names))
+```
+
+See [Benchmarking](https://fii-optim-lab.github.io/hgp-lib/guide/benchmarking/) for scorer optimization, custom binarizers, and the aggregated result fields.
+
+## Customizing the algorithm
+
+The population, mutation, and crossover behavior is configured through factories passed to `BooleanGPConfig`.
+The default factories cover the common case.
+To use custom initialization strategies or mutations, subclass a factory and override its construction hook.
+
+```python
+from hgp_lib.populations import PopulationGeneratorFactory
+
+factory = PopulationGeneratorFactory(population_size=100)
+```
+
+The [Configuring HGP](https://fii-optim-lab.github.io/hgp-lib/guide/configuring/) guide covers the built-in factories and hierarchical GP.
+The [Extending HGP](https://fii-optim-lab.github.io/hgp-lib/guide/extending/) guide covers custom strategies, mutations, and low-level use of `BooleanGP` directly.
+
+## Documentation
+
+- [Getting Started](https://fii-optim-lab.github.io/hgp-lib/getting-started/)
+- [Theory](https://fii-optim-lab.github.io/hgp-lib/theory/)
+- [Interpretability](https://fii-optim-lab.github.io/hgp-lib/interpretability/)
+- [Data Preparation](https://fii-optim-lab.github.io/hgp-lib/guide/data-preparation/)
+- [Training](https://fii-optim-lab.github.io/hgp-lib/guide/training/)
+- [Benchmarking](https://fii-optim-lab.github.io/hgp-lib/guide/benchmarking/)
+- [Configuring HGP](https://fii-optim-lab.github.io/hgp-lib/guide/configuring/)
+- [Extending HGP](https://fii-optim-lab.github.io/hgp-lib/guide/extending/)
+- [Rule Trees](https://fii-optim-lab.github.io/hgp-lib/guide/rule-trees/)
+- [Experiments](https://fii-optim-lab.github.io/hgp-lib/experiments/)
+- [API Reference](https://fii-optim-lab.github.io/hgp-lib/api/)
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md).

hgp_lib-0.0.1/README.md

@@ -0,0 +1,132 @@
+# Hierarchical Genetic Programming Library
+
+A Python library for explainable rule-based classification.
+It evolves human-readable boolean rule trees via hierarchical genetic programming, with automatic binarization and parallel benchmarking.
+
+Full documentation: <https://fii-optim-lab.github.io/hgp-lib/>
+
+## What it does
+
+`hgp_lib` evolves boolean rules that classify tabular data.
+A rule is a tree of logical operators (`And`, `Or`) over literals, for example `And(age < 50, Or(income >= 30k, employed))`.
+Rules are readable, so a trained classifier can be inspected and explained.
+
+The method is genetic programming.
+A population of candidate rules is scored against the data, the best rules are selected, and crossover and mutation produce the next generation.
+Over many epochs the population converges toward rules with high fitness.
+Hierarchical GP extends this with child populations that evolve on sampled subsets of features, then combine into larger rules.
+
+Boolean GP operates on boolean data.
+Numeric and categorical columns are binarized first, so a numeric feature becomes a set of boolean bins.
+See [Data Preparation](https://fii-optim-lab.github.io/hgp-lib/guide/data-preparation/) for details.
+
+The model is a single boolean rule, so it is readable on its own and needs no separate explanation.
+See [Theory](https://fii-optim-lab.github.io/hgp-lib/theory/) for how the search works and [Interpretability](https://fii-optim-lab.github.io/hgp-lib/interpretability/) for why this matters.
+
+## Installation
+
+```bash
+pip install -e .
+```
+
+## Quickstart
+
+Binarize the data, train a rule with `GPTrainer`, then use it to predict and print it as plain logic.
+
+```python
+from hgp_lib.preprocessing import StandardBinarizer
+from hgp_lib.configs import BooleanGPConfig, TrainerConfig
+from hgp_lib.trainers import GPTrainer
+from hgp_lib.utils.metrics import fast_f1_score
+
+binarizer = StandardBinarizer(num_bins=5)
+train_bin = binarizer.fit_transform(train_data, train_labels)
+test_bin = binarizer.transform(test_data)
+
+gp = BooleanGPConfig(
+    score_fn=fast_f1_score,
+    train_data=train_bin.to_numpy(),
+    train_labels=train_labels,
+)
+history = GPTrainer(TrainerConfig(gp_config=gp, num_epochs=1000)).fit()
+
+rule = history.global_best_rule
+predictions = rule.evaluate(test_bin.to_numpy())
+column_names = dict(enumerate(train_bin.columns))
+print(rule.to_str(column_names))
+```
+
+The `column_names` map turns literal indices back into the binarized column names, so the printed rule reads as plain logic.
+The [Data Preparation](https://fii-optim-lab.github.io/hgp-lib/guide/data-preparation/) guide shows how to use `StandardBinarizer` without leaking data between splits.
+
+## Benchmarking
+
+`GPBenchmarker` runs multiple independent experiments and aggregates the results.
+Each run takes a stratified train/test split, performs k-fold cross-validation on the training set, and evaluates the best rule on the held-out test set.
+Runs execute in parallel by default.
+
+The benchmarker binarizes data internally, per fold, so you pass a raw `pandas.DataFrame` and skip manual binarization.
+
+```python
+import numpy as np
+import pandas as pd
+from hgp_lib.configs import BenchmarkerConfig, BooleanGPConfig, TrainerConfig
+from hgp_lib.benchmarkers import GPBenchmarker
+
+data = pd.DataFrame(...)  # raw features (bool / categorical / numeric)
+labels = np.array(...)    # 1-D target array
+
+gp_config = BooleanGPConfig(score_fn=score_fn)
+trainer_config = TrainerConfig(gp_config=gp_config, num_epochs=1000, val_every=100)
+config = BenchmarkerConfig(
+    data=data,
+    labels=labels,
+    trainer_config=trainer_config,
+    num_runs=30,
+    n_folds=5,
+    test_size=0.2,
+    n_jobs=-1,
+)
+result = GPBenchmarker(config).fit()
+
+test_scores = result.test_scores
+print(f"Test score: {np.mean(test_scores):.4f} ± {np.std(test_scores):.4f}")
+
+# Human-readable best rule
+print(result.best_rule.to_str(result.best_run.feature_names))
+```
+
+See [Benchmarking](https://fii-optim-lab.github.io/hgp-lib/guide/benchmarking/) for scorer optimization, custom binarizers, and the aggregated result fields.
+
+## Customizing the algorithm
+
+The population, mutation, and crossover behavior is configured through factories passed to `BooleanGPConfig`.
+The default factories cover the common case.
+To use custom initialization strategies or mutations, subclass a factory and override its construction hook.
+
+```python
+from hgp_lib.populations import PopulationGeneratorFactory
+
+factory = PopulationGeneratorFactory(population_size=100)
+```
+
+The [Configuring HGP](https://fii-optim-lab.github.io/hgp-lib/guide/configuring/) guide covers the built-in factories and hierarchical GP.
+The [Extending HGP](https://fii-optim-lab.github.io/hgp-lib/guide/extending/) guide covers custom strategies, mutations, and low-level use of `BooleanGP` directly.
+
+## Documentation
+
+- [Getting Started](https://fii-optim-lab.github.io/hgp-lib/getting-started/)
+- [Theory](https://fii-optim-lab.github.io/hgp-lib/theory/)
+- [Interpretability](https://fii-optim-lab.github.io/hgp-lib/interpretability/)
+- [Data Preparation](https://fii-optim-lab.github.io/hgp-lib/guide/data-preparation/)
+- [Training](https://fii-optim-lab.github.io/hgp-lib/guide/training/)
+- [Benchmarking](https://fii-optim-lab.github.io/hgp-lib/guide/benchmarking/)
+- [Configuring HGP](https://fii-optim-lab.github.io/hgp-lib/guide/configuring/)
+- [Extending HGP](https://fii-optim-lab.github.io/hgp-lib/guide/extending/)
+- [Rule Trees](https://fii-optim-lab.github.io/hgp-lib/guide/rule-trees/)
+- [Experiments](https://fii-optim-lab.github.io/hgp-lib/experiments/)
+- [API Reference](https://fii-optim-lab.github.io/hgp-lib/api/)
+
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md).

hgp_lib-0.0.1/hgp_lib/__init__.py

@@ -0,0 +1,3 @@
+from .configs import BenchmarkerConfig, BooleanGPConfig, TrainerConfig
+
+__all__ = ["BooleanGPConfig", "TrainerConfig", "BenchmarkerConfig"]

hgp_lib-0.0.1/hgp_lib/algorithms/__init__.py

@@ -0,0 +1,3 @@
+from .boolean_gp import BooleanGP
+
+__all__ = ["BooleanGP"]