forestgump 0.1.0__tar.gz

forestgump-0.1.0/.gitignore

@@ -0,0 +1,6 @@
+.venv/
+__pycache__/
+*.egg-info/
+dist/
+.pytest_cache/
+.ruff_cache/

forestgump-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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.

forestgump-0.1.0/PKG-INFO

@@ -0,0 +1,157 @@
+Metadata-Version: 2.5
+Name: forestgump
+Version: 0.1.0
+Summary: Life is like a box of baselines. Did your cheminformatics model beat a random forest trained on Morgan fingerprints?
+Author-email: Jenny Luo <jennyluo@berkeley.edu>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: baselines,cheminformatics,model-evaluation,morgan-fingerprint,random-forest,rdkit
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Chemistry
+Requires-Python: >=3.10
+Requires-Dist: numpy>=1.24
+Requires-Dist: pandas>=2.0
+Requires-Dist: rdkit>=2023.9
+Requires-Dist: scikit-learn>=1.3
+Requires-Dist: scipy>=1.10
+Provides-Extra: test
+Requires-Dist: pytest>=8; extra == 'test'
+Description-Content-Type: text/markdown
+
+# forestgump
+
+*Life is like a box of baselines.*
+
+**Morgan-fingerprint baselines for cheminformatics models.**
+
+You trained a molecular property model for 3 days on 8×H100. Did it beat a random forest trained on Morgan
+fingerprints?
+
+forestgump takes your molecules as SMILES, plus your labels, your cross-validation folds and your model's
+out-of-fold predictions. It fits three baselines on **exactly the same folds**: the training mean, Tanimoto kNN on
+Morgan fingerprints, and a random forest on Morgan fingerprints. Name a context column, such as an assay, a
+chemical series or a reaction's catalyst, and it adds a fourth: the context mean. Then it runs a paired test to
+decide whether your model beat the forest.
+
+```
+Your model, trained on 8×H100 for 3 days, lost to a random forest. The forest trained in 31 seconds on a CPU.
+The forest has no GPU. The forest has no feelings. The forest won.
+```
+
+## Install
+
+```bash
+pip install forestgump
+```
+
+## Try it
+
+```bash
+forestgump demo                             # a model that predicts noise. The forest wins.
+forestgump demo --model oracle              # knows the answer, beats the forest on all 5 folds, and only ties
+forestgump demo --model oracle --repeats 3  # 15 folds is enough evidence. You win.
+```
+
+The demo molecules are 105 para-disubstituted benzenes. Their labels are RDKit's Crippen logP.
+
+The tie is not a bug. Five folds is not much evidence, and the test is built not to call a winner without it.
+
+## Use it
+
+You need one CSV with one row per molecule. Its columns are:
+
+| Column | Meaning |
+|---|---|
+| `smiles` | the molecule |
+| `target` | the label: a number, or one of two classes |
+| `fold` | which test fold the row belongs to |
+| `pred` | your model's prediction for the row, made while it was in the test fold. For a two-class target, this is the probability of the larger class label. |
+
+```bash
+forestgump run my_results.csv
+forestgump run my_results.csv --smiles SMILES --target y --fold cv_fold --pred my_model
+```
+
+For **repeated** cross-validation, add one row per (molecule, repeat) and pass `--repeat repeat_column`. The test
+set of (repeat r, fold f) is those rows. Its training set is every other row of repeat r.
+
+To add the context mean, name one or more context columns. With several, a group is one combination of their values.
+
+```bash
+forestgump run my_results.csv --context catalyst base
+```
+
+From Python:
+
+```python
+import forestgump
+
+report = forestgump.run(df, smiles="smiles", target="target", fold="fold", pred="pred", context=["catalyst", "base"])
+print(report.verdict)  # "win", "lose", "tie", or "refuse"
+print(report.render())
+report.to_json("forest.json")
+```
+
+## The baselines
+
+Each baseline is retrained on every training set, and its hyperparameters are picked from **that training set
+only**. Test rows are only ever predicted.
+
+- **The Mean** has nothing to tune. It predicts the training-set mean for every test row, or for a two-class
+  target the training share of the larger class.
+- **Retrieval-Augmented Mean** appears only with `--context`, and it has nothing to tune either. For each test
+  row it retrieves the training rows with the same context values and averages their labels. A group with no
+  training rows gets the training-set mean, and the report says how many test rows that happened to.
+- **Large Lookup Model** uses inner cross-validation, which takes milliseconds for kNN: 5 folds, or 3 below 50
+  training rows.
+- **The Forest** fits each of its 12 configs once and keeps the one with the best out-of-bag score. Every tree
+  skips about a third of the training rows, so the forest gets a validation score for free. If you'd rather tune
+  it like everything else, `--forest-inner-cv` uses inner cross-validation instead. That fits each config once
+  per inner fold and then refits the winner, so it is about 5× slower.
+
+| Name | What it is | Grid |
+|---|---|---|
+| The Mean | the training-set mean, or the class prior | none (zero parameters, zero shots, zero GPUs) |
+| Retrieval-Augmented Mean | only with `--context`: the mean label of the training rows in the test row's group, or the training-set mean if the group has no training rows | none (it is a groupby) |
+| Large Lookup Model | k-nearest neighbors with Tanimoto distance | k ∈ {1, 3, 5, 10} × {uniform, distance} weights × radius ∈ {2, 3} |
+| The Forest | a random forest with 500 trees | max_features ∈ {sqrt, 0.3, 1.0} × min_samples_leaf ∈ {1, 3} × radius ∈ {2, 3} |
+
+Both fingerprint baselines use 2048-bit Morgan fingerprints from RDKit.
+
+## How the verdict is decided
+
+The primary metric is RMSE for numeric targets and ROC-AUC for two-class targets. The report also gives MAE, R²
+and Spearman ρ, or accuracy.
+
+1. Every method is scored on every test set. The full per-test-set table is printed **before** any verdict.
+2. Your model is compared with each baseline on the per-test-set differences, using the **Nadeau–Bengio corrected
+   resampled t-test**. CV training sets overlap, so the differences are correlated and a plain paired t-test is
+   overconfident. The correction inflates the variance by `1/J + n_test/n_train` over J test sets
+   (Nadeau & Bengio 2003; Bouckaert & Frank 2004 for repeated CV).
+3. The p-values, three or four with `--context`, are Holm-adjusted together.
+4. The verdict compares you with the forest at α = 0.05: **win**, **lose**, or **tie**. With fewer than 3 test
+   sets the forest declines to be judged.
+
+The report also gives the mean difference, its confidence interval and Cohen's d_z. Use `--json` to get every
+number, the hyperparameters chosen on each test set, and the baselines' predictions.
+
+## Flags
+
+| Flag | Effect |
+|---|---|
+| `--seriously` | plain output with no jokes, for logs and papers |
+| `--brag "a 3-billion-parameter foundation model"` | changes how the forest describes your training |
+| `--forest-inner-cv` | picks the forest's hyperparameters by inner CV instead of out-of-bag score. About 5× slower, and it warns you. |
+| `--fail-if-forest-wins` | exits 1 if the forest won, so a CI pipeline goes red when your model loses |
+| `--context catalyst base` | adds the context mean, grouping rows by these columns. The report says how many test rows had a group with no training rows and fell back to the training-set mean. |
+| `--task regression\|binary` | overrides the task. By default a target with 2 values is binary. |
+| `--seed 0` | the random seed for the forest's trees and the inner CV splits. Default 0. In `forestgump demo` it also sets the demo's folds and noise. |
+| `--n-jobs -1` | how many CPU cores the forest uses. Default -1, meaning all of them. |
+| `--alpha 0.05` | the significance level: the forest wins or loses only when the Holm-adjusted p is below it. It also sets the confidence intervals to 1 − alpha. Default 0.05. |
+
+## License
+
+Apache-2.0.

forestgump-0.1.0/README.md

@@ -0,0 +1,134 @@
+# forestgump
+
+*Life is like a box of baselines.*
+
+**Morgan-fingerprint baselines for cheminformatics models.**
+
+You trained a molecular property model for 3 days on 8×H100. Did it beat a random forest trained on Morgan
+fingerprints?
+
+forestgump takes your molecules as SMILES, plus your labels, your cross-validation folds and your model's
+out-of-fold predictions. It fits three baselines on **exactly the same folds**: the training mean, Tanimoto kNN on
+Morgan fingerprints, and a random forest on Morgan fingerprints. Name a context column, such as an assay, a
+chemical series or a reaction's catalyst, and it adds a fourth: the context mean. Then it runs a paired test to
+decide whether your model beat the forest.
+
+```
+Your model, trained on 8×H100 for 3 days, lost to a random forest. The forest trained in 31 seconds on a CPU.
+The forest has no GPU. The forest has no feelings. The forest won.
+```
+
+## Install
+
+```bash
+pip install forestgump
+```
+
+## Try it
+
+```bash
+forestgump demo                             # a model that predicts noise. The forest wins.
+forestgump demo --model oracle              # knows the answer, beats the forest on all 5 folds, and only ties
+forestgump demo --model oracle --repeats 3  # 15 folds is enough evidence. You win.
+```
+
+The demo molecules are 105 para-disubstituted benzenes. Their labels are RDKit's Crippen logP.
+
+The tie is not a bug. Five folds is not much evidence, and the test is built not to call a winner without it.
+
+## Use it
+
+You need one CSV with one row per molecule. Its columns are:
+
+| Column | Meaning |
+|---|---|
+| `smiles` | the molecule |
+| `target` | the label: a number, or one of two classes |
+| `fold` | which test fold the row belongs to |
+| `pred` | your model's prediction for the row, made while it was in the test fold. For a two-class target, this is the probability of the larger class label. |
+
+```bash
+forestgump run my_results.csv
+forestgump run my_results.csv --smiles SMILES --target y --fold cv_fold --pred my_model
+```
+
+For **repeated** cross-validation, add one row per (molecule, repeat) and pass `--repeat repeat_column`. The test
+set of (repeat r, fold f) is those rows. Its training set is every other row of repeat r.
+
+To add the context mean, name one or more context columns. With several, a group is one combination of their values.
+
+```bash
+forestgump run my_results.csv --context catalyst base
+```
+
+From Python:
+
+```python
+import forestgump
+
+report = forestgump.run(df, smiles="smiles", target="target", fold="fold", pred="pred", context=["catalyst", "base"])
+print(report.verdict)  # "win", "lose", "tie", or "refuse"
+print(report.render())
+report.to_json("forest.json")
+```
+
+## The baselines
+
+Each baseline is retrained on every training set, and its hyperparameters are picked from **that training set
+only**. Test rows are only ever predicted.
+
+- **The Mean** has nothing to tune. It predicts the training-set mean for every test row, or for a two-class
+  target the training share of the larger class.
+- **Retrieval-Augmented Mean** appears only with `--context`, and it has nothing to tune either. For each test
+  row it retrieves the training rows with the same context values and averages their labels. A group with no
+  training rows gets the training-set mean, and the report says how many test rows that happened to.
+- **Large Lookup Model** uses inner cross-validation, which takes milliseconds for kNN: 5 folds, or 3 below 50
+  training rows.
+- **The Forest** fits each of its 12 configs once and keeps the one with the best out-of-bag score. Every tree
+  skips about a third of the training rows, so the forest gets a validation score for free. If you'd rather tune
+  it like everything else, `--forest-inner-cv` uses inner cross-validation instead. That fits each config once
+  per inner fold and then refits the winner, so it is about 5× slower.
+
+| Name | What it is | Grid |
+|---|---|---|
+| The Mean | the training-set mean, or the class prior | none (zero parameters, zero shots, zero GPUs) |
+| Retrieval-Augmented Mean | only with `--context`: the mean label of the training rows in the test row's group, or the training-set mean if the group has no training rows | none (it is a groupby) |
+| Large Lookup Model | k-nearest neighbors with Tanimoto distance | k ∈ {1, 3, 5, 10} × {uniform, distance} weights × radius ∈ {2, 3} |
+| The Forest | a random forest with 500 trees | max_features ∈ {sqrt, 0.3, 1.0} × min_samples_leaf ∈ {1, 3} × radius ∈ {2, 3} |
+
+Both fingerprint baselines use 2048-bit Morgan fingerprints from RDKit.
+
+## How the verdict is decided
+
+The primary metric is RMSE for numeric targets and ROC-AUC for two-class targets. The report also gives MAE, R²
+and Spearman ρ, or accuracy.
+
+1. Every method is scored on every test set. The full per-test-set table is printed **before** any verdict.
+2. Your model is compared with each baseline on the per-test-set differences, using the **Nadeau–Bengio corrected
+   resampled t-test**. CV training sets overlap, so the differences are correlated and a plain paired t-test is
+   overconfident. The correction inflates the variance by `1/J + n_test/n_train` over J test sets
+   (Nadeau & Bengio 2003; Bouckaert & Frank 2004 for repeated CV).
+3. The p-values, three or four with `--context`, are Holm-adjusted together.
+4. The verdict compares you with the forest at α = 0.05: **win**, **lose**, or **tie**. With fewer than 3 test
+   sets the forest declines to be judged.
+
+The report also gives the mean difference, its confidence interval and Cohen's d_z. Use `--json` to get every
+number, the hyperparameters chosen on each test set, and the baselines' predictions.
+
+## Flags
+
+| Flag | Effect |
+|---|---|
+| `--seriously` | plain output with no jokes, for logs and papers |
+| `--brag "a 3-billion-parameter foundation model"` | changes how the forest describes your training |
+| `--forest-inner-cv` | picks the forest's hyperparameters by inner CV instead of out-of-bag score. About 5× slower, and it warns you. |
+| `--fail-if-forest-wins` | exits 1 if the forest won, so a CI pipeline goes red when your model loses |
+| `--context catalyst base` | adds the context mean, grouping rows by these columns. The report says how many test rows had a group with no training rows and fell back to the training-set mean. |
+| `--task regression\|binary` | overrides the task. By default a target with 2 values is binary. |
+| `--seed 0` | the random seed for the forest's trees and the inner CV splits. Default 0. In `forestgump demo` it also sets the demo's folds and noise. |
+| `--n-jobs -1` | how many CPU cores the forest uses. Default -1, meaning all of them. |
+| `--alpha 0.05` | the significance level: the forest wins or loses only when the Holm-adjusted p is below it. It also sets the confidence intervals to 1 − alpha. Default 0.05. |
+
+## License
+
+Apache-2.0.

forestgump-0.1.0/pyproject.toml

@@ -0,0 +1,47 @@
+[build-system]
+requires = ["hatchling>=1.25"]
+build-backend = "hatchling.build"
+
+[project]
+name = "forestgump"
+version = "0.1.0"
+description = "Life is like a box of baselines. Did your cheminformatics model beat a random forest trained on Morgan fingerprints?"
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [{ name = "Jenny Luo", email = "jennyluo@berkeley.edu" }]
+requires-python = ">=3.10"
+dependencies = [
+    "numpy>=1.24",
+    "pandas>=2.0",
+    "rdkit>=2023.9",
+    "scikit-learn>=1.3",
+    "scipy>=1.10",
+]
+keywords = ["baselines", "random-forest", "cheminformatics", "morgan-fingerprint", "rdkit", "model-evaluation"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Topic :: Scientific/Engineering :: Chemistry",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+
+[project.scripts]
+forestgump = "forestgump.cli:main"
+
+[project.optional-dependencies]
+test = ["pytest>=8"]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/forestgump"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+
+[tool.ruff]
+line-length = 120
+target-version = "py310"
+
+[tool.ruff.lint]
+select = ["E", "F", "W", "I", "UP", "B", "RUF"]

forestgump-0.1.0/src/forestgump/__init__.py

@@ -0,0 +1,14 @@
+"""forestgump: did your model beat a random forest? Life is like a box of baselines."""
+
+from importlib.metadata import PackageNotFoundError, version
+
+try:
+    __version__ = version("forestgump")
+except PackageNotFoundError:  # running from a source tree
+    __version__ = "0+unknown"
+
+from .core import run
+from .io import InputError, load
+from .report import Report
+
+__all__ = ["InputError", "Report", "__version__", "load", "run"]