pypu-learn 0.0.1__tar.gz

pypu_learn-0.0.1/.gitignore

@@ -0,0 +1,44 @@
+# Byte-compiled / cached files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Build artifacts
+build/
+dist/
+*.egg-info/
+*.egg
+wheels/
+
+# Version file generated by hatch-vcs at build time
+src/pypu/_version.py
+
+# Virtual environments
+.venv/
+venv/
+env/
+
+# Test, coverage and lint caches
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+.coverage
+.coverage.*
+coverage.xml
+htmlcov/
+
+# Docs build
+docs/_build/
+site/
+
+# Jupyter
+.ipynb_checkpoints/
+
+# Editors and OS
+.idea/
+.vscode/
+*.swp
+.DS_Store
+
+# Local Claude Code settings (shared settings in .claude/settings.json are kept)
+.claude/settings.local.json

pypu_learn-0.0.1/CHANGELOG.md

@@ -0,0 +1,26 @@
+# Changelog
+
+All notable changes to PyPU are documented in this file.
+
+The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and the project
+uses [Semantic Versioning](https://semver.org/spec/v2.0.0.html). While the version is `0.y.z`
+the public API may change between minor versions; such changes are always listed under
+**Changed** or **Removed**.
+
+## [Unreleased]
+
+## [0.0.1] - 2026-11-06
+
+### Added
+
+- Project scaffold: packaging with hatchling and version numbers taken from git tags
+  (hatch-vcs), CI on Linux, macOS and Windows for Python 3.11–3.14, and a tag-triggered
+  release workflow that publishes to TestPyPI and PyPI.
+- `pypu.base.BasePUClassifier`, the interface shared by all models: `fit(X, s)`,
+  `predict_proba`, `decision_function` and `predict`.
+- `pypu.models.NaivePU`, the baseline that treats unlabeled samples as negatives.
+- `pypu.utils.check_pu_labels`, `pypu.utils.check_prior`, `pypu.utils.threshold_from_prior`
+  and `pypu.show_versions()`.
+
+[Unreleased]: https://github.com/izavits/PyPU/compare/v0.0.1...HEAD
+[0.0.1]: https://github.com/izavits/PyPU/releases/tag/v0.0.1

pypu_learn-0.0.1/CITATION.cff

@@ -0,0 +1,14 @@
+cff-version: 1.2.0
+message: "If you use PyPU in your research, please cite it using the metadata below."
+title: "PyPU: Positive-unlabeled learning in Python"
+type: software
+authors:
+  - given-names: Ilias
+    family-names: Zavitsanos
+repository-code: "https://github.com/izavits/PyPU"
+license: BSD-3-Clause
+keywords:
+  - positive-unlabeled learning
+  - PU learning
+  - machine learning
+  - scikit-learn

pypu_learn-0.0.1/LICENSE

@@ -0,0 +1,29 @@
+BSD 3-Clause License
+
+Copyright (c) 2026, Ilias Zavitsanos
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+
+3. Neither the name of the copyright holder nor the names of its
+   contributors may be used to endorse or promote products derived from
+   this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

pypu_learn-0.0.1/PKG-INFO

@@ -0,0 +1,137 @@
+Metadata-Version: 2.5
+Name: pypu-learn
+Version: 0.0.1
+Summary: Positive-unlabeled (PU) learning in Python, with a scikit-learn style API.
+Project-URL: Homepage, https://github.com/izavits/PyPU
+Project-URL: Repository, https://github.com/izavits/PyPU
+Project-URL: Issues, https://github.com/izavits/PyPU/issues
+Project-URL: Changelog, https://github.com/izavits/PyPU/blob/main/CHANGELOG.md
+Author: Ilias Zavitsanos
+License-Expression: BSD-3-Clause
+License-File: LICENSE
+Keywords: machine-learning,positive-unlabeled,pu-learning,scikit-learn,semi-supervised,weak-supervision
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.11
+Requires-Dist: numpy>=1.26
+Requires-Dist: scikit-learn>=1.6
+Requires-Dist: scipy>=1.11
+Description-Content-Type: text/markdown
+
+# PyPU
+
+**Positive-unlabeled (PU) learning in Python, with a scikit-learn style API.**
+
+[![CI](https://github.com/izavits/PyPU/actions/workflows/ci.yml/badge.svg)](https://github.com/izavits/PyPU/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/pypu-learn.svg)](https://pypi.org/project/pypu-learn/)
+[![Python versions](https://img.shields.io/pypi/pyversions/pypu-learn.svg)](https://pypi.org/project/pypu-learn/)
+[![License: BSD-3-Clause](https://img.shields.io/badge/License-BSD_3--Clause-blue.svg)](https://github.com/izavits/PyPU/blob/main/LICENSE)
+
+> **Status: pre-alpha.** The common interface is in place and the methods are being ported.
+> See the [roadmap](https://github.com/izavits/PyPU/blob/main/ROADMAP.md).
+
+In PU learning the training data hold some examples labeled positive and many unlabeled
+examples, which are a mix of positives and negatives. No example is labeled negative. This
+happens whenever only one class gets recorded: confirmed frauds, known disease genes, reported
+misstatements, clicked items.
+
+PyPU collects PU learning methods behind one interface, in the spirit of
+[PyOD](https://github.com/yzhao062/pyod) for outlier detection: import a model, `fit` it on
+PU data, and predict on new data.
+
+## Installation
+
+```bash
+pip install pypu-learn
+```
+
+The package is imported as `pypu` and needs Python 3.11 or newer. (The PyPI name `pypu`
+belongs to an unrelated project, hence `pypu-learn`.)
+
+Until the first release is on PyPI, install from GitHub:
+
+```bash
+pip install git+https://github.com/izavits/PyPU.git
+```
+
+## Quick start
+
+```python
+import numpy as np
+from sklearn.datasets import make_classification
+from sklearn.metrics import roc_auc_score
+from sklearn.model_selection import train_test_split
+
+from pypu.models import NaivePU
+
+# A fully labeled dataset...
+X, y = make_classification(n_samples=2000, weights=[0.8], random_state=0)
+X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=0)
+
+# ...turned into PU data: label half of the training positives, leave the rest unlabeled.
+rng = np.random.default_rng(0)
+s_train = ((y_train == 1) & (rng.random(len(y_train)) < 0.5)).astype(int)
+
+clf = NaivePU(prior=y_train.mean())
+clf.fit(X_train, s_train)  # s = 1: labeled positive, s = 0: unlabeled
+
+scores = clf.predict_proba(X_test)[:, 1]
+print("ROC AUC:", roc_auc_score(y_test, scores))
+```
+
+Data utilities that turn labeled datasets into PU data in one call are coming in 0.1.0.
+
+## The interface
+
+Every model derives from `pypu.base.BasePUClassifier` and is a scikit-learn estimator, so it
+works with `clone`, `Pipeline` and `GridSearchCV`.
+
+| Method | Returns |
+| --- | --- |
+| `fit(X, s)` | The fitted model. `s[i] = 1` marks a labeled positive, `s[i] = 0` an unlabeled sample. |
+| `predict_proba(X)` | An `(n_samples, 2)` array; column 1 is the positive-class probability. |
+| `decision_function(X)` | One score per sample; higher means more likely positive. |
+| `predict(X)` | Labels in `{0, 1}`, thresholding the positive-class probability at `threshold_`. |
+
+Models that need the class prior π = P(y = 1) take it as a `prior` parameter.
+
+## Methods
+
+| Model | Description | Status |
+| --- | --- | --- |
+| `NaivePU` | Treats unlabeled samples as negatives; the usual lower bound | available |
+| `IFPU` | Focal-loss PU risk with gradient boosting | planned (0.1.0) |
+| `IFPNU` | Anomaly detector picks reliable negatives, then a focal PNU risk with gradient boosting | planned (0.1.0) |
+| `SAREM` | EM for labels selected at random (SAR) | planned (0.1.0) |
+| `ElkanNoto`, `PUBagging` | Classic PU baselines | planned (0.1.0) |
+| `PUHellingerTree`, `PUHellingerForest` | Hellinger-distance decision trees and forests for PU data | planned (0.2.0) |
+| `NNPU`, `LBE`, `PUe`, `ALMPU` | Neural PU methods (optional PyTorch dependency) | planned (0.3.0) |
+
+Also planned: creating PU data from labeled datasets (uniform SCAR selection, KNN-biased and
+other SAR selection mechanisms), class-prior estimation, and PU-specific metrics.
+
+## Contributing
+
+Contributions are welcome. See
+[CONTRIBUTING.md](https://github.com/izavits/PyPU/blob/main/CONTRIBUTING.md) for the
+development setup, how to add a model, and the release process. Changes are listed in
+[CHANGELOG.md](https://github.com/izavits/PyPU/blob/main/CHANGELOG.md).
+
+## Citing
+
+If you use PyPU in your research, please cite it; GitHub's "Cite this repository" button uses
+[CITATION.cff](https://github.com/izavits/PyPU/blob/main/CITATION.cff).
+
+## License
+
+PyPU is distributed under the
+[BSD 3-Clause License](https://github.com/izavits/PyPU/blob/main/LICENSE).

pypu_learn-0.0.1/README.md

@@ -0,0 +1,108 @@
+# PyPU
+
+**Positive-unlabeled (PU) learning in Python, with a scikit-learn style API.**
+
+[![CI](https://github.com/izavits/PyPU/actions/workflows/ci.yml/badge.svg)](https://github.com/izavits/PyPU/actions/workflows/ci.yml)
+[![PyPI](https://img.shields.io/pypi/v/pypu-learn.svg)](https://pypi.org/project/pypu-learn/)
+[![Python versions](https://img.shields.io/pypi/pyversions/pypu-learn.svg)](https://pypi.org/project/pypu-learn/)
+[![License: BSD-3-Clause](https://img.shields.io/badge/License-BSD_3--Clause-blue.svg)](https://github.com/izavits/PyPU/blob/main/LICENSE)
+
+> **Status: pre-alpha.** The common interface is in place and the methods are being ported.
+> See the [roadmap](https://github.com/izavits/PyPU/blob/main/ROADMAP.md).
+
+In PU learning the training data hold some examples labeled positive and many unlabeled
+examples, which are a mix of positives and negatives. No example is labeled negative. This
+happens whenever only one class gets recorded: confirmed frauds, known disease genes, reported
+misstatements, clicked items.
+
+PyPU collects PU learning methods behind one interface, in the spirit of
+[PyOD](https://github.com/yzhao062/pyod) for outlier detection: import a model, `fit` it on
+PU data, and predict on new data.
+
+## Installation
+
+```bash
+pip install pypu-learn
+```
+
+The package is imported as `pypu` and needs Python 3.11 or newer. (The PyPI name `pypu`
+belongs to an unrelated project, hence `pypu-learn`.)
+
+Until the first release is on PyPI, install from GitHub:
+
+```bash
+pip install git+https://github.com/izavits/PyPU.git
+```
+
+## Quick start
+
+```python
+import numpy as np
+from sklearn.datasets import make_classification
+from sklearn.metrics import roc_auc_score
+from sklearn.model_selection import train_test_split
+
+from pypu.models import NaivePU
+
+# A fully labeled dataset...
+X, y = make_classification(n_samples=2000, weights=[0.8], random_state=0)
+X_train, X_test, y_train, y_test = train_test_split(X, y, stratify=y, random_state=0)
+
+# ...turned into PU data: label half of the training positives, leave the rest unlabeled.
+rng = np.random.default_rng(0)
+s_train = ((y_train == 1) & (rng.random(len(y_train)) < 0.5)).astype(int)
+
+clf = NaivePU(prior=y_train.mean())
+clf.fit(X_train, s_train)  # s = 1: labeled positive, s = 0: unlabeled
+
+scores = clf.predict_proba(X_test)[:, 1]
+print("ROC AUC:", roc_auc_score(y_test, scores))
+```
+
+Data utilities that turn labeled datasets into PU data in one call are coming in 0.1.0.
+
+## The interface
+
+Every model derives from `pypu.base.BasePUClassifier` and is a scikit-learn estimator, so it
+works with `clone`, `Pipeline` and `GridSearchCV`.
+
+| Method | Returns |
+| --- | --- |
+| `fit(X, s)` | The fitted model. `s[i] = 1` marks a labeled positive, `s[i] = 0` an unlabeled sample. |
+| `predict_proba(X)` | An `(n_samples, 2)` array; column 1 is the positive-class probability. |
+| `decision_function(X)` | One score per sample; higher means more likely positive. |
+| `predict(X)` | Labels in `{0, 1}`, thresholding the positive-class probability at `threshold_`. |
+
+Models that need the class prior π = P(y = 1) take it as a `prior` parameter.
+
+## Methods
+
+| Model | Description | Status |
+| --- | --- | --- |
+| `NaivePU` | Treats unlabeled samples as negatives; the usual lower bound | available |
+| `IFPU` | Focal-loss PU risk with gradient boosting | planned (0.1.0) |
+| `IFPNU` | Anomaly detector picks reliable negatives, then a focal PNU risk with gradient boosting | planned (0.1.0) |
+| `SAREM` | EM for labels selected at random (SAR) | planned (0.1.0) |
+| `ElkanNoto`, `PUBagging` | Classic PU baselines | planned (0.1.0) |
+| `PUHellingerTree`, `PUHellingerForest` | Hellinger-distance decision trees and forests for PU data | planned (0.2.0) |
+| `NNPU`, `LBE`, `PUe`, `ALMPU` | Neural PU methods (optional PyTorch dependency) | planned (0.3.0) |
+
+Also planned: creating PU data from labeled datasets (uniform SCAR selection, KNN-biased and
+other SAR selection mechanisms), class-prior estimation, and PU-specific metrics.
+
+## Contributing
+
+Contributions are welcome. See
+[CONTRIBUTING.md](https://github.com/izavits/PyPU/blob/main/CONTRIBUTING.md) for the
+development setup, how to add a model, and the release process. Changes are listed in
+[CHANGELOG.md](https://github.com/izavits/PyPU/blob/main/CHANGELOG.md).
+
+## Citing
+
+If you use PyPU in your research, please cite it; GitHub's "Cite this repository" button uses
+[CITATION.cff](https://github.com/izavits/PyPU/blob/main/CITATION.cff).
+
+## License
+
+PyPU is distributed under the
+[BSD 3-Clause License](https://github.com/izavits/PyPU/blob/main/LICENSE).

pypu_learn-0.0.1/pyproject.toml

@@ -0,0 +1,135 @@
+[build-system]
+requires = ["hatchling>=1.27", "hatch-vcs>=0.4"]
+build-backend = "hatchling.build"
+
+[project]
+# The distribution name on PyPI. `pypu` is taken (abandoned since 2014); the import name is `pypu`.
+name = "pypu-learn"
+dynamic = ["version"]
+description = "Positive-unlabeled (PU) learning in Python, with a scikit-learn style API."
+readme = "README.md"
+license = "BSD-3-Clause"
+license-files = ["LICENSE"]
+requires-python = ">=3.11"
+authors = [{ name = "Ilias Zavitsanos" }]
+keywords = [
+    "pu-learning",
+    "positive-unlabeled",
+    "semi-supervised",
+    "weak-supervision",
+    "machine-learning",
+    "scikit-learn",
+]
+classifiers = [
+    "Development Status :: 2 - Pre-Alpha",
+    "Intended Audience :: Science/Research",
+    "Intended Audience :: Developers",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+    "numpy>=1.26",
+    "scipy>=1.11",
+    "scikit-learn>=1.6",
+]
+
+[project.urls]
+Homepage = "https://github.com/izavits/PyPU"
+Repository = "https://github.com/izavits/PyPU"
+Issues = "https://github.com/izavits/PyPU/issues"
+Changelog = "https://github.com/izavits/PyPU/blob/main/CHANGELOG.md"
+
+[dependency-groups]
+test = [
+    "pytest>=8",
+    "pytest-cov>=5",
+    "pandas>=2",  # DataFrame input tests
+]
+dev = [
+    { include-group = "test" },
+    "ruff>=0.17",
+    "pre-commit>=4",
+    "build>=1.2",
+    "twine>=6",
+]
+
+# ---------------------------------------------------------------- build
+
+[tool.hatch.version]
+source = "vcs"
+# Used when building outside a git checkout or before the first commit/tag.
+fallback-version = "0.0.0"
+
+[tool.hatch.build.hooks.vcs]
+version-file = "src/pypu/_version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/pypu"]
+
+[tool.hatch.build.targets.sdist]
+include = [
+    "src/pypu",
+    "tests",
+    "README.md",
+    "CHANGELOG.md",
+    "CITATION.cff",
+    "LICENSE",
+]
+
+# ---------------------------------------------------------------- tests
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = ["-ra", "--strict-markers", "--strict-config"]
+xfail_strict = true
+
+[tool.coverage.run]
+source = ["pypu"]
+branch = true
+omit = ["*/_version.py"]
+
+[tool.coverage.report]
+show_missing = true
+skip_covered = true
+exclude_also = [
+    "if TYPE_CHECKING:",
+    "raise NotImplementedError",
+    "@abstractmethod",
+]
+
+# ---------------------------------------------------------------- lint
+
+[tool.ruff]
+line-length = 100
+target-version = "py311"
+src = ["src", "tests"]
+
+[tool.ruff.lint]
+select = [
+    "E",   # pycodestyle errors
+    "W",   # pycodestyle warnings
+    "F",   # pyflakes
+    "I",   # isort
+    "B",   # flake8-bugbear
+    "UP",  # pyupgrade
+    "SIM", # flake8-simplify
+    "NPY", # numpy-specific rules
+    "RUF", # ruff-specific rules
+    "D",   # pydocstyle (numpy convention)
+]
+ignore = [
+    "D105", # magic methods need no docstring
+    "D107", # parameters are documented in the class docstring (scikit-learn style)
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "numpy"
+
+[tool.ruff.lint.per-file-ignores]
+"tests/**" = ["D"]

pypu_learn-0.0.1/src/pypu/__init__.py

@@ -0,0 +1,24 @@
+"""PyPU: positive-unlabeled (PU) learning in Python.
+
+PU learning trains a binary classifier from positive examples and unlabeled examples
+(a mix of positives and negatives), without any example labeled negative. PyPU collects
+PU learning methods behind one scikit-learn style interface: every model is fitted with
+``fit(X, s)``, where ``s[i] == 1`` marks a labeled positive and ``s[i] == 0`` an unlabeled
+sample.
+
+Subpackages
+-----------
+models
+    The PU classifiers, e.g. ``from pypu.models import NaivePU``.
+utils
+    Input validation and helpers shared by the models.
+"""
+
+from pypu.utils import show_versions
+
+try:
+    from pypu._version import __version__
+except ImportError:  # pragma: no cover - only when running from a source tree without installing
+    __version__ = "0.0.0+unknown"
+
+__all__ = ["__version__", "show_versions"]

pypu_learn-0.0.1/src/pypu/_version.py

@@ -0,0 +1,24 @@
+# file generated by vcs-versioning
+# don't change, don't track in version control
+from __future__ import annotations
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+version: str
+__version__: str
+__version_tuple__: tuple[int | str, ...]
+version_tuple: tuple[int | str, ...]
+commit_id: str | None
+__commit_id__: str | None
+
+__version__ = version = '0.0.1'
+__version_tuple__ = version_tuple = (0, 0, 1)
+
+__commit_id__ = commit_id = None