PyPU

Positive-unlabeled (PU) learning in Python, with a scikit-learn style API.

Status: pre-alpha. The common interface is in place and the methods are being ported. See the roadmap.

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 for outlier detection: import a model, fit it on PU data, and predict on new data.

Installation

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:

pip install git+https://github.com/izavits/PyPU.git

Quick start

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.

Models that need the class prior π = P(y = 1) take it as a prior parameter.

Methods

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 for the development setup, how to add a model, and the release process. Changes are listed in CHANGELOG.md.

Citing

If you use PyPU in your research, please cite it; GitHub's "Cite this repository" button uses CITATION.cff.

License

PyPU is distributed under the BSD 3-Clause License.