scada-python 0.1.0

Statistical Inference for k-means Clustering after Domain Adaptation

Statistical Inference for k-means Clustering after Domain Adaptation

This package provides a statistical inference framework for k-means clustering after domain adaptation (DA). It leverages the SI framework and employs a divide-and-conquer strategy to efficiently compute the p-value of selected features. Our method ensures reliable feature selection by controlling the false positive rate (FPR) while simultaneously maximizing the true positive rate (TPR), effectively reducing the false negative rate (FNR).

Installization

pip install PySCaDA

Usage

Follows the notebook examples in our Github repository: DAIR-Group/SCaDA