Stream-learn — open-source Python library for difficult data stream batch analysis

Stream-learn is a Python package compatible with scikit-learn and developed for the drifting imbalanced data stream analysis. Its main component generator, which allows producing synthetic that may incorporate each of three concept drift types (i.e., sudden, gradual incremental drift) in their recurring or non-recurring version, as well static dynamic class imbalance. The conducting experiments following established evaluation methodologies Test-Then-Train Prequential). Besides, estimators adapted classification have been implemented, including both simple classifiers state-of-the-art chunk-based online classifier ensembles. utilises its own implementations prediction metrics binary tasks to improve computational efficiency.