nannyml.drift.univariate package


Module contents

Univariate drift detection methods, considering a single column at a time.

Some methods are applicable exclusively to continuous or categorical columns, others are applicable to both.

This package currently holds an implementation for the following univariate drift detection methods:

  • Kolmogorov-Smirnov statistic (continuous)

  • Wasserstein distance (continuous)

  • Chi-squared statistic (categorical)

  • L-infinity distance (categorical)

  • Jensen-Shannon distance

  • Hellinger distance

For more information, check out the tutorial or the deep dive.

For help selecting the correct univariate drift detection method for your use case, check the method selection guide.