Evidently helps analyze machine learning models during validation or production monitoring. It generates interactive reports or JSON profiles from pandas
The tool currently works with tabular data. 6 reports are available.
Detects changes in feature distribution.
Detects changes in numerical target and feature behavior.
Detects changes in categorical target and feature behavior.
Analyzes the performance of a regression model and model errors.
Analyzes the performance and errors of a classification model. Works both for binary and multi-class models.
Analyzes the performance of a probabilistic classification model, quality of the model calibration, and model errors. Works both for binary and multi-class models.