Python toolset for statistical comparison of machine learning models and human readers by/via @budamat

P-value and confidence intervals still give more insight into results than a raw performance measure (and are required by many journals). This post explains how to use Python code to compute confidence intervals and p-values comparing machine learning models and human readers.

This is a great article with clear examples and code fragments so that you can ace these two calculations in my Python code. Very helpful and worth a bookmark.