How To Compare 2 Datasets With Pandas-profiling

A data quality use case with advanced EDA

Pandas-profiling compare report (screenshot by the author)

Visualization is the cornerstone of EDA. When facing a new, unknown dataset, visual inspection allows us to get a feel of the available information, draw some patterns regarding the data, and diagnose several issues that we might need to address. In that regard, Pandas Profiling has been the indispensable swiss-knife in every data scientist’s tool belt. In my past articles, I’ve mentioned how pandas profiling …

analytics data science datasets data visualization machine learning pandas pandas-profiling profiling tutorial