ydata-profiling icon indicating copy to clipboard operation
ydata-profiling copied to clipboard

Boxplot to show relationship between a real value vs categorical values

Open trungtly opened this issue 3 years ago • 1 comments

Missing functionality

In a dataset for regression problem, we want to know the relationship between the numerical target and all other features. Currently pandas-profiling show the correlation / interaction between numerical values only. No correlation plot is available for categorical values.

Proposed feature

Generate the plot between a target column and categorical columns, similar to the boxplot from seaborn https://seaborn.pydata.org/examples/grouped_boxplot.html

Alternatives considered

Additional context

trungtly avatar Feb 15 '22 05:02 trungtly

The correlation between categorical-categorical and categorical-numerical are already available (e.g. check the Phik correlation)! Regarding the interactions however, there are indeed multiple options to extend the functionality.

sbrugman avatar May 01 '22 20:05 sbrugman