I'm working on association analysis on my dataset that consist majorly of categorical features and I'm using Cramers' V and Theils U statistical measures for showcasing the association metrics.
I have 2 questions related to the same :
If there are some missing values in some of the columns in my dataset, how should I handle them while calculation Cramers' V and theils u metrics? Shall I replace the missing value with some dummy value?
Note: I'm using python's python library for the calculation of both the metrics.
dython.nominal.cramers_v(data[field1],data[field2]) and dython.nominal.theils_u(data[field1],data[field2])
If I have a column name like "Task Creation Date" that consists of DateTime values. How can I include this field as part of my association analysis? Does Cramers' V and Theils U consider date values as input ? or some conversion is required?
Any help would be much appreciated.