explore_feature_map() function feedback

[pokrovskyy]

clsu22

• In addition, wrong input type for the dataframe argument should be a TypeError instead of a ValueError.
• This function is useful for numeric variables but seems to do nothing with categorical variables. I think you should clarify this in your function description. What's my suggestion is that you could also include categorical variables and use ANOVA test statistics or p-value to show the correlation between numeric variables and categorical variables. Also could do the chi-square test to find the correlation between two categorical variables. See my comment below

Keanna-K (for R, transitioned to Python)

• Consider adding an option for handling data frames that contain NA values. Currently, if this function is performed on a data frame that has NA values, the function still runs without throwing any errors or warnings but the pairwise Pearson Correlation is not shown for the corresponding columns.

[pokrovskyy]

On categorical data:

The categorical data visualization is complex as it is much dependent on the type of categorical data. How do you define if it is not just some textual data? Is it sequential?

Thus I believe the best solution would be to keep this function as is for now and let user partition their data at their discretion, and then run pairwise feature correlation / plot on each partition individually

[pokrovskyy]

Moved discussion on categorical features plotting to here #67