Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Print segment name in Segmented MNL summary tables #59

Open
mxndrwgrdnr opened this issue Nov 13, 2018 · 3 comments
Open

Print segment name in Segmented MNL summary tables #59

mxndrwgrdnr opened this issue Nov 13, 2018 · 3 comments

Comments

@mxndrwgrdnr
Copy link
Member

Not sure if this should be done in choicemodels where the summary_table() object in created (here) or as a filler in between summary tables in the for loop here, but it would be super helpful to have the segments names shown when all submodels are being fitted.

@smmaurer
Copy link
Member

Ah, good point. More generally, it would probably be helpful to print the table names and data filters whenever we're fitting any kind of model. (And since the segmentation is implemented as filters, that would automatically handle this case.)

Approach 1: add to the top part of the summary table

  • makes sense from a ux perspective, since this info is a basic complement to things like the model expression, sample size, etc.
  • this would include it in the saved summary table, which would be nice: clearer record of what data the model was last estimated with, in case the table settings are changed
  • not too hard to implement, at least for models like MNL where we generate the summary table
  • probably not feasible right now for OLS or binary logit, since the summary tables come from Statsmodels

Approach 2: just use print statements or log messages

  • easier to implement, but not as nice for the user
  • good temporary solution for non-MNL models

@mxndrwgrdnr, does this fit with what you were thinking? I can work on it..

@mxndrwgrdnr
Copy link
Member Author

Ah, yes, that does make sense to think of it from the perspective of data filters. Approach 2 might be better for the time being then.

@smmaurer
Copy link
Member

PR #61 includes an implementation of Approach 2 above, for segmented MNL models only.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants