Output summary about mgwr HOT 9 CLOSED

I think I have one when I was writing the MGWR GUI a long time ago. Let me dig it.

from mgwr.

That would be great! Could be good to mention and highlight it in the JSS manuscript if we have it updated for both gwr/mgwr.

from mgwr.

Hi
I have previously made one summary function for the GUI, which is based on Wei's summary code and compatible with our current APIs.

It looks like this.

But two things not sure how to deal with:

1. Do we need to output summary for global regression? It makes sense to me to put the summary function into GWRResults class as GWRResults.summary. And maybe only output GWR results?

2. Since our interface takes numpy array, we do not have variable names, and they may be needed in the summary. Any solution?

from mgwr.

On 1, I think it would be good to have. Could utilize spglm, since its already a dependency and include with the output from GWRResults.summary.

On 2, I think it makes sense to have a field_name parameter that accepts a list of names either in the GWR class or to GWRResults.summary method. Could actually pass it to either of those two and use it if it is available. If not, could auto-generate placeholder names like x1, x2, x3, etc.

from mgwr.

Shipped with #18.
Hi @TaylorOshan, do you mind adding the aicc for global glm in spglm? I could only find aic and bic but not aicc. It would be easier if you could do a quick PR to spglm, I'm less familiar with that lib. It would be good to have the aicc in global regression summary output.

from mgwr.

I'm a bit apprehensive to add it to spglm because I don't think it is used for GLM's outside of the GWR framework. Perhaps we could generalize the AICc in diagnostics.py to also take a GLMResults class by adding a tr_S attribute?. Then the AICc could be computed on a global and GWR/MGWR models.

from mgwr.

Sure, if you could do that, I will push a new commit to include aicc for global model.

from mgwr.

Done in spglm/#7, should allow aicc to be calculated for GLMResults object.

from mgwr.

Satisfied by #18

from mgwr.