Wei Kang

This is a nice feature. One additional thing to consider is whether we want the returned spatial weight matrix to be symmetric. For contiguity-based spatial weights, symmetry could be an...

This makes a lot of sense. One concern I have is regarding how this change will impact the property [`islands`](https://github.com/pysal/libpysal/blob/master/libpysal/weights/weights.py#L644). Will the out-degree islands be considered as `islands`?

> > Will the out-degree islands be considered as `islands`? > > Good question! By our current definition, [they would be](https://github.com/pysal/libpysal/blob/master/libpysal/weights/weights.py#L584) since their neighbor list is empty. This also means...

@rsbivand thank you for pointing this out! I think it is reasonable to make `quantecon` import conditional especially if pysal is planning to support Python 3.9 very soon. Since I...

I think maintainers can release the package on pypi. Having at least one maintainer in addition to the owner should be OK?

> 3. If this goes here, should `Tau_Local` go here, too? or, at least cross-listing them by importing giddy & adding them to an `esda.correlation` namespace? We all think it...

> hey @weikang9009 @sjsrey, with `giddy.rank.Tau_Local`, I don't see an explicit permutational inference strategy. Thinking about it, I'm not sure how to do this for a correlation coefficient: an observation...

Hi @emanuelemassaro @ocefpaf, I think the error is due to the fact that `geopandas` is a soft dependency for `mgwr`. In other words, we do not install `geopandas` on your...

Thanks for the explanation. I prefer to make it a soft dependency as `esda` is considered to be light-weighted to me and has a bunch of upstream packages (e.g. `giddy`)...

Makes good sense. I still think that it might be helpful to include the `standardization` option though we assume that it is simple and straightforward for the API users to...