Levi John Wolf

Hi, sorry for the delay on addressing this, but we're working to change implementations to [`pysal/region`](https://github.com/pysal/region), a separate package released as `region`. We hope to have this done by the...

Nope. A simple "asarray" would do it I think.

Yeah, this should be easy to do. We would need to allow for "dissimilarity='precomputed'", as is common in other sklearn-style estimators. As it stands @Shruthi-Patil, you could try using `sklearn.cluster.AgglomerativeClustering()`,...

Interesting.... well I can take a look at customizing this very soon. I think the diff would be about 6 lines.

If you'd like to try it on your data, use `pip install git+https://github.com/ljwolf/spopt` and follow the example above.

I am not sure I want to merge this unless more people beyond @Shruti-Patil find it useful.... In abstract, it seems like a good idea, and I'm all for user...

fyi, [geo support](http://nbviewer.jupyter.org/github/ljwolf/cenpy/blob/master/demo.ipynb#GEO-&-Tiger-Integration) is provided over in [cenpy](https://github.com/ljwolf/cenpy). I've looked into the machinery here, and what we're doing is quite different; `cenpy` automatically discovers & wraps all endpoints exposed by...

There's now a ton more geo support and a [better, place-oriented API](https://nbviewer.jupyter.org/github/cenpy-devs/cenpy/blob/master/notebooks/product-api.ipynb) over in `cenpy`. Would be great to get development efforts on the US Census Bureau's APIs consolidated in...

Would be happy to collaborate/merge where possible. I've just merged and released a better default variable explorer using dataframes in `cenpy`. More than happy to recommend `census` as a good...

That'd be a great contribution! I pieced together our current `_get_boundary_points` to allow for ducktyping of pysal polygons and shapely polygons as part of our migration to being able to...