esda
esda copied to clipboard
pysal
statistics and classes for exploratory spatial data analysis
In addition to the `Lee` statistic in #51, we should also strive to add a few new statistics that have cropped up since PySAL was written: - [x] [LOSH](https://www.rdocumentation.org/packages/spdep/versions/1.1-2/topics/LOSH), for...
New functionality needs to be described in: - [api](https://pysal.org/esda/api.html) - [ tutorial](https://pysal.org/esda/tutorial.html)
Hello, If I understand correctly, the headbang triples spatial smoothing is not beign supported because the current one doesn't work too well in python 3. After reviewing, I think I...
Hello, I've been really impressed with the pysal library and especially the documentation I've found in the ongoing Geographic Data Science Book: https://geographicdata.science/book/. But I have a question that hasn't...
these are generally unusued, as user interaction decisions generally went in a different direction than what we thought back in 2014 when these were implemented. As their author, I'd like...
Is `geopandas` a hard dependency for `esda` now? [adbscan imports geopandas](https://github.com/pysal/esda/blob/master/esda/adbscan.py#L10): ```python from geopandas import GeoSeries ```
we should be able to exploit `numpy.subtract.outer` and elementwise matrix multiplication to do the Geary statistic in a much faster fashion than our current list comprehension. Something like: ```python numerator...
Correlation coefficients can also be "localized" as a LISA: ``` r[i] = (x[i]*y[i]) / numpy.sqrt((x**2).sum() * (y**2).sum()) ``` for any two variates `x`,`y`. This provides the "contribution" each site makes...
When testing esda against master in libpysal, one [test](https://travis-ci.org/pysal/esda/jobs/653937197#L872) is failing due to a change in https://github.com/pysal/libpysal/commit/9a303797dc68ad0db2c339ef54c2270a5950b5cc#diff-e8a3363e7d0110431da1549a5428007b having to do with what `.w.to_adjlist(remove_symmetric=True)` returns. Because the focal units that are...
For some reason, I have the Lee statistics tested locally (in a `esda/tests/test_lee.py` file) but that didn't make it into the repo. I've added that to #89