Release Notes for PySAL 2.0 This release represents over 15 months of hard work on PySAL. It brings major transitions in the project together with many new enhancements, improved documentation, and many bug fixes and optimizations. <!-- markdown-toc start - Don't edit this section. Run M-x markdown-toc-generate-toc again --> **Table of Contents** - [Release Notes for PySAL 2.0](#release-notes-for-pysal-20) - [Major Changes](#major-changes) - [Entirely New Packages](#entirely-new-packages) - [Significant Enhancements to Existing Packages](#significant-enhancements-to-existing-packages) - [Changes by Package](#changes-by-package) - [libpysal](#libpysal) - [esda](#esda) - [giddy](#giddy) - [inequality](#inequality) - [pointpats](#pointpats) - [spaghetti](#spaghetti) - [mapclassify](#mapclassify) - [splot](#splot) - [spreg](#spreg) - [spglm](#spglm) - [spint](#spint) - [mgwr](#mgwr) - [spvcm](#spvcm) - [Summary Statistics](#summary-statistics) - [Package Activity](#package-activity) - [Contributor Activity](#contributor-activity) - [Contributor by Package Activity](#contributor-by-package-activity) <!-- markdown-toc end --> <a name="major-changes"></a> Major Changes This release, we've had a ton of activity in PySAL, much of which has been conducted in our subpackages, the independently-released components of our library. Because it is too onerous to list all the changes to the API here, please consult the Migrating to PySAL 2.0 page for a detailed discussion of all reorganization-related changes. This document will focus only on improvements to functionality, enhancements, and additional modules added to 2.0, over and above the last stable release of the 1.0 series, PySAL 1.14.4. <a name="entirely-new-packages"></a> Entirely New Packages For starters, we've added some entirely-new subpackages to this release candidate: mgwr, the multi-scale Geographically-weighted regression package for Python. Don't worry, mgwr fits single-scale geographically-weighted regressions, too. Geographically-weighted regression is a kind of generalized additive model that uses kernel functions in the geographic area around each observation to predict outcomes at that area more accuratly, kind of like Gaussian Process regression for geographic data. spvcm, for spatially-correlated multilevel models. Spatially-correlated multilevel models are models that allow for random effects of nearby areas, regions, or groups to be correlated with one another. This is a Gibbs sampling framework plus diagnostics & plotting tools for general Bayesian analysis of Gibbs samplers. The package also contains simple tools to implement new samplers on top of the infrastructure provided, which is fast, parallel, serializable, iterative-write, and interruptible. spint, for estimating spatial interaction models, such as the production-constrained or consumption-constrained gravity models. spglm, a package for fitting sparse GLMs, focused on performance over sparse categorical data. splot, for spatial vizualization in Python, built on top of the excellent geopandas. This is headed by our Google Summer of Code (2018) student, Stefanie Lumnitz, and will be ongoing throughout the release candidate maturation cycle. pointpats, a package for the statistical analysis of point patterns, geographical colocation, and dispersion. <a name="significant-enhancements-to-existing-packages"></a> Significant Enhancements to Existing Packages We've also had a ton of activity adding new features in our submodules: alpha shapes, a fast implementation (numba-enabled) of the original algorithm generalizing convex hulls to allow for non-convex hulls Contiguity weights from voronoi tesselations/delaunay triangulation graphs for point patterns Fuzzy contiguity weights, for polygonal data where planarity is not strictly enforced (provided in part by geopandas) A family of spatially explicit indicators of mobility association including the inter- and intra-regional indicators as well as the local indicators. The inter- and intra-regional indicators provide a meso-level view on the exchange mobility pattern, shedding light on specific regions hosting frequent rank exchanges while the local indicators examine the concordance relationship between a focal spatial unit and its neighbors for revealing the role of space in shaping the exchange mobility pattern over time. Categorical Spatial Markov, a generalization of the Spatial_Markov class previously implemented to interrogate the role of space in shaping regional income distribution dynamics to incorporate direct variables. Here, the categorical spatial lag is adopted for formalizing the neighborhood. Connected Components checks for our spatial graph matrices Pandas Adjacency list constructors and NetworkX adapters for PySAL graph objects Attach islands, tooling to merge isolated observations into existing spatial graphs Construct Contiguity graphs from linestrings, allowing for easy and fast access to road network data in PySAL <a name="changes-by-package"></a> Changes by Package Overall, there were 1636 commits that closed 368 issues, together with 236 pull requests since our last release on 2017-11-03. <a name="libpysal"></a> libpysal weights.distance.KNN.from_dataframe ignoring radius (#116) Always make spherical KDTrees if radius is passed (#117) [ENH] should weights.util.get_ids() also accept a geodataframe? (#97) enh: add doctests to travis (#2) (#112) sphinx docs need updating (#49) Add notebooks for subpackage contract (#108) Api docs complete (#110) Doctests and start of documentation for libpysal (#109) Add dependencies to requirements_plus.txt for test_db (#107) Weights/util/get ids gdf (#101) missing adjustments to lower case module names (#106) Rel.4.0.0 (#105) REL: 3.0.8 (#104) error importing v3.0.7 (#100) Lower case module names (#98) remove function regime_weights (#96) depreciating regime_weights in the new release? (#94) inconsistency in api? (#93) Ensure consistency in from .module import * in components of libpysal (#95) [WIP] cleanup (#88) docstrings for attributes are defined in properties (#87) docstrings in W class need editing (#64) version name as version (#92) remove del statements and modify alphashape all (#89) libpysal/libpysal/cg/init.py not importing rtree (#90) including rtree in imports (#91) BUG: test_weights_IO.py is using pysal and hard-coded paths (#85) fix hardcoded swm test (#86) check for spatial index if nonplanar neighbors (#84) nonplanar_neighbors fails when sindex is not constructed. (#63) increment version number and add bugfixes, api changes (#79) Spherebug (#82) only warn once for islands/disconnected components (#83) only warn on disconnected components if there are no islands (#81) LEP: Stuff/use pysal/network stuff to provide queen weights on linestring dataframes (#59) swm fix not ported forward from pysal. (#66) import scipy syntax typo in the new issue template (#68) deletion of extra spaces in warning message (#78) Nightli.es build permissions (#77) name of geometry column is hardcoded in nonplanar_neighbors (#75) changed geometry column name from a str to an attribute (#76) Missing example file (#71) if numba isn't present, libpysal warns every time imported (#73) add check for disconnected components (#65) clean up for release (#74) update for new examples (#72) Swm (#70) Remaining concerns left unfixed in #61 (#62) [WIP] Alpha shapes (2D) code (#58) [WIP]: add linestring/multilinestring functionality (#61) Fuzzy contiguity (#57) add berlin example (#56) force UTF8 encoding for the long description read (#55) add guerry example dataset (#45) update georgia shapefile (#53) fix typo add non_planar_joins instead of non_planar_neighbor attr… (#54) add voronoi to the API (#46) ENH: Neighbor detection for nonplanar enforced polygon collections. (#51) Missing example used by gwr tests (#43) Wplot (#50) close the door on 2 for libpysal (#44) To networkx argument name changed (#40) bump micro version (#42) fix networkx adapters (#41) minor version bump for release (#39) Plot weights (#38) forward port of legacy fix #1028 (#37) Adding Voronoi generator for cg as well as Voronoi weights from 2-d points (#36) bump version for release (#34) attach_islands correction: incorporate pr #32 (#33) change data type of contiguity W.neighbors value from set to list (consistent with other weights) (#32) add a function to attach the nearest neighbor to island (#30) fix id2i lookup for string names and make better names (#31) two modules "Wsets.py" and "util.py" depend on each other (#26) add unittest for Wset.w_clip (#29) resolve circular import in Wsets and util (#28) update doctests in weights module to use libpysal instead of pysal (#27) bump stable date (#25) bump version for point release of lag cat fix (#24) <a name="esda"></a> esda enh: updating travis build and rtd (#40) BUG: missing rtd file (#39) REL: 2.0.1 (#38) Prepping for a doc release (#37) docstrings are using pysal legacy (#4) add zenodo doi badge (#36) REL: 2.0.0 (#34) Changing esda setup to handle version programatically (#33) port legacy esda fix for 1013 (#12) notebook links broken (#29) include /tests in release (#32) Add tests to release (#27) Accounting for incoming API changes to libpysal and adding testing against libpysal's master branch (#26) no varnames in Moran_BV_matrix (#22) add .varnames attribute to Moran_BV objects in Moran_BV_Matrix results (#23) Inconsistent metadata in setup.py (#28) Update license (#30) esda has no readme (#14) Readme added (#25) move api into init and remove api (#24) .z attribute divided by standard deviation (#21) offer standardised and non-standardised .z, .x and .y attributes (#20) get sjsrey's changes into a release (#16) esda's namespace is broken (#17) update api.py (#18) Update docstrings to use libpysal not pysal (#13) esda needs an api.py module (#9) chore: Update setup for 3+ (#15) Master (#10) <a name="giddy"></a> giddy remove giddy.api in README.rst (#66) chore: update for libpysal lower case module name changes (#65) remove api.py (#62) set up travis dual testing against mapclassify and esda (#63) replace libpysal.api imports with new imports in markov.py and `d…