GeoDa v1.20

Features:

1. Spatial validation

Spatial validation provides a collection of validation measures including (1) fragmentations (entropy, simpson), (2) join count ratio, (3) compactness (isoperimeter quotient) and (4) diameter.

Fragmentation is a measure of spatial validation of clusters. It includes:

1. entropy, which measures the fraction of observations in each cluster
2. entropy*, which is the standardized entropy measure
3. simpson, which is an index for diversity measure in each cluster
4. simpson*, which is the standardized simpson measure

For non-spatially constrained clusters, the validation also reports cluster_fragmentation, which is a list of Fragmentation objects for each cluster, or None for spatially constrained clusters.

JoinCountRatio is measure of join counts (the number of times a category is surrounded by neighbors of the same category) over the total number of neighbors after converting each category to a dummy variable. It includes:

1. neighbors, the total number of neighbors of elements in a cluster
2. join count, the total join count of elements in a cluster
3. ratio: the ratio of total join count over total neighbors

Compactness is a measure of isoperimeter quotient for each spatially constrained cluster. It includes:

1. area, the area of a cluster. For points, the convex hull is used to compute the area.
2. perimeter, the perimeter of a cluster. For points, the convex hull is used to compute the perimeter
3. isoperimeter_quotient, (4 * pi * area) / (perimeter^2)

Diameter is a measure of the longest shortest distance between any pairs in a cluster. It includes:

1. steps, the longest shortest distance between any pairs
2. ratio, the ratio of steps over the number of elements in the cluster

2. Make Spatial

Make spatially constrained clusters from spatially non-constrained clusters using the contiguity information from the input weights

3. SC K Means

Spatially constrained K Means clustering algorithm implemented.

4. Join Count Ratio for Unique Value Maps

Add join count ratio option for unique value maps

5. Block Weights

Add block weights option in the contiguity weights creation

6. Cluster Map Match

Compare two clustering results using cluster map match.

7. Windows Installer for lab environment

Create installer for Windows 7+, which can be used in a Windows Lab Environment.

8. Add installer for Apple M1

Fixes:

• Weights creation from polygons wrong: double precision epsilon was not handled in weights creation code.
• fix issue that 3D plot doesn't work on Mac OS with version > 1.18.0.6
• Update GeoDa-win7+.iss for issue MS 2015-2019 Redist problems #2360

GeoDa 1.18

Note: Version 1.18.0.0 with major updates on spatially constrained clustering (Hierarchical Methods, Partitioning Methods)
Please download version 1.18.0.0 from: https://geodacenter.github.io/download.html

See the latest lab notes by Dr. Luc Anselin:

• Spatial Clustering (1) - Spatializing Classic Clustering Methods https://geodacenter.github.io/workbook/9a_spatial1/lab9a.html
• Spatial Clustering (2) - Spatially Constrained Clustering, Hierarchical Methods https://geodacenter.github.io/workbook/9c_spatial3/lab9c.html
• Spatial Clustering (3) - Spatially Constrained Clustering, Partitioning Methods https://geodacenter.github.io/workbook/9d_spatial4/lab9d.html

New/updated features:

1. AZP Updates:

• AZP: add ARiSeL #2266 (see https://geodacenter.github.io/workbook/9d_spatial4/lab9d.html#arisel)
• AZP Tabu search (see https://geodacenter.github.io/workbook/9d_spatial4/lab9d.html#tabu-search-1)
• AZP Simulated Annealing (see https://geodacenter.github.io/workbook/9d_spatial4/lab9d.html#simulated-annealing)
• Update Minimum Bound on AZP

2. Max-p Updates:

• Reimplement max-p based on AZP (parallelized)
• max-p Greedy (see https://geodacenter.github.io/workbook/9d_spatial4/lab9d.html#greedy)
• max-p Tabu Search (see https://geodacenter.github.io/workbook/9d_spatial4/lab9d.html#tabu-search-2)
• max-p Simulated Annealing (see https://geodacenter.github.io/workbook/9d_spatial4/lab9d.html#simulated-annealing-2)

3. Spatially Constrained Hierarchical Clustering (SCHC) Updates:
(see https://geodacenter.github.io/workbook/9c_spatial3/lab9c.html#spatially-constrained-hierarchical-clustering-schc)

Add/update SCHC using Single/Average/Complete/Wards-linkage
The algorithm has been reimplemented based on Skater/Redcap

4. REDCAP Updates:
(see https://geodacenter.github.io/workbook/9c_spatial3/lab9c.html#redcap)

Add/update: FullOrder-WardsLinkage, FullOrder-SingleLinkage, Fullorder-AverageLinkage, Fullorder-CompleteLinkage, Firstorder-SingleLinkage

5. Language updates:
Spanish language (Thanks to Coro)
Russian language (Thanks to Venera Timiryanova)

Fixes:

1. Update Windows installer with Chinese language
2. Fix crash when using an empty column #2261
3. Fix "Heat Map" on Windows and Ubuntu #2263
4. Load incompatible Mat file in weights dialog will crash GeoDa #2265
5. Fix conditional boxplot crashes with time-grouped variables #2279
6. Fix a crash: when loading csv with empty coordinates as the second layer

GeoDa 1.16.0.16

Download version 1.16.0.16: https://geodacenter.github.io/download.html

bugfixes and some enhancement:

1. #2241 Add “Set as Unique Value” option in the conditional histogram
2. #2242 Quantile Lisa negative spatial autocorrelation; add more check to bivariate and co-location join count

GeoDa 1.16.0.12

Download version 1.16.0.12: https://geodacenter.github.io/download.html

bugfixes and some enhancement:

1. • Variable name contains "%" will crash LISA maps [Windows only] bug
2. • Heat Map behaves differently on Windows bug
3. • add Median spatial lag to the Spatial Lag tab in the Calculator enhancement
4. • [Distance Scatter Plot] Update LOESS setup UI enhancement
5. • Missing [OK] button in 'Spatial Assign' and 'Spatial Count' on Windows only bug
6. • bug: Save Spanning Tree does not work in REDCAP bug
7. • Change Map Transparency for basemap impacts the highlighting transparency enhancement
8. • bug: regression report with undefined/empty values

GeoDa 1.16

Download: https://geodacenter.github.io/download.html

Many bug fixes for 1.14 and

New features:

GIS features

1. Reprojection (specify projection when save)

2. Minimum Spanning Tree (MST)

3. Spatial Dissolve

4. Multi-Layer Support (Linked Multi-Layers, Automatic reprojection)

5. Spatial Assign/Spatial Count/ Spatial Join (multi-variables)

6. Heat map

Spatial Weights

7. Create weights from variables

8. Make (mutual) Symmetric weights

Local Spatial Autocorrelation

9. Median Local Moran

10. Univariate Quantile LISA

11. Multivariate Quantile LISA

12. Local Neighbor Match Test

Map/Plots/Table

13. Conditional Box plot

14. Distance Scatter plot with loess

15. Render numeric labels on map

16. Data transform: Standarize(MAD)/ Range Adjust/ Range Standardize

Dimension Reduction Methods

17. Multidimensional Scaling (MDS) 2D/3D, SMACOF

18. Spatial weights from MDS scatter plot

19. t-SNE (animation)

Cluster Analysis

20. K Medoids (FastPAM, FastCLARA, FastCLARANS)

21. Spectral Clustering with large scale sparse eigenvalue solver (k-nn, mutual k-nn, gaussian)

22. DBScan & DBScan*

23. Hierarchical DBScan (with linking Condensed Tree graph)

24. Spatial Constrained Hierarchical Clustering (SCHC)

25. AZP (greedy, simulated annealing, tabu search)

26. Skater/Redcap with max-p-regions solver

Internationalization

27. Russian

GeoDa 1.14.0.2

Note: add an emergent release 1.14.0.4 for macOS https://github.com/GeoDaCenter/geoda/releases/download/1.14.0.2/GeoDa1.14.0.4-Installer.dmg
This release includes a fix for an issue that GeoDa can't drag-n-drop to open a ESRI shapefile on macOS Catalina (10.15)

1.14.0.2 Release Notes:

1. Fix an issue of specifying CRS when exporting:
   When there is no projection information of the current dataset (e.g. no .prj file, or create points from a CSV table), specifying CRS when exporting to a vector data format doesn't generate a .prj file or related projection information.

2. Add Russian language support

3. Enhancement: some Chinese translations

4. Update Ubuntu build scripts for version Disco Dingo

5. Enhancement: allow resizing the Preference dialog, for low screen resolutions (e.g. 1024x768)

GeoDa 1.14.0

There have been many commits since 1.12.x. The primary focus of this release is on bug fixes and incremental improvements, however there is a usual lot of new features as well, including:

Cluster:

Add fast HDBSCAN method
Add Redcap methods
Add Local Join Count method
Add auto-weighting function
(GeoDa now has a suite of Spatially Constrained Cluster techniques, including skater, redcap, max-p, k-means, k-medians, k-medoids, and spectral clustering. )

Mapping:

Add multi-layer support (+ map boundary, point size, stroke/fill color, etc.)
Support HDPI on Mac OSX in all maps and plots
Add Map layout preview tools for saving map w/ legends and plots in high resolution
Add configurable Basemap options
Add re-projection function when exporting a map
Add Spatial join and spatial aggregation
Add colocation map

Weights:

Add social-weights creation
Add support for ArcGIS .swm format, Matlab .mat format
Add weights intersection and weights union
Add weights network graph, (minimum) spanning tree as weights and network graph

Internationalization:

Add internationalization framework
Chinese version and Spanish version

For Linux, GeoDa now supports Ubuntu 16.04 and 18.04 with GTK 3.0, which is more stable and has better rendering quality and performance.

Please download GeoDa 1.14 installers from https://geodacenter.github.io/

GeoDa 1.12.1.241

#1898 Fix bug: Table merge bug: integers with commas are cut off
Also add "Setup Number Formatting" to allow user to specify "thousand separator" and "decimal separator"
#1898 update fix with testing on merging feature
fix ui issue of weights creation dialog: When use low resolution projection (e.g. 640x480), the weights creation dialog can not be fully displayed, and a verticle scroll bar is needed in this case (as in other dialog e.g. k-means dialog)
fix a bug in spatial join (assign operation)
update build script on osx 10.7 for TSL1.2 support
update build scripts for Ubuntu 18.04

GeoDa 1.12.1.237

add "Dissolve" feature
add Hierarchical Map feature
cache.sqlite located in room directory on LInux #623
add "polygon" in "polygon" test in Spatial Join
update libcurl to support TLS1.2 (issue: can't load ESRI basemap)
add option "Save Minimum Spanning Tree" in Skater/Redcap
add infrastructure for a crowdsourcing internationalization project
update logic when saving a DBF file
crash related to field names with merged tables #1861
averages tool does not give variables in correct order #1862
update Multivariate Local Join Count->Co-location Join Count
Allow user to set display precision in map legend #1834
upgrade code logic to handle data with NULL geometry when creating weights
file name in weights file should be quoted
Custom breaks category editor do not 'stick' #1847
v217 won't read csv as 2nd layer #1843
Add CRS feature when save dataset
multi layer: pan seems to break connection #1806
Separate "Color for Category" to "Fill Color and Outline Color" in Map window #1838
feature request - metadata on saved classifications in Project File #1552
Allow user to set display precision in PCP #1833
update UI MDS-Weights creation
show selection and neighbors #1832
social weights function enhancement #1751
Table: editing is limited to 10 digits in a integer field #1819
bug in natural breaks #1829
Enhancement for Chinese translation #1809
bug: Standardize(MAD) computation is incorrect #1831
add Negative category in multivariate Local Geary cluster map #1830
EB Moran and Local Moran - enable saving standardized rates #1828
Table - stack: problem with edit variable properties #1810

GeoDa 1.12.1.201

fixes:
#1818 Edit String content in Table crashes GeoDa in V197
#1817 bounding box issue with multiple layers
#1810 Table - stack: problem with edit variable properties
#1809 Enhancement for Chinese translation
#1819 Table: editing is limited to 10 digits in an integer field
#1815 UI update for weights creation dialog when loading a table-only dataset
fix: converting column (string type) with numbers using comma as a decimal separator to real type.

enhancement: support case sensitive “variable names” on some data format e.g. ESRI shapefile)