Notebooks and libraries for spatial/geo Python explorations
Spatial Modelling for Data Scientists
MGWR 2.0 Software
A C++ library for building geographically weighted models.
Draw map boundaries your data supports instead of inheriting ones that don't fit. spatialkit tessellates point observations into Voronoi, hex, grid or Delaunay cells, aggregates to them with autocorrelation-aware standard errors, and fits GWR, Bayesian GP or random-forest models validated by spatial cross-validation.
Computational Improvements to Multi-scale Geographically Weighted Regression (MGWR)
Compared Ordinary Least Square (OLS) and Geographically Weighted Regression (GWR) using R programming with interpretation
Spatial Autoregressive Geographically Weighted Regression (SARGWR) implemented in Python.
Geographically Weighted Negative Binomial Regression in Python - local spatial modeling for over dispersed count data.
Open research companion: mapping daytime urban heat exposure across Local Climate Zones with cloud-local data cubes, multi-scale MGWR, and neighbourhood-level heat-justice planning in Izmir, Turkiye. Manuscript under review at Cities.
Multiscale GWR insurance risk pricing model for LA County. Full spatial regression progression: OLS -> Spatial Error -> GWR -> MGWR, with per-variable bandwidth analysis, significance-masked coefficient maps, LISA clustering, and an interactive Folium dashboard. FEMA, Census ACS, NIFC & OSM data.
A visual and spatial analysis of London's Airbnb market using K-Means clustering and Geographically Weighted Regression (GWR).
Comparing a global Ordinary Least Squares (OLS) to a Multiscale Geographically Weighted Regression (MGWR) model. R code is provided for those interested in creating local parameter maps.
The factors influencing stunting in East Java in 2022 are analyzed using Geographically Weighted Regression (GWR) using R Studio
(In development) Interactive mapping project for political marketers to spot election precincts with diverging voting results on two similar progressive issues. In addition, marketers can flag those precincts and leave comments.
Evaluate the equity of the change in tree canopy cover across New York City.
Predicting neighbourhood deprivation change across Glasgow
Spatial Statistical analyses created using R and RStudio for an "Advanced Statistics for Urban Applications" at Temple University
To associate your repository with the geographically-weighted-regression topic, visit your repo's landing page and select "manage topics."