mgwr
multiscale geographically weighted regression
Decision gist · record as of 2026-08-14
Yes. The package is production-stable, actively maintained, has no known vulnerabilities, and low installation friction. It fills a specialized but well-established niche in spatial statistics. Install it if you need to model geographic variation in regression relationships; skip it if your analysis is non-spatial or you need only global regression coefficients.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Low friction installation with a pure-Python wheel.
- The package depends on five established scientific libraries (scipy, numpy, libpysal, spglm, spreg) that are well-maintained and widely available.
- Maintenance is active with recent commits and production-stable status.
License · maintenance · safety
3-Clause BSD (permissive) — Licensed under 3-Clause BSD (permissive), so you can use, modify, and distribute the package freely in both open-source and commercial projects with minimal restrictions.
last release 2024-01-06 (951 days) · last repo commit 2026-04-05 · 432 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 101,811 downloads/mo, #12,914 on PyPI
Alternatives
Verify before relying
pip install mgwr
import mgwr.gwr as gwr
from mgwr.sel_bw import Sel_BW
# Prepare data: y (dependent), X (independent), coords (lat/lon)
bw = Sel_BW(coords, y, X).search()
model = gwr.GWR(coords, y, X, bw=bw).fit()- Whether parallel computing support requires additional setup or dependencies beyond the listed runtime packages.
- Performance characteristics and scalability limits for large spatial datasets.
- Availability and completeness of documentation for model diagnostics and covariate-specific inference workflows.
What it is and what it does
MGWR is a Python implementation of multiscale geographically weighted regression, a statistical method for modeling spatial relationships where regression coefficients vary across geographic locations. It extends traditional GWR by allowing different spatial scales (bandwidths) for different covariates, capturing the idea that some processes operate at finer or coarser geographic resolutions than others.
The package handles model calibration for Gaussian, Poisson, and binomial probability distributions; bandwidth selection via golden section or equal interval search; spatial prediction; and model diagnostics including multiple hypothesis test correction and local collinearity assessment. It builds on sparse generalized linear modeling (spglm) and integrates with the PySAL ecosystem (libpysal, spreg). Parallel computing is available for computationally intensive GWR and MGWR workflows.
Use it for
- Analyze how housing price determinants vary geographically—e.g., proximity to transit matters more in urban areas than rural ones.
- Model disease incidence or health outcomes across regions where risk factors operate at different spatial scales.
- Estimate local effects of environmental variables (pollution, temperature) on ecological or agricultural outcomes.
- Conduct spatial heterogeneity tests to determine whether a global regression model is appropriate or if local variation is significant.
- Generate spatially-varying predictions and confidence intervals for regression surfaces across a study region.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is production-stable, actively maintained, has no known vulnerabilities, and low installation friction. It fills a specialized but well-established niche in spatial statistics. Install it if you need to model geographic variation in regression relationships; skip it if your analysis is non-spatial or you need only global regression coefficients.
Install
mgwr on PyPI
Before you install
Low friction installation with a pure-Python wheel. The package depends on five established scientific libraries (scipy, numpy, libpysal, spglm, spreg) that are well-maintained and widely available. Maintenance is active with recent commits and production-stable status.
License in practice
Licensed under 3-Clause BSD (permissive), so you can use, modify, and distribute the package freely in both open-source and commercial projects with minimal restrictions.
Quickstart
pip install mgwr
import mgwr.gwr as gwr
from mgwr.sel_bw import Sel_BW
# Prepare data: y (dependent), X (independent), coords (lat/lon)
bw = Sel_BW(coords, y, X).search()
model = gwr.GWR(coords, y, X, bw=bw).fit()Verify before relying
- Whether parallel computing support requires additional setup or dependencies beyond the listed runtime packages.
- Performance characteristics and scalability limits for large spatial datasets.
- Availability and completeness of documentation for model diagnostics and covariate-specific inference workflows.
Package facts
| License | 3-Clause BSD permissive |
| Python support | Supports the current Python release >3.5 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packagesscipynumpylibpysalspglmspreg |
| Maintenance | Actively maintained 951 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 101,811 / month, #12,914 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: OSI Approved :: BSD LicenseProgramming Language :: PythonProgramming Language :: Python :: 3.6Programming Language :: Python :: 3.7Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: GIS |
Evidence: mgwr-2.2.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “geographically weighted regression”
- mgwrCalibrates multiscale and traditional geographically weighted…
- polars-olsPolars OLS provides Rust-optimized linear regression models (OLS,…
- spglmFits Gaussian, Poisson, QuasiPoisson, and Logistic generalized linear…
Give your agent the search over MCP, or paste the wish link into any chat.
More Scientific/Engineering packages
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
pandas provides fast, flexible data structures (Series and DataFrame) for loading, cleaning, transforming, and analyzing labeled or relational data in Python.
scipy provides numerical algorithms for mathematics, science, and engineering—including optimization, integration, linear algebra, Fourier transforms, signal and image processing, and ODE solvers—built on numpy arrays.
scikit-learn provides a comprehensive Python library for supervised and unsupervised machine learning, including classification, regression, clustering, dimensionality reduction, and model evaluation tools built on NumPy and SciPy.
Install it if you need to train, evaluate, or deploy supervised or unsupervised learning models.
dill extends Python's pickle module to serialize and deserialize a much wider range of Python objects, including functions, lambdas, classes, and interpreter sessions, to byte streams for storage or network transmission.
Multiprocess is an enhanced fork of Python's standard multiprocessing library that uses dill for better serialization, allowing you to spawn processes with a threading-like API and share complex objects between them.
Install it if you use multiprocessing and encounter pickle serialization limits with lambdas or complex objects.
See also spglm · spint · spreg · gmr · pysal · glum · dask-glm · statsmodels · gstools · SALib