{"categories":[{"label":"GIS","url":"https://skillfed.io/packages/category/scientific-engineering-gis"}],"enrichment":{"capability":"Giddy provides methods for exploratory spatiotemporal data analysis, including directional LISA, spatial Markov chains, mobility measures, and sequence analysis to study how geospatial distributions evolve over time.","skillfed_tags":["spatial-statistics","time-series-analysis","regional-science"],"use_cases":["Analyze how regional income inequality evolves spatially over time using spatial Markov and directional LISA methods.","Detect directional spatial autocorrelation in economic or demographic variables to visualize spatial trends as rose diagrams.","Decompose regional mobility and rank changes to understand inter- and intra-regional economic dynamics.","Study sequence alignment in spatiotemporal trajectories to compare regional development paths.","Measure global and local indicators of mobility association to quantify how regions move relative to each other."],"what_it_does":"Giddy is a PySAL library for analyzing how geospatial distributions change over time. It implements statistical methods that explicitly account for spatial structure when studying temporal evolution\u2014directional LISA for detecting directional spatial autocorrelation in income or other variables, spatial Markov chains to model transitions between spatial regimes, and mobility measures to quantify rank changes across regions. It's built on scipy, libpysal, mapclassify, esda, and quantecon, and includes visualization support via matplotlib and seaborn.\n\nYou use giddy when you have time-stamped spatial data (e.g., regional income over decades, population density across years) and want to understand not just how values change, but how spatial patterns and regional relative positions shift. It's designed for researchers and analysts in economic geography, regional science, and spatial statistics who need to move beyond simple time-series or cross-sectional analysis.","worth_installing":"Yes. Giddy is actively maintained, has low install friction, carries a permissive BSD license, and fills a specific niche in spatiotemporal analysis. It's suitable if you work with regional or geographic time-series data and need methods that explicitly model spatial structure in distribution dynamics. Requires Python 3.12+."},"id":"giddy","links":{"html":"https://skillfed.io/packages/giddy","md":"https://skillfed.io/packages/giddy.md","pypi":"https://pypi.org/project/giddy/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-07-26","license_spdx":null,"license_treatment":"permissive","name":"giddy","python_support":"supports_current","summary":"PySAL-giddy for exploratory spatiotemporal data analysis"},"popularity":{"monthly_downloads":157061,"position":10766,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"2.3.9"}