R & Space : GI Science with R
summary
R code reproduces a full workflow: ingest household travel surveys, build individual activity sequences, map hourly population locations, compute Duncan dissimilarity and Moran‑style spatial autocorrelation at each hour, and standardize with permutation tests. A MobileScope platform visualizes Paris hourly segregation, a nine‑class spatio‑temporal classification highlights central zones that mix and peripheral zones that stay segregated, and a sex‑segregation analysis across 20 French cities shows daytime increases with some extreme workplace sex ratios. Implementation uses R packages (spdep/Spatial* and ggplot) and runs end‑to‑end.
AI-written summary · about
chapters (8)
- 0:00Introduction to R and GIS
- 1:03PhD journey and software dilemma
- 4:29Using R for spatial analysis
- 8:39Daytime segregation research
- 13:17Spatial dependence package in R
- 16:01Visualizing segregation dynamics
- 18:18Standardizing segregation indexes
- 20:40Conclusion and future possibilities
related talks
20mSpatial data science in the Tidyverse
20mEmbracing R in the Geospatial Community
30mLocation Intelligence and Spatial Data Science: from geographic coordinates to business insights
22mUsing Python & R in Harmony
30mUnlocking Geospatial Data Science: A Strategic Overview
20m15 Years of R in Quantitative Finance
06mInsights in 5-D! (Using magic small-multiples layouts)
20mThe next million R users