Here's a chronological timeline of posts. I've added a ● for the posts that I think are a bit more neat or some to have had more visitors.
-
The D-AI-LY: An Autonomous Statistical Digest
Replicating Statistics Canada's The Daily using Claude Code alongside dedicated tools and a skills-based harness.
-
Census Monkey Typewriter Part 2: from single agent to multi-agent
Assembling my own autonomous data blogging team: quality and workflow improvements from moving to a multi-agent workflow
-
A million monkeys doing data blogging - agentic social science with Claude Code and friends
An experiment in using LLMs to automate social science writing. Here's what I learned about LLM-assisted social science blogging.
-
Spatially constrained clustering and regionalization
A step-by-step guide to creating spatially-contiguous socioeconomic clusters in R using the SKATER algorithm
-
Will walk for food: exploring Singapore's hawker food density
How many hawker centres and stalls are a short walk away from me at any given location in Singapore? An interactive map, and a step-by-step guide of how it was made.
-
What is the most 'normal' city in Canada?
Using Census data to find which Canadian city best represents the national demographic mix
-
A look at the Vancouver mayoral race twitter picture
Using Twitter data and NLP tools to look at the timelines of the six most prominent candidates for Mayor of Vancouver
-
The CANSIM package, Canadian tourism, and slopegraphs
A quick introduction to the cansim R package using an interesting dataset about Canadian domestic tourism trends
-
Make better maps in R with vector tiles
Short tutorial for using and styling vector tiles in R for more flexibility with maps
-
Mirror images: city similarity with t-SNE
Using machine learning to find similar cities across many dimensions.