You can also also view the full archives of micro-posts. Longer blog posts are available in the Articles section.
Lovely. https://leon-kim.com/
eBay’s TSV Utilities: Command line tools for large, tabular data files. Filtering, statistics, sampling, joins and more.
Population genetics notes, from the the Coop Lab. #bioinformatics
Ezhil: Clean and minimal personal blog theme for Hugo.
Random Forests, Decision Trees, and Categorical Predictors: The “Absent Levels” Problem (PDF).
This problem occurs whenever there is an indeterminacy over how to handle an observation that has reached a categorical split which was determined when the observation in question’s level was absent during training.
TL;DR No feature engineering heuristics seem to really help mitigate this kind problem.
Old times good times: A Brief Timeline of the History of Blogging. Although I came late to the party (around 2006), I remember all those emerging blogs from the 2000s, I mean, before the advent of social networks. Then came Twitter, Blogger and Tumblr.
Want some training or refresh your TeX memory? https://texnique.xyz
Well, I finally updated my config for Doom Emacs, which now relies on straight to manage all packages. The first upgrade was quite buggy, but once I figured out I could just delete my current .emacs.d and start from scratch again, I got a working install in a few minutes. Beware that the process of downloading and configuring all packages is quite long. You will also likely need to update your autoloads, e.g., doom refresh -f. Also, if you have a problem rebuilding the pdf-tools viewer, eval this before running pdf-tools-install: (setenv "PKG_CONFIG_PATH" "/usr/local/lib/pkgconfig:/usr/local/Cellar/libffi/3.2.1/lib/pkgconfig"). #emacs