Data
Download once; everything then works offline.
Every dataset used in the course is here, so nothing depends on a website being up during class. Each session’s lab zip also contains the data that lab needs.
All course data, sessions 1–2
(zip). Unzip it and copy the files from its
data-raw folder into data/raw/ in your course
folder.
| File | Rows × columns | Used in | What it is |
|---|---|---|---|
auto.csv |
392 × 9 | S1, S2 | Cars from the 1970s–80s: mpg, cylinders, weight, origin (1 = US, 2 = Europe, 3 = Japan). The classic Auto MPG teaching dataset |
auto_messy.csv |
392 × 9 | S2 | A version of auto.csv for session 2 |
titanic.csv |
891 × 12 | S2 exercise | Titanic passengers: survival, class, sex, age, fare |
| Register lab data | per pair | S3 | Synthetic Swedish-style register files (persons, firms, years); one dataset per pair. Posted before session 3 |
The register data are synthetic: generated by a script, with invented values and publicly documented variable names. No real person or firm is in them.