Kelly N. Bodwin
Kelly N. Bodwin
Hi, I wanted to open this issue before PR'ing, because maybe there's a good reason for the current setup that I'm not seeing. Short version: I think `add_predictions()` should have...
I recently found myself wishing for a pipe operator that sends 2 objects into the first 2 elements of a function. Much like how we have `purrr::map` and `purrr::map2`, it'd...
This is a niche feature I've always wanted. It might not fit with the goals of `pak`, but worth a try. I often want to have students in a class/workshop...
This is my writeup with some details about clustering (unsupervised learning) and how I envision that fitting into the `tidymodels` framework.
This is way down the road, just a reminder to myserf: it would be nice to have subclustering ability on an already-clustered object.
Discussion thread for community detection functions driven by `igraph`. Questions to ponder: - Which community detection/extraction methods should we focus on first? - What are the tuning parameters? - Is...
To think about for the future: Sometimes it might make sense to predict in batches. That is, `predict(c(x1, x2))` returns different results from `predict(x1), predict(x2)` This is relevant in hierarchical...
Discussion thread for implementation of Bayesian model-based clustering driven by `mclust()`. Tuning parameters: - Number of models/clusters - Types of models - Prior distribution(s) - Tons of control parameters! Other...
What metrics might we use to validate clusterings? Metrics that can be computed from a single cluster fit: - The within sum of squares to between sum of squares ratio,...
Thoughts on the "modes" in the recipes for unsupervised methods: - _partition_ : Each observation is assigned exactly one cluster. - _extraction_: The method returns extracted groups. Each observation may...