agentsclimarketplace

Umap dimensionality reduction starter

Skill ma-compbio-lab/SkillFoundry/skills/statistical-and-machine-learning-foundations-for-science/umap-dimensionality-reduction-starter

A framework for discovering, compiling, and validating reusable skills for scientific agents.

Install
npx -y skills add ma-compbio-lab/SkillFoundry --skill umap-dimensionality-reduction-starter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

0.8 KB, 161 tokens by cl100k_base, as published. Nobody here has run it

UMAP Dimensionality Reduction Starter

Use this skill to embed a tiny labeled feature matrix with UMAP and summarize the resulting 2D geometry.

What This Skill Does

  • reads a toy feature matrix with labels
  • computes a deterministic 2D UMAP embedding
  • summarizes per-label centroids and separation
  • emits machine-readable point coordinates for downstream plotting

Run

./slurm/envs/statistics/bin/python skills/statistical-and-machine-learning-foundations-for-science/umap-dimensionality-reduction-starter/scripts/run_umap_dimensionality_reduction.py --input skills/statistical-and-machine-learning-foundations-for-science/umap-dimensionality-reduction-starter/examples/toy_embedding_input.tsv --out scratch/statistics/umap_embedding_summary.json

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.