UMAP-Learn

Overview

UMAP (Uniform Manifold Approximation and Projection) is a dimensionality reduction technique for visualization and general non-linear dimensionality reduction. Apply this skill for fast, scalable embeddings that preserve local and global structure, supervised learning, and clustering preprocessing.

When to Use This Skill

Use this skill when the user wants to:

• Project high-dimensional features or embeddings to 2-D/3-D for visualization.
• Reduce dimensionality before density-based clustering (HDBSCAN).
• Fit supervised, semi-supervised, parametric, or aligned UMAP models, or transform new data with a fitted model.
• Tune n_neighbors, min_dist, n_components, and metric, or make embeddings reproducible.

Does NOT Trigger