lmcinnes/umap
Uniform Manifold Approximation and Projection
Combines fuzzy topological structure preservation with fast neighbor approximation via Numba JIT compilation and pynndescent, enabling scalable non-linear dimensionality reduction beyond visualization. Integrates seamlessly with scikit-learn's API while supporting optional density preservation (densMAP) and parametric variants via TensorFlow, with pluggable distance metrics and sparse matrix compatibility.
8,114 stars and 5,454,447 monthly downloads. Used by 78 other packages. Actively maintained with 20 commits in the last 30 days. Available on PyPI.
Stars
8,114
Forks
860
Language
Python
License
BSD-3-Clause
Category
Last pushed
Mar 10, 2026
Monthly downloads
5,454,447
Commits (30d)
20
Dependencies
6
Reverse dependents
78
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lmcinnes/umap"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
geomstats/geomstats
Computations and statistics on manifolds with geometric structures.
pyRiemann/pyRiemann
Machine learning for multivariate data through the Riemannian geometry of positive definite...
higra/Higra
Hierarchical Graph Analysis
pavlin-policar/openTSNE
Extensible, parallel implementations of t-SNE
giotto-ai/giotto-tda
A high-performance topological machine learning toolbox in Python