A high performance implementation of HDBSCAN clustering.
BSD-3-CLAUSE License
Bot releases are hidden (Show)
Published by lmcinnes over 8 years ago
Boruvka scales poorly with dimension; by approximating the minimal spanning tree we can achieve far better scaling with dimension at the cost of slightly less accurate clustering. In testing the loss of accuracy seems very small, so I'm pushing it out with that defaulted to on.
Published by lmcinnes almost 9 years ago
Fix bugs introduced when working around numpy performance regression.
Published by lmcinnes almost 9 years ago
Setting upper condo building
Published by lmcinnes almost 9 years ago
Fix issues with 32 bit Windows installs
Fix issues caused by a performance regression in bumpy structured array accesses
Published by lmcinnes almost 9 years ago
Better performance
Fixes for Robust Single Linkage
Faster cluster extraction from trees
New Notebooks
Published by lmcinnes almost 9 years ago
Further optimization of routines that became bottlenecks due to the new faster minimum spanning tree algorithm. Reworking the calling of query on trees to optimize core distance computation in higher dimensional spaces.
Published by lmcinnes about 9 years ago