python-pynndescent 0.5.2+dfsg-1 source package in Ubuntu
Changelog
python-pynndescent (0.5.2+dfsg-1) unstable; urgency=medium * Team Upload. [ Andreas Tille ] * New upstream version * Exclude *.pyc files from upstream source * Make package Architecture dependent to exclude 32bit architectures where the tests are failing * Remove empty boilerplate [ Nilesh Patra ] * d/rules: Enable build time tests respecting DEB_BUILD_OPTIONS * d/tests/control: Restrict testing architectures to supported build architectures * d/salsa-ci.yml: Do run build on i386 -- Nilesh Patra <email address hidden> Sat, 03 Jul 2021 23:45:46 +0530
Upload details
- Uploaded by:
- Debian Med
- Uploaded to:
- Sid
- Original maintainer:
- Debian Med
- Architectures:
- any-amd64 arm64 mips64el ppc64el s390x ia64 ppc64 riscv64 sparc64 alpha
- Section:
- misc
- Urgency:
- Medium Urgency
See full publishing history Publishing
Series | Published | Component | Section | |
---|---|---|---|---|
Jammy | release | universe | misc |
Downloads
File | Size | SHA-256 Checksum |
---|---|---|
python-pynndescent_0.5.2+dfsg-1.dsc | 2.4 KiB | 38f4205869167fd1f644b7728c5fad7a6098d756d4a6667f008c8771a78d7435 |
python-pynndescent_0.5.2+dfsg.orig.tar.xz | 934.8 KiB | 9d9608281140b4fcd521b07c3636c12aac77e2125e70ed144e11a7cf077910b6 |
python-pynndescent_0.5.2+dfsg-1.debian.tar.xz | 3.5 KiB | 417fa5f29cd16da0514c45d4fa2085f08e63aa7724949023c7e56c52ba02bd3e |
Available diffs
- diff from 0.5.1-2 to 0.5.2+dfsg-1 (7.7 KiB)
No changes file available.
Binary packages built by this source
- python3-pynndescent: nearest neighbor descent for approximate nearest neighbors
PyNNDescent is a Python nearest neighbor descent for approximate nearest
neighbors. It provides a Python implementation of Nearest Neighbor
Descent for k-neighbor-graph construction and approximate nearest
neighbor search, as per the paper:
.
Dong, Wei, Charikar Moses, and Kai Li. "Efficient k-nearest neighbor
graph construction for generic similarity measures." Proceedings of the
20th international conference on World wide web. ACM, 2011.
.
This library supplements that approach with the use of random projection
trees for initialisation. This can be particularly useful for the
metrics that are amenable to such approaches (euclidean, minkowski,
angular, cosine, etc.). Graph diversification is also performed, pruning
the longest edges of any triangles in the graph.
.
Currently this library targets relatively high accuracy (80%-100%
accuracy rate) approximate nearest neighbor searches.