There is a newer version of umap-learnUniform Manifold Approximation and Projection (UMAP) is a dimension reduction technique that can be used for visualisation similarly to t-SNE, but also for general non-linear dimension reduction.
Accessing umap-learn 0.4.6-fosscuda-2020b
To load the module for umap-learn 0.4.6-fosscuda-2020b please use this command on the BEAR systems (BlueBEAR, BEARCloud VMs, and CaStLeS VMs):
module load umap-learn/0.4.6-fosscuda-2020b
There is a CPU version of this module: umap-learn 0.4.6-foss-2020b
BEAR Apps Version
For more information visit the umap-learn website.
This version of umap-learn has a direct dependency on: fosscuda/2020b numba/0.52.0-fosscuda-2020b Python/3.8.6-GCCcore-10.2.0 scikit-learn/0.23.2-fosscuda-2020b SciPy-bundle/2020.11-fosscuda-2020b
This version of umap-learn is a direct dependent of: cell2location/0.05-alpha-fosscuda-2020b
These versions of umap-learn are available on the BEAR systems (BlueBEAR, BEARCloud VMs, and CaStLeS VMs). These will be retained in accordance with our Applications Support and Retention Policy.
|Version||BEAR Apps Version|
Last modified on 28th July 2021