Faq python different results

From Eigenvector Research Documentation Wiki
Jump to navigation Jump to search
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

Issue:

Why am I seeing different results from ANNDL, ANNDLDA, UMAP, TSNE when using the same hyperparameters?

Possible Solutions:

Python's random seeding depends on the operating system (OS) used to generate the necessary random components that each method uses to compute results. We fix a random state for these methods, so results should be reproducible on your machine and other machines that use the same OS. This is not guaranteed across different OSes. See this issue being brought up with the creator of the umap-learn package for more details: https://github.com/lmcinnes/umap/issues/153.


Still having problems? Please contact our helpdesk at helpdesk@eigenvector.com