You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For binary data, it would be helpful to support the binary metric as implemented in dist(metric="binary"). Currently, the only way is to pass the dist object directly, which is very memory inefficient.
The text was updated successfully, but these errors were encountered:
The description in the doc for ?dist seems to be indicate that method = "binary" is the Jaccard/Tanimoto distance. Supporting this will require an alternative to Annoy, so it won't be happening any time soon, unfortunately.
Although not as convenient as full integration with uwot, rnndescent supports the Jaccard/Tanimoto coefficient with binary data. See the rnndescent article for details on using it with uwot.
For binary data, it would be helpful to support the binary metric as implemented in
dist(metric="binary")
. Currently, the only way is to pass thedist
object directly, which is very memory inefficient.The text was updated successfully, but these errors were encountered: