Open nlahaye opened 2 years ago
This issue has been labeled inactive-30d
due to no recent activity in the past 30 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed. This issue will be labeled inactive-90d
if there is no activity in the next 60 days.
Is your feature request related to a problem? Please describe. I am currently using scikit-learn's version of BIRCH Clustering, but would like to port to cuML. I see there is currently no implementation of BIRCH.
Describe the solution you'd like A cuML implementation of BIRCH clustering
Describe alternatives you've considered For my research I have previously tested agglomerative clustering with all linkage types, spectral clustering, DBSCAN, BIRCH, and k-means. BIRCH clustering provides optimal results at the fastest speed. Agglomerative clustering with Ward's linkage performs well also, but is much slower.
Additional context Thank you much for your help!