File tree Expand file tree Collapse file tree 1 file changed +6
-0
lines changed
Expand file tree Collapse file tree 1 file changed +6
-0
lines changed Original file line number Diff line number Diff line change @@ -16,6 +16,12 @@ HDBSCAN is ideal for exploratory data analysis; it's a fast and robust
1616algorithm that you can trust to return meaningful clusters (if there
1717are any).
1818
19+ **WARNING **: Numpy version 1.10.1 introduced `performance regressions in structured
20+ array access <https://github.com/numpy/numpy/issues/6467> `_ ; this does have
21+ a notable performance impact on hdbscan. Consider upgrading to a newer version,
22+ or downgrading in the meantime if performance counts. I will be working to
23+ ensure hdbscan performance regardless of this issue in coming releases.
24+
1925Based on the paper:
2026 R. Campello, D. Moulavi, and J. Sander, *Density-Based Clustering Based on
2127 Hierarchical Density Estimates *
You can’t perform that action at this time.
0 commit comments