fmcquillan99 commented on issue #441: Kmeans: simplified silhouette per point 
for k-means
URL: https://github.com/apache/madlib/pull/441#issuecomment-532002100
 
 
   > It means the closes centroid was 1 and the second closest centroid was 0.
   
   I see.  May I suggest we add a separate column instead?
   ```
   Output 
   For the average function, a single value for simple silhouette score is 
returned. For the per-point function, the output table contains the following 
columns:
   
   pid  
   INTEGER. Point ID.
   
   centroid_id  
   INTEGER. The cluster that the point is assigned to.
   
   neighbor_centroid_id 
   INTEGER. The next closest cluster to the one that the point is assigned to.
   
   simple_silhouette    
   DOUBLE PRECISION. Simplified silhouette score for the point.
   ```

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to