[jira] [Created] (IGNITE-9239) [ML] KMeansTrainer crashed if amount of possible clusters more than amount of partitions in dataset

[Anton Vinogradov (Jira)]

Aleksey Zinoviev created IGNITE-9239:
----------------------------------------

             Summary: [ML] KMeansTrainer crashed if amount of possible clusters more than amount of partitions in dataset
                 Key: IGNITE-9239
                 URL: https://issues.apache.org/jira/browse/IGNITE-9239
             Project: Ignite
          Issue Type: Bug
          Components: ml
            Reporter: Aleksey Zinoviev
            Assignee: Aleksey Zinoviev


How to reproduce?

Set the K parameter in KMeans Trainer to 100, and run KMeansClusterization Example

\

StackTrace is

Exception in thread "KMeansClusterizationExample-#44" java.lang.RuntimeException: java.lang.IllegalArgumentException: bound must be positive
 at org.apache.ignite.ml.clustering.kmeans.KMeansTrainer.fit(KMeansTrainer.java:112)
 at org.apache.ignite.ml.clustering.kmeans.KMeansTrainer.fit(KMeansTrainer.java:46)
 at org.apache.ignite.ml.trainers.DatasetTrainer.fit(DatasetTrainer.java:68)
 at org.apache.ignite.examples.ml.clustering.KMeansClusterizationExample.lambda$main$0(KMeansClusterizationExample.java:60)
 at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.IllegalArgumentException: bound must be positive
 at java.util.Random.nextInt(Random.java:388)
 at org.apache.ignite.ml.clustering.kmeans.KMeansTrainer.initClusterCentersRandomly(KMeansTrainer.java:193)
 at org.apache.ignite.ml.clustering.kmeans.KMeansTrainer.fit(KMeansTrainer.java:86)
 ... 4 more

 

 

The possible solution :

correct the mechanism of rndPnts computation in the row 180-190 in KMeansTrainer



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)