[
https://issues.apache.org/jira/browse/SPARK-2547?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Josh Rosen resolved SPARK-2547.
-------------------------------
Resolution: Fixed
Fix Version/s: 0.9.3
Target Version/s: (was: 0.9.2)
> The clustering documentaion example provided for spark 0.9.1/docs is having a
> error
> -----------------------------------------------------------------------------------
>
> Key: SPARK-2547
> URL: https://issues.apache.org/jira/browse/SPARK-2547
> Project: Spark
> Issue Type: Documentation
> Components: Documentation, Examples, MLlib, PySpark
> Affects Versions: 0.9.1
> Environment: All
> Reporter: Rahul K Bhojwani
> Labels: documentation, easyfix
> Fix For: 0.9.3
>
> Original Estimate: 1h
> Remaining Estimate: 1h
>
> The documentation example for MLlib Clustering contains Kmeans example.
> http://spark.apache.org/docs/0.9.1/mllib-guide.html#clustering-2
> Here this line mentioned below is wrong and misleading.
> clusters = KMeans.train(parsedData, 2, maxIterations=10,runs=30,
> initialization_mode="random")
> Look at the key parameter "initialization_mode" given in example. Its wrong
> as per the implementation of KMeans. It should be "initializationMode"
> Correction:
> clusters = KMeans.train(parsedData, 2, maxIterations=10,runs=30,
> initializationMode="random")
--
This message was sent by Atlassian JIRA
(v6.2#6252)
