<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>question Re: Fetch distinct values of a column in Dataframe using Spark in Support Questions</title>
    <link>https://community.cloudera.com/t5/Support-Questions/Fetch-distinct-values-of-a-column-in-Dataframe-using-Spark/m-p/174634#M136897</link>
    <description>&lt;P&gt;Yes i am doing the same. Below is my spark-submit command.
&lt;/P&gt;&lt;PRE&gt;spark-submit --class com.BreakpointPredictionDriver --master yarn-cluster --num-executors 4 --driver-memory 8g --executor-memory 8g --executor-cores 4 --name BreakPointPrediction --jars /usr/hdp/current/spark-client/lib/datanucleus-core-3.2.10.jar,/usr/hdp/current/spark-client/lib/datanucleus-api-jdo-3.2.6.jar,/usr/hdp/current/spark-client/lib/datanucleus-rdbms-3.2.9.jar hdfs://PROD1/testdata/spark-jobs/bp-preprocessing-assembly-1.0.0.jar --hbaseZookeeperQuorum 127.0.0.1 --hbaseZookeeperPort 2181&lt;/PRE&gt;</description>
    <pubDate>Mon, 15 Aug 2016 12:22:55 GMT</pubDate>
    <dc:creator>kaz_narasimhan</dc:creator>
    <dc:date>2016-08-15T12:22:55Z</dc:date>
  </channel>
</rss>

