LearningJournal

import java.util.*;
    import org.apache.kafka.clients.producer.*;                                    
    public class SimpleProducer {                                    
        public static void main(String[] args) throws Exception{

            String key = "Key1";
            String value = "Value-1";
            String topicName = "SimpleProducerTopic";
                                    
            Properties props = new Properties();

LearningJournal

spark.range(100).repartition(1).write.mode("overwrite").csv("/tmp/test-1")

LearningJournal

 kafka-topics.sh --create --zookeeper localhost:2181 --replication-factor 1 --partitions 1 --topic test 

LearningJournal

sudo yum -y install java-1.8.0-openjdk

LearningJournal

#!/bin/bash
SBT_OPTS="-Xms512M -Xmx1536M -Xss1M -XX:+CMSClassUnloadingEnabled"
java $SBT_OPTS -jar `dirname $0`/sbt-launch.jar "$@"

LearningJournal

def doubler(i: Int) = { i * 2 }
(i: Int) => { i * 2 }

LearningJournal

wget -c --header "Cookie: oraclelicense=accept-securebackup-cookie" http://download.oracle.com/otn-pub/java/jdk/8u144-b01/090f390dda5b47b9b721c7dfaa008135/jdk-8u144-linux-x64.rpm     
yum localinstall jdk-8u121-linux-x64.rpm

LearningJournal

//load a text file from current directory
val flistRDD = sc.textFile("flist.txt")
//Check number of defaults partitions
flistRDD.getNumPartitions
//Reload with five partitions
val flistRDD = sc.textFile("flist.txt", 5)
//Count the number of elements in each partition
flistRDD.foreachPartition(
  p => println("Items in partition-" + p.count(y => true))
)

LearningJournal

import java.util.Scanner

LearningJournal

<p>
    Let me take you to <a href="https://www.google.com">Google</a>.
<p>