hakanilter

 INFO [2016-09-21 07:51:29,993] ({pool-2-thread-3} SchedulerFactory.java[jobStarted]:131) - Job remoteInterpretJob_1474444289992 started by scheduler org.apache.zeppelin.spark.SparkInterpreter1153170779
 INFO [2016-09-21 07:51:30,682] ({pool-2-thread-3} Logging.scala[logInfo]:58) - Starting job: take at NativeMethodAccessorImpl.java:-2
 INFO [2016-09-21 07:51:30,709] ({dag-scheduler-event-loop} Logging.scala[logInfo]:58) - Registering RDD 8 (take at NativeMethodAccessorImpl.java:-2)
 INFO [2016-09-21 07:51:30,712] ({dag-scheduler-event-loop} Logging.scala[logInfo]:58) - Got job 0 (take at NativeMethodAccessorImpl.java:-2) with 200 output partitions
 INFO [2016-09-21 07:51:30,712] ({dag-scheduler-event-loop} Logging.scala[logInfo]:58) - Final stage: ResultStage 1 (take at NativeMethodAccessorImpl.java:-2)
 INFO [2016-09-21 07:51:30,713] ({dag-scheduler-event-loop} Logging.scala[logInfo]:58) - Parents of final stage: List(ShuffleMapStage 0)
 INFO [2016-09-21 07:51:30,714] ({dag-scheduler-event-loop} Logging.sca

hakanilter

mvn clean package -DskipTests \
        -Pr \
        -Pspark-1.6 \
        -Psparkr \
        -Phadoop-2.6 \
        -Dspark.version=1.6.2 \
        -Dhadoop.version=2.6.0-cdh5.7.1 \
        -Dhbase.hbase.version=1.2.0-cdh5.7.1 \
        -Dhbase.hadoop.version=2.6.0-cdh5.7.1 \
        -Dhive.hive.version=1.1.0-cdh5.7.1 \

hakanilter

mvn clean package -DskipTests \
        -Phive \
        -Phive-thriftserver \
        -Pyarn \
        -Psparkr \
        -Phadoop-2.6 \
        -Dhadoop.version=2.6.0-cdh5.7.1 \
        -Dhive.hive.version=1.1.0-cdh5.7.1 \
        -Dhive.hadoop.version=2.6.0-cdh5.7.1

hakanilter

Stream<Supplier<String>> calls = list.stream().map(value -> () -> callMe(value));
List<String> results = calls
                .map(CompletableFuture::supplyAsync).collect(Collectors.toList())
                .stream()
                .map(CompletableFuture::join).collect(Collectors.toList());

hakanilter

/*
*  PyroCollector : Clickstream Collector Client
*  (c)2018 DataPyro.com
*/
// set your endpoint
var endPoint = "https://d1q9rxqnug6ou7.cloudfront.net/public/blank.gif?";
// collector
var pyroCollector = {
	collect: function(obj) {
		if (typeof(obj) !== undefined) {

hakanilter

/**
<properties>
  <sqlite4java.version>1.0.392</sqlite4java.version>
</properties>
 
<dependencies>
        <dependency>
            <groupId>com.almworks.sqlite4java</groupId>
            <artifactId>sqlite4java</artifactId>
            <version>${sqlite4java.version}</version>

hakanilter

SparkConf sparkConf = new SparkConf()
        .setAppName(JdbcDynamoDbExportJob.class.getSimpleName())
        .setMaster(config.getProperty("spark.master"));
JavaSparkContext jsc = new JavaSparkContext(sparkConf);
SQLContext sqlContext = new SQLContext(jsc);

// read from database
Properties properties = new Properties();
properties.setProperty("user", config.getProperty("jdbc.user"));
properties.setProperty("password", config.getProperty("jdbc.pass"));

hakanilter

var elasticsearch = require('elasticsearch');
var elastic = new elasticsearch.Client({
    host: 'localhost:9200',
    log: 'info'
});

var kafka = require('kafka-node'),
HighLevelConsumer = kafka.HighLevelConsumer,
client = new kafka.Client(),
consumer = new HighLevelConsumer(

hakanilter

#!/bin/bash

# install git
sudo yum install git

# maven
sudo wget http://repos.fedorapeople.org/repos/dchen/apache-maven/epel-apache-maven.repo -O /etc/yum.repos.d/epel-apache-maven.repo
sudo sed -i s/\$releasever/6/g /etc/yum.repos.d/epel-apache-maven.repo
sudo yum install -y apache-maven
mvn --version

hakanilter

Create a new instance, edit following file

sudo vim /etc/yum.repos.d/cassandra.repo

Add Cassandra repo

[cassandra]
name=Apache Cassandra
baseurl=https://www.apache.org/dist/cassandra/redhat/311x/