java.lang.NoClassDefFoundError: org/apache/spark/sql/DataFrame

Question

I am running my Spark code to save data to HBase in Amazon EMR 5.8.0 which has Spark 2.2.0 installed. Running in IntelliJ, it works fine but in EMR Cluster it is throwing me this error:

java.lang.NoClassDefFoundError: org/apache/spark/sql/DataFrame

Code

val zookeeperQuorum = args(0)
val tableName = args(1)
val inputPath = args(2)
val spark = SparkSession.builder
  .appName("PhoenixSpark")
  .getOrCreate

val df = spark.read
  .option("delimiter", "\001")
  .csv(inputPath)

val hBaseDf = spark.read
  .format("org.apache.phoenix.spark")
  .option("table", tableName)
  .option("zkUrl", zookeeperQuorum)
  .load()

val tableSchema = hBaseDf.schema
val rowKeyDf = df.withColumn("row_key", concat(col("_c3"), lit("_"), col("_c5"), lit("_"), col("_c0")))
rowKeyDf.createOrReplaceTempView("mytable")

val correctedDf = spark.sql("Select row_key, _c0, _c1, _c2, _c3, _c4, _c5, _c6, _c7," +
  "_c8, _c9, _c10, _c11, _c12, _c13, _c14, _c15, _c16, _c17, _c18, _c19 from mytable")
val rdd = correctedDf.rdd
val finalDf= spark.createDataFrame(rdd, tableSchema)

finalDf.write
  .format("org.apache.phoenix.spark")
  .mode("overwrite")
  .option("table", tableName)
  .option("zkUrl", zookeeperQuorum)
  .save()

spark.stop()

My pom.xml which is correctly mentioning Spark version as 2.2.0

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
     xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
     xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>

<groupId>org.myntra.analytics</groupId>
<artifactId>com.myntra.analytics</artifactId>
<version>1.0-SNAPSHOT</version>
<build>
    <plugins>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-compiler-plugin</artifactId>
            <configuration>
                <source>1.8</source>
                <target>1.8</target>
            </configuration>
        </plugin>
        <plugin>
            <groupId>org.scala-tools</groupId>
            <artifactId>maven-scala-plugin</artifactId>
            <executions>
                <execution>
                    <goals>
                        <goal>compile</goal>
                        <goal>testCompile</goal>
                    </goals>
                </execution>
            </executions>
        </plugin>
        <!-- "package" command plugin -->
        <plugin>
            <artifactId>maven-assembly-plugin</artifactId>
            <version>2.6</version>
            <configuration>
                <descriptorRefs>
                    <descriptorRef>jar-with-dependencies</descriptorRef>
                </descriptorRefs>
            </configuration>
            <executions>
                <execution>
                    <id>make-assembly</id>
                    <phase>package</phase>
                    <goals>
                        <goal>single</goal>
                    </goals>
                </execution>
            </executions>
        </plugin>
    </plugins>
</build>

<dependencies>
    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-core_2.11</artifactId>
        <version>2.2.0</version>
        <scope>provided</scope>
    </dependency>

    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-sql_2.11</artifactId>
        <version>2.2.0</version>
        <scope>provided</scope>
    </dependency>

    <dependency>
        <groupId>org.apache.spark</groupId>
        <artifactId>spark-hive_2.11</artifactId>
        <version>2.2.0</version>
        <scope>provided</scope>
    </dependency>

    <dependency>
        <groupId>org.apache.phoenix</groupId>
        <artifactId>phoenix-spark</artifactId>
        <version>4.11.0-HBase-1.3</version>
        <scope>provided</scope>
    </dependency>

</dependencies>

<pluginRepositories>
    <pluginRepository>
        <id>scala-tools.org</id>
        <name>Scala-tools Maven2 Repository</name>
        <url>http://scala-tools.org/repo-releases</url>
    </pluginRepository>
</pluginRepositories>

Here is the stacktrace from EMR logs which shows this error.

17/09/28 23:20:18 ERROR ApplicationMaster: User class threw exception: 
java.lang.NoClassDefFoundError: org/apache/spark/sql/DataFrame
java.lang.NoClassDefFoundError: org/apache/spark/sql/DataFrame
at java.lang.Class.getDeclaredMethods0(Native Method)
at java.lang.Class.privateGetDeclaredMethods(Class.java:2701)
at java.lang.Class.getDeclaredMethod(Class.java:2128)
at java.io.ObjectStreamClass.getPrivateMethod(ObjectStreamClass.java:1475)
at java.io.ObjectStreamClass.access$1700(ObjectStreamClass.java:72)
at java.io.ObjectStreamClass$2.run(ObjectStreamClass.java:498)
at java.io.ObjectStreamClass$2.run(ObjectStreamClass.java:472)
at java.security.AccessController.doPrivileged(Native Method)
at java.io.ObjectStreamClass.<init>(ObjectStreamClass.java:472)
at java.io.ObjectStreamClass.lookup(ObjectStreamClass.java:369)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1134)
at java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:43)
at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100)
at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:295)
at org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:288)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:108)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2287)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:370)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:369)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.map(RDD.scala:369)
at org.apache.phoenix.spark.PhoenixRDD.toDataFrame(PhoenixRDD.scala:131)
at org.apache.phoenix.spark.PhoenixRelation.schema(PhoenixRelation.scala:60)
at org.apache.spark.sql.execution.datasources.LogicalRelation$.apply(LogicalRelation.scala:77)
at org.apache.spark.sql.SparkSession.baseRelationToDataFrame(SparkSession.scala:415)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:172)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:146)
at com.mynra.analytics.chronicles.PhoenixSpark$.main(PhoenixSpark.scala:29)
at com.mynra.analytics.chronicles.PhoenixSpark.main(PhoenixSpark.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.yarn.ApplicationMaster$$anon$2.run(ApplicationMaster.scala:635)

Caused by: java.lang.ClassNotFoundException: org.apache.spark.sql.DataFrame
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:335)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
... 41 more

Answer 1

We encountered the same problem on Hortonworks HDP 2.6.3. The cause appears to be classpath conflict for the org.apache.phoenix.spark classes. In HDP, the Spark 1.6 version of this package is included in phoenix-client.jar. You need to override it by placing the Spark2-specific plugin phoenix-spark2.jar in front :

/usr/hdp/current/spark2-client/bin/spark-submit --master yarn-client --num-executors 2 --executor-cores 2 --driver-memory 3g --executor-memory 3g 
--conf "spark.driver.extraClassPath=/usr/hdp/current/phoenix-client/phoenix-spark2.jar:/usr/hdp/current/phoenix-client/phoenix-client.jar:/etc/hbase/conf" --conf "spark.executor.extraClassPath=/usr/hdp/current/phoenix-client/phoenix-spark2.jar:/usr/hdp/current/phoenix-client/phoenix-client.jar:/etc/hbase/conf" 
--class com.example.test phoenix_test.jar

Answer 2

I ran into this same issue and was even seeing it with spark-shell without any of my custom code. After some wrangling I think it is an issue with the Phoenix jars that are included with EMR 5.8 (and 5.9). I have no idea why their Phoenix client jar seems to have a class reference to org.apache.spark.sql.DataFrame since it was changed in Spark 2.0.0 to be an alias to DataSet[Row]. (Especially since their Phoenix jars claim to be 4.11 which should have this issue fixed.)

Below I have what I did that fixed it for me. I suspect you could also monkey with your build to not use the provided Phoenix but to jar up your local version as well.

What I did to get around it:

I. I copied my local Phoenix client jar to S3 (I had a 4.10 version laying around.)

II. I wrote a simple install shell script and also put that on S3:

aws s3 cp s3://<YOUR_BUCKET_GOES_HERE>/phoenix-4.10.0-HBase-1.2-client.jar /home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar

III. I created a bootstrap action that simply ran the shell script from Step 2.

IV. I created a JSON file to put this jar into the executor and driver classpaths for spark-default and put it in S3 as well:

[
    {
      "Classification": "spark-defaults",
      "Properties": {
          "spark.executor.extraClassPath": "/home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar:/etc/hadoop/conf:/etc/hive/conf:/usr/lib/hadoop-lzo/lib/*:/usr/share/aws/aws-java-sdk/*:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/*:/usr/share/aws/emr/emrfs/auxlib/*",
              "spark.driver.extraClassPath": "/home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar:/etc/hadoop/conf:/etc/hive/conf:/usr/lib/hadoop-lzo/lib/*:/usr/share/aws/aws-java-sdk/*:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/*:/usr/share/aws/emr/emrfs/auxlib/*"
      }
    }
]

5. When I went to create my cluster I referenced the full S3 path to my JSON file in the "Edit software settings (optional)" -> "Load JSON from S3" section of the AWS console.

After that I booted up my cluster and fired up a spark-shell. Below you can see the output from it, including the verbose classpath info showing my jar being used, and a DataFrame being successfully loaded.

[hadoop@ip-10-128-7-183 ~]$ spark-shell -v
Using properties file: /usr/lib/spark/conf/spark-defaults.conf
SLF4J: Class path contains multiple SLF4J bindings.
SLF4J: Found binding in [jar:file:/home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar!/org/slf4j/impl/StaticLoggerBinder.class]
SLF4J: Found binding in [jar:file:/usr/lib/spark/jars/slf4j-log4j12-1.7.16.jar!/org/slf4j/impl/StaticLoggerBinder.class]
SLF4J: See http://www.slf4j.org/codes.html#multiple_bindings for an explanation.
Adding default property: spark.sql.warehouse.dir=hdfs:///user/spark/warehouse
Adding default property: spark.executor.extraJavaOptions=-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=70 -XX:MaxHeapFreeRatio=70 -XX:+CMSClassUnloadingEnabled -XX:OnOutOfMemoryError='kill -9 %p'
Adding default property: spark.history.fs.logDirectory=hdfs:///var/log/spark/apps
Adding default property: spark.eventLog.enabled=true
Adding default property: spark.shuffle.service.enabled=true
Adding default property: spark.driver.extraLibraryPath=/usr/lib/hadoop/lib/native:/usr/lib/hadoop-lzo/lib/native
Adding default property: spark.yarn.historyServer.address=ip-10-128-7-183.columbuschildrens.net:18080
Adding default property: spark.stage.attempt.ignoreOnDecommissionFetchFailure=true
Adding default property: spark.resourceManager.cleanupExpiredHost=true
Adding default property: spark.yarn.appMasterEnv.SPARK_PUBLIC_DNS=$(hostname -f)
Adding default property: spark.driver.extraJavaOptions=-XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=70 -XX:MaxHeapFreeRatio=70 -XX:+CMSClassUnloadingEnabled -XX:OnOutOfMemoryError='kill -9 %p'
Adding default property: spark.master=yarn
Adding default property: spark.blacklist.decommissioning.timeout=1h
Adding default property: spark.executor.extraLibraryPath=/usr/lib/hadoop/lib/native:/usr/lib/hadoop-lzo/lib/native
Adding default property: spark.sql.hive.metastore.sharedPrefixes=com.amazonaws.services.dynamodbv2
Adding default property: spark.executor.memory=6144M
Adding default property: spark.driver.extraClassPath=/home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar:/etc/hadoop/conf:/etc/hive/conf:/usr/lib/hadoop-lzo/lib/*:/usr/share/aws/aws-java-sdk/*:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/*:/usr/share/aws/emr/emrfs/auxlib/*
Adding default property: spark.eventLog.dir=hdfs:///var/log/spark/apps
Adding default property: spark.dynamicAllocation.enabled=true
Adding default property: spark.executor.extraClassPath=/home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar:/etc/hadoop/conf:/etc/hive/conf:/usr/lib/hadoop-lzo/lib/*:/usr/share/aws/aws-java-sdk/*:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/*:/usr/share/aws/emr/emrfs/auxlib/*
Adding default property: spark.executor.cores=1
Adding default property: spark.history.ui.port=18080
Adding default property: spark.blacklist.decommissioning.enabled=true
Adding default property: spark.hadoop.yarn.timeline-service.enabled=false
Parsed arguments:
  master                  yarn
  deployMode              null
  executorMemory          6144M
  executorCores           1
  totalExecutorCores      null
  propertiesFile          /usr/lib/spark/conf/spark-defaults.conf
  driverMemory            null
  driverCores             null
  driverExtraClassPath    /home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar:/etc/hadoop/conf:/etc/hive/conf:/usr/lib/hadoop-lzo/lib/*:/usr/share/aws/aws-java-sdk/*:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/*:/usr/share/aws/emr/emrfs/auxlib/*
  driverExtraLibraryPath  /usr/lib/hadoop/lib/native:/usr/lib/hadoop-lzo/lib/native
  driverExtraJavaOptions  -XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=70 -XX:MaxHeapFreeRatio=70 -XX:+CMSClassUnloadingEnabled -XX:OnOutOfMemoryError='kill -9 %p'
  supervise               false
  queue                   null
  numExecutors            null
  files                   null
  pyFiles                 null
  archives                null
  mainClass               org.apache.spark.repl.Main
  primaryResource         spark-shell
  name                    Spark shell
  childArgs               []
  jars                    null
  packages                null
  packagesExclusions      null
  repositories            null
  verbose                 true

Spark properties used, including those specified through
 --conf and those from the properties file /usr/lib/spark/conf/spark-defaults.conf:
  (spark.blacklist.decommissioning.timeout,1h)
  (spark.blacklist.decommissioning.enabled,true)
  (spark.executor.extraLibraryPath,/usr/lib/hadoop/lib/native:/usr/lib/hadoop-lzo/lib/native)
  (spark.hadoop.yarn.timeline-service.enabled,false)
  (spark.executor.memory,6144M)
  (spark.sql.warehouse.dir,hdfs:///user/spark/warehouse)
  (spark.driver.extraLibraryPath,/usr/lib/hadoop/lib/native:/usr/lib/hadoop-lzo/lib/native)
  (spark.yarn.historyServer.address,ip-10-128-7-183.columbuschildrens.net:18080)
  (spark.eventLog.enabled,true)
  (spark.history.ui.port,18080)
  (spark.stage.attempt.ignoreOnDecommissionFetchFailure,true)
  (spark.yarn.appMasterEnv.SPARK_PUBLIC_DNS,$(hostname -f))
  (spark.executor.extraJavaOptions,-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=70 -XX:MaxHeapFreeRatio=70 -XX:+CMSClassUnloadingEnabled -XX:OnOutOfMemoryError='kill -9 %p')
  (spark.resourceManager.cleanupExpiredHost,true)
  (spark.shuffle.service.enabled,true)
  (spark.history.fs.logDirectory,hdfs:///var/log/spark/apps)
  (spark.driver.extraJavaOptions,-XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=70 -XX:MaxHeapFreeRatio=70 -XX:+CMSClassUnloadingEnabled -XX:OnOutOfMemoryError='kill -9 %p')
  (spark.sql.hive.metastore.sharedPrefixes,com.amazonaws.services.dynamodbv2)
  (spark.eventLog.dir,hdfs:///var/log/spark/apps)
  (spark.executor.extraClassPath,/home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar:/etc/hadoop/conf:/etc/hive/conf:/usr/lib/hadoop-lzo/lib/*:/usr/share/aws/aws-java-sdk/*:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/*:/usr/share/aws/emr/emrfs/auxlib/*)
  (spark.master,yarn)
  (spark.dynamicAllocation.enabled,true)
  (spark.executor.cores,1)
  (spark.driver.extraClassPath,/home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar:/etc/hadoop/conf:/etc/hive/conf:/usr/lib/hadoop-lzo/lib/*:/usr/share/aws/aws-java-sdk/*:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/*:/usr/share/aws/emr/emrfs/auxlib/*)


Main class:
org.apache.spark.repl.Main
Arguments:

System properties:
(spark.blacklist.decommissioning.timeout,1h)
(spark.executor.extraLibraryPath,/usr/lib/hadoop/lib/native:/usr/lib/hadoop-lzo/lib/native)
(spark.blacklist.decommissioning.enabled,true)
(spark.hadoop.yarn.timeline-service.enabled,false)
(spark.executor.memory,6144M)
(spark.driver.extraLibraryPath,/usr/lib/hadoop/lib/native:/usr/lib/hadoop-lzo/lib/native)
(spark.sql.warehouse.dir,hdfs:///user/spark/warehouse)
(spark.yarn.historyServer.address,ip-10-128-7-183.columbuschildrens.net:18080)
(spark.eventLog.enabled,true)
(spark.history.ui.port,18080)
(spark.stage.attempt.ignoreOnDecommissionFetchFailure,true)
(spark.yarn.appMasterEnv.SPARK_PUBLIC_DNS,$(hostname -f))
(SPARK_SUBMIT,true)
(spark.executor.extraJavaOptions,-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=70 -XX:MaxHeapFreeRatio=70 -XX:+CMSClassUnloadingEnabled -XX:OnOutOfMemoryError='kill -9 %p')
(spark.app.name,Spark shell)
(spark.resourceManager.cleanupExpiredHost,true)
(spark.shuffle.service.enabled,true)
(spark.history.fs.logDirectory,hdfs:///var/log/spark/apps)
(spark.driver.extraJavaOptions,-XX:+UseConcMarkSweepGC -XX:CMSInitiatingOccupancyFraction=70 -XX:MaxHeapFreeRatio=70 -XX:+CMSClassUnloadingEnabled -XX:OnOutOfMemoryError='kill -9 %p')
(spark.jars,)
(spark.submit.deployMode,client)
(spark.executor.extraClassPath,/home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar:/etc/hadoop/conf:/etc/hive/conf:/usr/lib/hadoop-lzo/lib/*:/usr/share/aws/aws-java-sdk/*:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/*:/usr/share/aws/emr/emrfs/auxlib/*)
(spark.eventLog.dir,hdfs:///var/log/spark/apps)
(spark.sql.hive.metastore.sharedPrefixes,com.amazonaws.services.dynamodbv2)
(spark.master,yarn)
(spark.dynamicAllocation.enabled,true)
(spark.executor.cores,1)
(spark.driver.extraClassPath,/home/hadoop/phoenix-4.10.0-HBase-1.2-client.jar:/etc/hadoop/conf:/etc/hive/conf:/usr/lib/hadoop-lzo/lib/*:/usr/share/aws/aws-java-sdk/*:/usr/share/aws/emr/emrfs/conf:/usr/share/aws/emr/emrfs/lib/*:/usr/share/aws/emr/emrfs/auxlib/*)
Classpath elements:



Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
17/10/11 13:36:05 WARN yarn.Client: Neither spark.yarn.jars nor spark.yarn.archive is set, falling back to uploading libraries under SPARK_HOME.
17/10/11 13:36:23 WARN metastore.ObjectStore: Version information not found in metastore. hive.metastore.schema.verification is not enabled so recording the schema version 1.2.0
17/10/11 13:36:23 WARN metastore.ObjectStore: Failed to get database default, returning NoSuchObjectException
17/10/11 13:36:23 WARN metastore.ObjectStore: Failed to get database global_temp, returning NoSuchObjectException
Spark context Web UI available at http://ip-10-128-7-183.columbuschildrens.net:4040
Spark context available as 'sc' (master = yarn, app id = application_1507728658269_0001).
Spark session available as 'spark'.
Welcome to
      ____              __
     / __/__  ___ _____/ /__
    _\ \/ _ \/ _ `/ __/  '_/
   /___/ .__/\_,_/_/ /_/\_\   version 2.2.0
      /_/

Using Scala version 2.11.8 (OpenJDK 64-Bit Server VM, Java 1.8.0_141)
Type in expressions to have them evaluated.
Type :help for more information.

scala> :paste
// Entering paste mode (ctrl-D to finish)

import org.apache.spark.SparkContext
import org.apache.spark.sql.SQLContext
import org.apache.phoenix.spark._
import org.apache.spark.sql.DataFrame

var sqlContext = new SQLContext(sc);
val phoenixHost = "10.128.7.183:2181"

// Exiting paste mode, now interpreting.

warning: there was one deprecation warning; re-run with -deprecation for details
import org.apache.spark.SparkContext
import org.apache.spark.sql.SQLContext
import org.apache.phoenix.spark._
import org.apache.spark.sql.DataFrame
sqlContext: org.apache.spark.sql.SQLContext = org.apache.spark.sql.SQLContext@258ff54a
phoenixHost: String = 10.128.7.183:2181

scala> val variant_hg19_df = sqlContext.load("org.apache.phoenix.spark", Map("table" -> "VARIANT_ANNOTATION_HG19", "zkUrl" -> phoenixHost))
warning: there was one deprecation warning; re-run with -deprecation for details
variant_hg19_df: org.apache.spark.sql.DataFrame = [CHROMOSOME_ID: int, POSITION: int ... 36 more fields]