Hi Dalin,
It looks like Spark may have gone and broken their API again for Spark 2.0.
Could you file a JIRA ticket please?
Thanks,
Josh
On Mon, Sep 26, 2016 at 1:17 PM, dalin.qin <dalin...@gmail.com> wrote:
> Hi I'm trying some test with spark 2.0 together with phoenix 4.8 . My
> enviroment is HDP 2.5 , I installed phoenix 4.8 by myself.
>
> I got everything working perfectly under spark 1.6.2
>
> >>> df = sqlContext.read \
> ... .format("org.apache.phoenix.spark") \
> ... .option("table", "TABLE1") \
> ... .option("zkUrl", "namenode:2181:/hbase-unsecure") \
> ... .load()
>
> >>> df.show()
>
> +---+----------+
> | ID| COL1|
> +---+----------+
> | 1|test_row_1|
> | 2|test_row_2|
> +---+----------+
>
>
> But I got error "org.apache.spark.sql.DataFrame not existing " when
> loading data from phoenix table by using spark 2.0 (I've made sure that
> necessary jar files are in spark classpath) . I checked there is no such
> class in phoenix 4.8 . Can somebody check and update
> https://phoenix.apache.org/phoenix_spark.html for spark 2.0 usage?
>
>
> In [1]: df = sqlContext.read \
> ...: .format("org.apache.phoenix.spark") \
> ...: .option("table", "TABLE1") \
> ...: .option("zkUrl", "namenode:2181:/hbase-unsecure") \
> ...: .load()
> ------------------------------------------------------------
> ---------------
> Py4JJavaError Traceback (most recent call last)
> <ipython-input-1-e5dfb7bbb28b> in <module>()
> ----> 1 df = sqlContext.read .format("org.apache.phoenix.spark")
> .option("table", "TABLE1") .option("zkUrl", "namenode:2181:/hbase-unsecure")
> .load()
>
> /usr/hdp/2.5.0.0-1245/spark2/python/pyspark/sql/readwriter.pyc in
> load(self, path, format, schema, **options)
> 151 return self._df(self._jreader.load(
> self._spark._sc._jvm.PythonUtils.toSeq(path)))
> 152 else:
> --> 153 return self._df(self._jreader.load())
> 154
> 155 @since(1.4)
>
> /usr/hdp/2.5.0.0-1245/spark2/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py
> in __call__(self, *args)
> 931 answer = self.gateway_client.send_command(command)
> 932 return_value = get_return_value(
> --> 933 answer, self.gateway_client, self.target_id, self.name
> )
> 934
> 935 for temp_arg in temp_args:
>
> /usr/hdp/2.5.0.0-1245/spark2/python/pyspark/sql/utils.pyc in deco(*a,
> **kw)
> 61 def deco(*a, **kw):
> 62 try:
> ---> 63 return f(*a, **kw)
> 64 except py4j.protocol.Py4JJavaError as e:
> 65 s = e.java_exception.toString()
>
> /usr/hdp/2.5.0.0-1245/spark2/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py
> in get_return_value(answer, gateway_client, target_id, name)
> 310 raise Py4JJavaError(
> 311 "An error occurred while calling {0}{1}{2}.\n".
> --> 312 format(target_id, ".", name), value)
> 313 else:
> 314 raise Py4JError(
>
> Py4JJavaError: An error occurred while calling o43.load.
> : 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$$clean(ClosureCleaner.scala:288)
> at org.apache.spark.util.ClosureCleaner$.clean(
> ClosureCleaner.scala:108)
> at org.apache.spark.SparkContext.clean(SparkContext.scala:2037)
> at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:366)
> at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:365)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(
> RDDOperationScope.scala:151)
> at org.apache.spark.rdd.RDDOperationScope$.withScope(
> RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
> at org.apache.spark.rdd.RDD.map(RDD.scala:365)
> at org.apache.phoenix.spark.PhoenixRDD.toDataFrame(
> PhoenixRDD.scala:119)
> at org.apache.phoenix.spark.PhoenixRelation.schema(
> PhoenixRelation.scala:59)
> at org.apache.spark.sql.execution.datasources.
> LogicalRelation.<init>(LogicalRelation.scala:40)
> at org.apache.spark.sql.SparkSession.baseRelationToDataFrame(
> SparkSession.scala:382)
> at org.apache.spark.sql.DataFrameReader.load(
> DataFrameReader.scala:143)
> at org.apache.spark.sql.DataFrameReader.load(
> DataFrameReader.scala:122)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(
> NativeMethodAccessorImpl.java:62)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(
> DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498)
> at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:237)
> at py4j.reflection.ReflectionEngine.invoke(
> ReflectionEngine.java:357)
> at py4j.Gateway.invoke(Gateway.java:280)
> at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.
> java:128)
> at py4j.commands.CallCommand.execute(CallCommand.java:79)
> at py4j.GatewayConnection.run(GatewayConnection.java:211)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.lang.ClassNotFoundException:
> org.apache.spark.sql.DataFrame
> at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
> at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:331)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
> ... 45 more
>
>
>
