Just want to provide more information on how I ran the examples. Environment: Cloudera quick start Vm 5.1.0 (HBase 0.98.1 installed). I created a table called 'data1', and 'put' two records in it. I can see the table and data are fine in hbase shell.
I cloned spark repo and checked out to 1.1 branch, built it by running sbt/sbt assembly/assembly sbt/sbt examples/assembly. The script is basically, if __name__ == "__main__": conf = SparkConf().setAppName('testspark_similar_users_v2') sc = SparkContext(conf=conf, batchSize=512) conf2 = {"hbase.zookeeper.quorum": "localhost", "hbase.mapreduce.inputtable": 'data1'} hbase_rdd = sc.newAPIHadoopRDD( "org.apache.hadoop.hbase.mapreduce.TableInputFormat", "org.apache.hadoop.hbase.io.ImmutableBytesWritable", "org.apache.hadoop.hbase.client.Result", keyConverter="org.apache.spark.examples.pythonconverters.ImmutableBytesWritableToStringConverter", valueConverter="org.apache.spark.examples.pythonconverters.HBaseResultToStringConverter", conf=conf2) output = hbase_rdd.collect() for (k, v) in output: print (k, v) sc.stop() The error message is, 14/09/10 09:41:52 INFO ZooKeeper: Initiating client connection, connectString=localhost:2181 sessionTimeout=180000 watcher=hconnection 14/09/10 09:41:52 INFO RecoverableZooKeeper: The identifier of this process is 25963@quickstart.cloudera 14/09/10 09:41:52 INFO ClientCnxn: Opening socket connection to server quickstart.cloudera/127.0.0.1:2181. Will not attempt to authenticate using SASL (unknown error) 14/09/10 09:41:52 INFO ClientCnxn: Socket connection established to quickstart.cloudera/127.0.0.1:2181, initiating session 14/09/10 09:41:52 INFO ClientCnxn: Session establishment complete on server quickstart.cloudera/127.0.0.1:2181, sessionid = 0x1485b365c450016, negotiated timeout = 40000 14/09/10 09:52:32 ERROR TableInputFormat: org.apache.hadoop.hbase.client.NoServerForRegionException: Unable to find region for data1,,99999999999999 after 10 tries. at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.locateRegionInMeta(HConnectionManager.java:980) at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.locateRegion(HConnectionManager.java:885) at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.locateRegionInMeta(HConnectionManager.java:987) at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.locateRegion(HConnectionManager.java:889) at org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation.locateRegion(HConnectionManager.java:846) at org.apache.hadoop.hbase.client.HTable.finishSetup(HTable.java:234) at org.apache.hadoop.hbase.client.HTable.<init>(HTable.java:174) at org.apache.hadoop.hbase.client.HTable.<init>(HTable.java:133) at org.apache.hadoop.hbase.mapreduce.TableInputFormat.setConf(TableInputFormat.java:96) at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:90) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:202) at org.apache.spark.rdd.MappedRDD.getPartitions(MappedRDD.scala:28) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:202) at org.apache.spark.rdd.RDD.take(RDD.scala:1060) at org.apache.spark.rdd.RDD.first(RDD.scala:1091) at org.apache.spark.api.python.SerDeUtil$.pairRDDToPython(SerDeUtil.scala:70) at org.apache.spark.api.python.PythonRDD$.newAPIHadoopRDD(PythonRDD.scala:441) at org.apache.spark.api.python.PythonRDD.newAPIHadoopRDD(PythonRDD.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379) at py4j.Gateway.invoke(Gateway.java:259) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:207) at java.lang.Thread.run(Thread.java:745) Traceback (most recent call last): File "/home/cloudera/workspace/recom_env_testing/bin/sparkhbasecheck.py", line 71, in <module> conf=conf2) File "/home/cloudera/workspace/spark/python/pyspark/context.py", line 471, in newAPIHadoopRDD jconf, batchSize) File "/usr/lib/python2.6/site-packages/py4j-0.8.2.1-py2.6.egg/py4j/java_gateway.py", line 538, in __call__ self.target_id, self.name) File "/usr/lib/python2.6/site-packages/py4j-0.8.2.1-py2.6.egg/py4j/protocol.py", line 300, in get_return_value format(target_id, '.', name), value) py4j.protocol.Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.newAPIHadoopRDD. : java.io.IOException: No table was provided. at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase.getSplits(TableInputFormatBase.java:152) at org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:94) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:204) at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:202) at scala.Option.getOrElse(Option.scala:120) at org.apache.spark.rdd.RDD.partitions(RDD.scala:202) -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/how-to-run-python-examples-in-spark-1-1-tp13841p13905.html Sent from the Apache Spark User List mailing list archive at Nabble.com. --------------------------------------------------------------------- To unsubscribe, e-mail: user-unsubscr...@spark.apache.org For additional commands, e-mail: user-h...@spark.apache.org