notebook.community

Edit and run

Start up Spark





In [1]:



    


import os
import sys

spark_home = '/opt/spark'
os.environ['SPARK_HOME'] = spark_home

sys.path.insert(0, os.path.join(spark_home, 'python'))
sys.path.insert(0, os.path.join(spark_home, 'python/lib/py4j-0.8.1-src.zip'))

execfile(os.path.join(spark_home, 'python/pyspark/shell.py'))



    


















    






Welcome to
      ____              __
     / __/__  ___ _____/ /__
    _\ \/ _ \/ _ `/ __/  '_/
   /__ / .__/\_,_/_/ /_/\_\   version 1.5.2
      /_/

Using Python version 2.7.10 (default, Oct 23 2015 18:05:06)
SparkContext available as sc, HiveContext available as sqlContext.

















In [8]:



    


from pyspark.mllib.random import RandomRDDs
from pyspark.sql.types import StructType, StructField, DoubleType



    











In [93]:



    


u = RandomRDDs.uniformVectorRDD(sc, 10, 4)
schema = StructType([StructField('att%d' % i, DoubleType(), False) for i in range(0, len(u.first()))])
u = u.map(lambda x: x.tolist()).map(lambda x: x.append(1))
df = sqlContext.createDataFrame(u, schema)
df.collect()



    


















    






---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-93-2e4f09e4ba2c> in <module>()
      4 u = u.map(lambda x: x.tolist()).map(lambda x: x.append(1))
      5 df = sqlContext.createDataFrame(u, schema)
----> 6 df.collect()

/opt/spark/python/pyspark/sql/dataframe.pyc in collect(self)
    277         """
    278         with SCCallSiteSync(self._sc) as css:
--> 279             port = self._sc._jvm.PythonRDD.collectAndServe(self._jdf.javaToPython().rdd())
    280         return list(_load_from_socket(port, BatchedSerializer(PickleSerializer())))
    281 

/Users/zoltanctoth/env/lib/python2.7/site-packages/py4j/java_gateway.pyc in __call__(self, *args)
    811         answer = self.gateway_client.send_command(command)
    812         return_value = get_return_value(
--> 813             answer, self.gateway_client, self.target_id, self.name)
    814 
    815         for temp_arg in temp_args:

/opt/spark/python/pyspark/sql/utils.pyc in deco(*a, **kw)
     34     def deco(*a, **kw):
     35         try:
---> 36             return f(*a, **kw)
     37         except py4j.protocol.Py4JJavaError as e:
     38             s = e.java_exception.toString()

/Users/zoltanctoth/env/lib/python2.7/site-packages/py4j/protocol.pyc in get_return_value(answer, gateway_client, target_id, name)
    306                 raise Py4JJavaError(
    307                     "An error occurred while calling {0}{1}{2}.\n".
--> 308                     format(target_id, ".", name), value)
    309             else:
    310                 raise Py4JError(

Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 101.0 failed 1 times, most recent failure: Lost task 1.0 in stage 101.0 (TID 169, localhost): java.lang.NullPointerException
	at org.apache.spark.api.python.SerDeUtil$$anonfun$toJavaArray$1.apply(SerDeUtil.scala:103)
	at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
	at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
	at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.next(SerDeUtil.scala:120)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.next(SerDeUtil.scala:111)
	at scala.collection.Iterator$class.foreach(Iterator.scala:727)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.foreach(SerDeUtil.scala:111)
	at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
	at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
	at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
	at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.to(SerDeUtil.scala:111)
	at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.toBuffer(SerDeUtil.scala:111)
	at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.toArray(SerDeUtil.scala:111)
	at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:909)
	at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:909)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
	at org.apache.spark.scheduler.Task.run(Task.scala:88)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	at java.lang.Thread.run(Thread.java:745)

Driver stacktrace:
	at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1283)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1271)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1270)
	at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
	at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
	at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1270)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
	at scala.Option.foreach(Option.scala:236)
	at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1496)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1458)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1447)
	at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
	at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1824)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1837)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1850)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:1921)
	at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:909)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:310)
	at org.apache.spark.rdd.RDD.collect(RDD.scala:908)
	at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:405)
	at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
	at sun.reflect.GeneratedMethodAccessor90.invoke(Unknown Source)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:497)
	at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
	at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
	at py4j.Gateway.invoke(Gateway.java:259)
	at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
	at py4j.commands.CallCommand.execute(CallCommand.java:79)
	at py4j.GatewayConnection.run(GatewayConnection.java:207)
	at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.NullPointerException
	at org.apache.spark.api.python.SerDeUtil$$anonfun$toJavaArray$1.apply(SerDeUtil.scala:103)
	at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
	at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
	at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.next(SerDeUtil.scala:120)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.next(SerDeUtil.scala:111)
	at scala.collection.Iterator$class.foreach(Iterator.scala:727)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.foreach(SerDeUtil.scala:111)
	at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
	at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
	at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
	at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.to(SerDeUtil.scala:111)
	at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.toBuffer(SerDeUtil.scala:111)
	at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
	at org.apache.spark.api.python.SerDeUtil$AutoBatchedPickler.toArray(SerDeUtil.scala:111)
	at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:909)
	at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:909)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
	at org.apache.spark.scheduler.Task.run(Task.scala:88)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
	... 1 more

















In [115]:



    


import random

from pyspark.mllib.random import RandomRDDs
from pyspark.sql.types import StructType, StructField, DoubleType
from pyspark.sql.functions import udf

def gen_label(cols):
    if (cols[0] + cols[1] + cols[2] + random.random()) / 4 >= 0.5:
        cols.append(1.0)
    else:
        cols.append(0.0)
    return cols

def rm_main():
    n_examples = 100
    n_atts = 3

    u = RandomRDDs.uniformVectorRDD(sc, n_examples, n_atts)
    u = u.map(lambda x: x.tolist())
    u = u.map(gen_label)
    schema = StructType([StructField('att%d' % i, DoubleType(), True) for i in range(1, len(u.first()))] + [StructField('label', DoubleType(), True)])
    return sqlContext.createDataFrame(u, schema)



    











In [117]:



    


df = rm_main()



    


















    






StructType(List(StructField(att1,DoubleType,true),StructField(att2,DoubleType,true),StructField(att3,DoubleType,true),StructField(label,DoubleType,true)))

















In [139]:



    


rdd = RandomRDDs.uniformVectorRDD(sc, 5, 1).map(lambda x: str(x))



    











In [140]:



    


rdd.reduce(lambda x, y: x + " " + y)



    


















    
Out[140]:








'[ 0.24888427] [ 0.97353632] [ 0.00924526] [ 0.94860258] [ 0.6740812]'

















In [ ]:

Content source: zoltanctoth/bigdata-training

Similar notebooks:

notebook.community | gallery | about