Python 如何使用PySpark'；有RDD的FP增长？

我想使用FP growth来了解是否有来自以下RDD的相关关联规则。从一开始，我尝试了以下方法：

sqlContext = SQLContext(sc)

spark_df = sqlContext.createDataFrame(pandas_df[['Category','Descript', 'DayOfWeek', 'PdDistrict', 'Resolution', 'Address']])

spark_df.show(2)

+--------------+--------------------+---------+----------+--------------+------------------+
|      Category|            Descript|DayOfWeek|PdDistrict|    Resolution|           Address|
+--------------+--------------------+---------+----------+--------------+------------------+
|      WARRANTS|      WARRANT ARREST|Wednesday|  NORTHERN|ARREST, BOOKED|OAK ST / LAGUNA ST|
|OTHER OFFENSES|TRAFFIC VIOLATION...|Wednesday|  NORTHERN|ARREST, BOOKED|OAK ST / LAGUNA ST|
+--------------+--------------------+---------+----------+--------------+------------------+
only showing top 2 rows

from pyspark.mllib.fpm import FPGrowth

model = FPGrowth.train(spark_df.rdd, minSupport=0.2, numPartitions=10)

result = model.freqItemsets().collect()

for fi in result:

    print(fi)

然而，我得到了一个例外：

---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-7-fa62e885b01c> in <module>()
      4 #transactions = spark_df.map(lambda line: line.strip().split(' '))
      5 
----> 6 model = FPGrowth.train(spark_df.rdd, minSupport=0.2, numPartitions=10)
      7 
      8 result = model.freqItemsets().collect()

/Users/user/spark-1.6.2-bin-hadoop2.6/python/pyspark/mllib/fpm.py in train(cls, data, minSupport, numPartitions)
     75             parallel FP-growth (default: same as input data).
     76         """
---> 77         model = callMLlibFunc("trainFPGrowthModel", data, float(minSupport), int(numPartitions))
     78         return FPGrowthModel(model)
     79 

/Users/user/spark-1.6.2-bin-hadoop2.6/python/pyspark/mllib/common.py in callMLlibFunc(name, *args)
    128     sc = SparkContext.getOrCreate()
    129     api = getattr(sc._jvm.PythonMLLibAPI(), name)
--> 130     return callJavaFunc(sc, api, *args)
    131 
    132 

/Users/user/spark-1.6.2-bin-hadoop2.6/python/pyspark/mllib/common.py in callJavaFunc(sc, func, *args)
    121     """ Call Java Function """
    122     args = [_py2java(sc, a) for a in args]
--> 123     return _java2py(sc, func(*args))
    124 
    125 

/Users/user/spark-1.6.2-bin-hadoop2.6/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py 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:

/Users/user/spark-1.6.2-bin-hadoop2.6/python/pyspark/sql/utils.py in deco(*a, **kw)
     43     def deco(*a, **kw):
     44         try:
---> 45             return f(*a, **kw)
     46         except py4j.protocol.Py4JJavaError as e:
     47             s = e.java_exception.toString()

/Users/user/spark-1.6.2-bin-hadoop2.6/python/lib/py4j-0.9-src.zip/py4j/protocol.py 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 o76.trainFPGrowthModel.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 2.0 failed 1 times, most recent failure: Lost task 0.0 in stage 2.0 (TID 3, localhost): net.razorvine.pickle.PickleException: expected zero arguments for construction of ClassDict (for pyspark.sql.types._create_row)
    at net.razorvine.pickle.objects.ClassDictConstructor.construct(ClassDictConstructor.java:23)
    at net.razorvine.pickle.Unpickler.load_reduce(Unpickler.java:707)
    at net.razorvine.pickle.Unpickler.dispatch(Unpickler.java:175)
    at net.razorvine.pickle.Unpickler.load(Unpickler.java:99)
    at net.razorvine.pickle.Unpickler.loads(Unpickler.java:112)
    at org.apache.spark.mllib.api.python.SerDe$$anonfun$pythonToJava$1$$anonfun$apply$2.apply(PythonMLLibAPI.scala:1507)
    at org.apache.spark.mllib.api.python.SerDe$$anonfun$pythonToJava$1$$anonfun$apply$2.apply(PythonMLLibAPI.scala:1506)
    at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1631)
    at org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:1157)
    at org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:1157)
    at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1858)
    at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1858)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227)
    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$$failJobAndIndependentStages(DAGScheduler.scala:1431)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
    at scala.Option.foreach(Option.scala:236)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1929)
    at org.apache.spark.rdd.RDD.count(RDD.scala:1157)
    at org.apache.spark.mllib.fpm.FPGrowth.run(FPGrowth.scala:114)
    at org.apache.spark.mllib.api.python.PythonMLLibAPI.trainFPGrowthModel(PythonMLLibAPI.scala:565)
    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:231)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
    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:209)
    at java.lang.Thread.run(Thread.java:745)
Caused by: net.razorvine.pickle.PickleException: expected zero arguments for construction of ClassDict (for pyspark.sql.types._create_row)
    at net.razorvine.pickle.objects.ClassDictConstructor.construct(ClassDictConstructor.java:23)
    at net.razorvine.pickle.Unpickler.load_reduce(Unpickler.java:707)
    at net.razorvine.pickle.Unpickler.dispatch(Unpickler.java:175)
    at net.razorvine.pickle.Unpickler.load(Unpickler.java:99)
    at net.razorvine.pickle.Unpickler.loads(Unpickler.java:112)
    at org.apache.spark.mllib.api.python.SerDe$$anonfun$pythonToJava$1$$anonfun$apply$2.apply(PythonMLLibAPI.scala:1507)
    at org.apache.spark.mllib.api.python.SerDe$$anonfun$pythonToJava$1$$anonfun$apply$2.apply(PythonMLLibAPI.scala:1506)
    at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
    at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
    at org.apache.spark.util.Utils$.getIteratorSize(Utils.scala:1631)
    at org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:1157)
    at org.apache.spark.rdd.RDD$$anonfun$count$1.apply(RDD.scala:1157)
    at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1858)
    at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1858)
    at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    ... 1 more

---------------------------------------------------------------------------
Py4JJavaError回溯（最近一次调用）
在（）
4#事务=spark#u df.map（lambda行：line.strip（）.split（“”））
5.
---->6模型=FPGrowth.train（spark_df.rdd，minSupport=0.2，numPartitions=10）
7.
8结果=model.freqItemsets（）.collect（）
/列车中的Users/user/spark-1.6.2-bin-hadoop2.6/python/pyspark/mllib/fpm.py（cls、数据、minSupport、numPartitions）
75并行FP增长（默认值：与输入数据相同）。
76         """
--->77 model=callMLlibFunc（“trainFPGrowthModel”、数据、浮点（minSupport）、整数（numPartitions））
78返回FPGrowthModel（模型）
79
/callMLlibFunc（name，*args）中的Users/user/spark-1.6.2-bin-hadoop2.6/python/pyspark/mllib/common.py
128 sc=SparkContext.getOrCreate（）
129 api=getattr（sc.\u jvm.PythonMLLibAPI（），名称）
-->130返回callJavaFunc（sc、api、*args）
131
132
/callJavaFunc（sc，func，*args）中的Users/user/spark-1.6.2-bin-hadoop2.6/python/pyspark/mllib/common.py
121“调用Java函数”
122 args=[[u py2java（sc，a）表示args中的a]
-->123返回_java2py（sc，func（*args））
124
125
/Users/user/spark-1.6.2-bin-hadoop2.6/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py in_uu调用（self，*args）
811 answer=self.gateway\u client.send\u命令（command）
812返回值=获取返回值(
-->813应答，self.gateway\u客户端，self.target\u id，self.name）
814
815对于临时参数中的临时参数：
/deco中的Users/user/spark-1.6.2-bin-hadoop2.6/python/pyspark/sql/utils.py（*a，**kw）
43 def装饰（*a，**千瓦）：
44尝试：
--->45返回f（*a，**kw）
46除py4j.protocol.Py4JJavaError外，错误为e:
47 s=e.java_exception.toString（）
/获取返回值中的Users/user/spark-1.6.2-bin-hadoop2.6/python/lib/py4j-0.9-src.zip/py4j/protocol.py（答案、网关客户端、目标id、名称）
306 raise PY4JJAVA错误(
307“调用{0}{1}{2}时出错。\n”。
-->308格式（目标id，“.”，名称），值）
309其他：
310升起Py4JError(
Py4JJavaError:调用o76.trainFPGrowthModel时出错。
：org.apache.spark.SparkException:作业因阶段失败而中止：阶段2.0中的任务0失败1次，最近的失败：阶段2.0中的任务0.0丢失（TID 3，localhost）：net.razorvine.pickle.pickle异常：构造ClassDict（对于pyspark.sql.types.\u create\u row）的参数应为零
位于net.razorvine.pickle.objects.ClassDictConstructor.construct（ClassDictConstructor.java:23）
net.razorvine.pickle.Unpickler.load\u reduce（Unpickler.java:707）
位于net.razorvine.pickle.Unpickler.dispatch（Unpickler.java:175）
位于net.razorvine.pickle.Unpickler.load（Unpickler.java:99）
加载net.razorvine.pickle.Unpickler.load（Unpickler.java:112）
位于org.apache.spark.mllib.api.python.SerDe$$anonfun$pythonToJava$1$$anonfun$apply$2.apply（PythonMLLibAPI.scala:1507）
位于org.apache.spark.mllib.api.python.SerDe$$anonfun$pythonToJava$1$$anonfun$apply$2.apply（PythonMLLibAPI.scala:1506）
位于scala.collection.Iterator$$anon$13.hasNext（Iterator.scala:371）
在scala.collection.Iterator$$anon$11.hasNext（Iterator.scala:327）
位于org.apache.spark.util.Utils$.getIteratorSize（Utils.scala:1631）
位于org.apache.spark.rdd.rdd$$anonfun$count$1.apply（rdd.scala:1157）
位于org.apache.spark.rdd.rdd$$anonfun$count$1.apply（rdd.scala:1157）
位于org.apache.spark.SparkContext$$anonfun$runJob$5.apply（SparkContext.scala:1858）
位于org.apache.spark.SparkContext$$anonfun$runJob$5.apply（SparkContext.scala:1858）
位于org.apache.spark.scheduler.ResultTask.runTask（ResultTask.scala:66）
位于org.apache.spark.scheduler.Task.run（Task.scala:89）
位于org.apache.spark.executor.executor$TaskRunner.run（executor.scala:227）
位于java.util.concurrent.ThreadPoolExecutor.runWorker（ThreadPoolExecutor.java:1142）
位于java.util.concurrent.ThreadPoolExecutor$Worker.run（ThreadPoolExecutor.java:617）
运行（Thread.java:745）
驱动程序堆栈跟踪：
位于org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages（DAGScheduler.scala:1431）
位于org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply（DAGScheduler.scala:1419）
位于org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply（DAGScheduler.scala:1418）
位于scala.collection.mutable.resizeblearray$class.foreach（resizeblearray.scala:59）
位于scala.collection.mutable.ArrayBuffer.foreach（ArrayBuffer.scala:47）
位于org.apache.spark.scheduler.DAGScheduler.abortStage（DAGScheduler.scala:1418）
位于org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply（DAGScheduler.scala:799）
位于org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply（DAGScheduler.scala:799）
位于scala.Option.foreach（Option.scala:236）
位于org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed（DAGScheduler.scala:799）
位于org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive（DAGScheduler.scala:1640）
位于org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive（DAGScheduler.scala:1599）
位于org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive（DAGScheduler.scala:1588）
位于org.apache.spark.util.EventLoop$$anon$1.run（EventLoop.scala:48）
位于org.apache.spark.scheduler.DAGScheduler.runJob（DAGScheduler.scala:620）
位于org.apache.spark.SparkContext.runJob（SparkContext.scala:1832）
位于org.apache.spark.SparkContext.runJob（SparkContext.scala:1845）
>>> FPGrowth.train(
... spark_df.rdd.map(lambda x: list(set(x))),
... minSupport=0.2, numPartitions=10)