Bdtjtk

I installed canopy IDE on windows as well as python and pyspark. When executing the code of a program, there was problem of a sparK Context:

findspark.init()

conf = SparkConf().setMaster('local').setAppName('MonEssai')

sc = SparkContext.getOrCreate();

lines = sc.textFile("file:///PremiéreEssai/ file9.txt")

fun = lines.flatMap(listsGraph)

results =fun.collect()



for result1 in results:

  if(result1): 

    if ((result1[0].strip().startswith("sub_"))|(result1[0].strip().startswith("start"))):

      for k in range(0,len(result1)):

           if result1[k] not in Loc: 

                Loc.append(result1[k])

    else :

        for j in range(0,len(result1)):

           if result1[j] not in Ext: 

                Ext.append(result1[j])



result3 = sc.parallelize(Ext)

ExtSimilarity= result3.map(MatchExt).filter(lambda x: x != None).collect() 

#print(ExtSimilarity)         



#print(Loc)

result3 = sc.parallelize(Loc)

result9= result3.map(pos_debut)

result11= result9.map(opcode)

VectOpcode= result11.flatMapValues(f).flatMap(lambda X: [((X[0],len(X[1])))]).groupByKey().mapValues(list)

VectOpcode2 = VectOpcode.collect()

And I got the following error:

Py4JError: An error occurred while calling
None.org.apache.spark.api.python.PythonAccumulatorV2. Trace:
py4j.Py4JException: Constructor
org.apache.spark.api.python.PythonAccumulatorV2([class
java.lang.String, class java.lang.Integer, class java.lang.String])
does not exist

Py4JErrorTraceback (most recent call last)

C:Premi�reEssaimaman.py in <module>()

    818 findspark.init()

    819 conf = SparkConf().setMaster('local').setAppName('MonEssai')

--> 820 sc = SparkContext.getOrCreate();

    821 lines = sc.textFile("file:///PremiéreEssai/ file9.txt")

    822 fun = lines.flatMap(listsGraph)

C:UsersheneAppDataLocalEnthoughtCanopyedmenvsUserlibsite-packagespysparkcontext.pyc in getOrCreate(cls, conf)

    347         with SparkContext._lock:

    348             if SparkContext._active_spark_context is None:

--> 349                 SparkContext(conf=conf or SparkConf())

    350             return SparkContext._active_spark_context

    351 

C:UsersheneAppDataLocalEnthoughtCanopyedmenvsUserlibsite-packagespysparkcontext.pyc in __init__(self, master, appName, sparkHome, pyFiles, environment, batchSize, serializer, conf, gateway, jsc, profiler_cls)

    116         try:

    117             self._do_init(master, appName, sparkHome, pyFiles, environment, batchSize, serializer,

--> 118                           conf, jsc, profiler_cls)

    119         except:

    120             # If an error occurs, clean up in order to allow future SparkContext creation:

C:UsersheneAppDataLocalEnthoughtCanopyedmenvsUserlibsite-packagespysparkcontext.pyc in _do_init(self, master, appName, sparkHome, pyFiles, environment, batchSize, serializer, conf, jsc, profiler_cls)

    187         self._accumulatorServer = accumulators._start_update_server(auth_token)

    188         (host, port) = self._accumulatorServer.server_address

--> 189         self._javaAccumulator = self._jvm.PythonAccumulatorV2(host, port, auth_token)

    190         self._jsc.sc().register(self._javaAccumulator)

    191 

C:UsersheneAppDataLocalEnthoughtCanopyedmenvsUserlibsite-packagespy4jjava_gateway.pyc in __call__(self, *args)

   1523         answer = self._gateway_client.send_command(command)

   1524         return_value = get_return_value(

-> 1525             answer, self._gateway_client, None, self._fqn)

   1526 

   1527         for temp_arg in temp_args:

C:UsersheneAppDataLocalEnthoughtCanopyedmenvsUserlibsite-packagespy4jprotocol.pyc in get_return_value(answer, gateway_client, target_id, name)

    330                 raise Py4JError(

    331                     "An error occurred while calling {0}{1}{2}. Trace:n{3}n".

--> 332                     format(target_id, ".", name, value))

    333         else:

    334             raise Py4JError(

Py4JError: An error occurred while calling None.org.apache.spark.api.python.PythonAccumulatorV2. Trace:

py4j.Py4JException: Constructor org.apache.spark.api.python.PythonAccumulatorV2([class java.lang.String, class java.lang.Integer, class java.lang.String]) does not exist

at py4j.reflection.ReflectionEngine.getConstructor(ReflectionEngine.java:179)

at py4j.reflection.ReflectionEngine.getConstructor(ReflectionEngine.java:196)

at py4j.Gateway.invoke(Gateway.java:237)

at py4j.commands.ConstructorCommand.invokeConstructor(ConstructorCommand.java:80)

at py4j.commands.ConstructorCommand.execute(ConstructorCommand.java:69)

at py4j.GatewayConnection.run(GatewayConnection.java:238)

at java.lang.Thread.run(Thread.java:748)

So, I'm stuck in this what should I do?

Setting a environment variable called PYTHONPATH = {hadoop_path}/python would help