Error while using mapPartitions in Pyspark

Question

I am new to Python spark and I am running the below spark code in the Jupyter notebook and getting AttributeError: 'NoneType' object has no attribute '_jvm'

My spark version is 3.0.1.

from pyspark.sql import functions as func

one_through_9 = range(1,10)
parallel = sc.parallelize(one_through_9, 3)
def f(iterator): yield func.sum(iterator)
parallel.mapPartitions(f).collect()

Find below the full error while running the code.

---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
<ipython-input-55-44576a0dc413> in <module>
      2 def valueSum(f): return func.sum(f)
      3 
----> 4 mapp.mapPartitions(valueSum).collect()
      5 #one_through_9 = range(1,10)
      6 #parallel = sc.parallelize(one_through_9, 3)

~/spark-3.0.1-bin-hadoop2.7/python/pyspark/rdd.py in collect(self)
    887         """
    888         with SCCallSiteSync(self.context) as css:
--> 889             sock_info = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
    890         return list(_load_from_socket(sock_info, self._jrdd_deserializer))
    891 

~/spark-3.0.1-bin-hadoop2.7/python/lib/py4j-0.10.9-src.zip/py4j/java_gateway.py in __call__(self, *args)
   1302 
   1303         answer = self.gateway_client.send_command(command)
-> 1304         return_value = get_return_value(
   1305             answer, self.gateway_client, self.target_id, self.name)
   1306 

~/spark-3.0.1-bin-hadoop2.7/python/pyspark/sql/utils.py in deco(*a, **kw)
    126     def deco(*a, **kw):
    127         try:
--> 128             return f(*a, **kw)
    129         except py4j.protocol.Py4JJavaError as e:
    130             converted = convert_exception(e.java_exception)

~/spark-3.0.1-bin-hadoop2.7/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    324             value = OUTPUT_CONVERTER[type](answer[2:], gateway_client)
    325             if answer[1] == REFERENCE_TYPE:
--> 326                 raise Py4JJavaError(
    327                     "An error occurred while calling {0}{1}{2}.\n".
    328                     format(target_id, ".", name), value)

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 0 in stage 53.0 failed 1 times, most recent failure: Lost task 0.0 in stage 53.0 (TID 83, 192.168.43.228, executor driver): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/home/vijee/spark-3.0.1-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 605, in main
    process()
  File "/home/vijee/spark-3.0.1-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 595, in process
    out_iter = func(split_index, iterator)
  File "/home/vijee/spark-3.0.1-bin-hadoop2.7/python/pyspark/rdd.py", line 425, in func
    return f(iterator)
  File "<ipython-input-55-44576a0dc413>", line 2, in valueSum
  File "/home/vijee/spark-3.0.1-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/sql/functions.py", line 68, in _
    jc = getattr(sc._jvm.functions, name)(_to_java_column(col))
AttributeError: 'NoneType' object has no attribute '_jvm'

Answer 1

func.sum is for use with dataframes, not for summing numbers. Use the Python sum function instead:

one_through_9 = range(1,10)
parallel = sc.parallelize(one_through_9, 3)
def f(iterator):
    yield sum(iterator)

parallel.mapPartitions(f).collect()

which will give [6, 15, 24].