>>> v=sc.parallelize(["one", "two", "two", "three", "three", "three"])

>>> v2=v.map(lambda x: (x,1))

>>> v2.collect()

[('one', 1), ('two', 1), ('two', 1), ('three', 1), ('three', 1), ('three', 1)]

>>> v3=v2.groupByKey()

>>> v3.collect()

[('one', <pyspark.resultiterable.ResultIterable object at 0x7fd3c7850e90>), ('two', <pyspark.resultiterable.ResultIterable object at 0x7fd3c7850f10>), ('three', <pyspark.resultiterable.ResultIterable object at 0x7fd3c6dc83d0>)]

>>> v4=v3.filter(lambda x:len(x[1].data)>2)

>>> v4.collect()

[('three', <pyspark.resultiterable.ResultIterable object at 0x7fd3c6dc8510>)]