df = sqlContext.createDataFrame( [(0,1, "a", 23.0), (1,3, "C", -23.0), (2,3, "A", -21.0), (3,2, "B", -19.0) ], ('sec_code','dt','minute') )
df.show()
a = [(1,rdd)]
rdd = sc.parallelize(a)
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/local/lib/python2.7/site-packages/pyspark/context.py", line 484, in parallelize
jrdd = self._serialize_to_jvm(c, numSlices, serializer)
File "/usr/local/lib/python2.7/site-packages/pyspark/context.py", line 495, in _serialize_to_jvm
serializer.dump_stream(data, tempFile)
File "/usr/local/lib/python2.7/site-packages/pyspark/serializers.py", line 324, in dump_stream
self.serializer.dump_stream(self._batched(iterator), stream)
File "/usr/local/lib/python2.7/site-packages/pyspark/serializers.py", line 140, in dump_stream
self._write_with_length(obj, stream)
File "/usr/local/lib/python2.7/site-packages/pyspark/serializers.py", line 150, in _write_with_length
serialized = self.dumps(obj)
File "/usr/local/lib/python2.7/site-packages/pyspark/serializers.py", line 555, in dumps
return pickle.dumps(obj, protocol)
File "/usr/local/lib/python2.7/site-packages/pyspark/python/lib/py4j-0.10.6-src.zip/py4j/java_gateway.py", line 1160, in __call__
File "/usr/local/lib/python2.7/site-packages/pyspark/sql/utils.py", line 63, in deco
return f(*a, **kw)
File "/usr/local/lib/python2.7/site-packages/pyspark/python/lib/py4j-0.10.6-src.zip/py4j/protocol.py", line 324, in get_return_value
py4j.protocol.Py4JError: An error occurred while calling o88.__getnewargs__. Trace:
py4j.Py4JException: Method __getnewargs__([]) does not exist
at py4j.reflection.ReflectionEngine.getMethod(ReflectionEngine.java:318)
at py4j.reflection.ReflectionEngine.getMethod(ReflectionEngine.java:326)
at py4j.Gateway.invoke(Gateway.java:274)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
参考文献:
PySpark Throwing error Method __getnewargs__([]) does not exist:
https://stackoverflow.com/questions/40470487/pyspark-throwing-error-method-getnewargs-does-not-exist
Spark - Call unbound method with explicit self error:
https://stackoverflow.com/questions/34734180/spark-call-unbound-method-with-explicit-self-error