我正在编写这个程序,希望得到这个输出:
True
True
False
False
我和#34;没有"打印在我的预期输出之间:
True
None
True
None
False
None
False
None
我不知道为什么这些"没有"字符串正在打印,任何帮助将不胜感激!这是我的代码:
# function: check_answer
# input: two numbers (number1 & number2, both integers); an answer (an integer)
# and an operator (+ or -, expressed as a String)
# processing: determines if the supplied expression is correct. for example, if the operator
# is "+", number1 = 1, number2 = 2 and answer = 3 then the expression is correct
# (1 + 2 = 3).
# output: returns True if the expression is correct, False if it is not correct
def check_answer (number1, number2, answer, operator):
if operator == "+":
test = number1 + number2
if test == answer:
print ("True")
else:
print ("False")
if operator == "-":
test2 = number1 - number2
if test2 == answer:
print ("True")
else:
print ("False")
return
answer1 = check_answer(1, 2, 3, "+")
print (answer1)
answer2 = check_answer(1, 2, -1, "-")
print (answer2)
answer3 = check_answer(9, 5, 3, "+")
print (answer3)
answer4 = check_answer(8, 2, 4, "-")
print (answer4)
非常感谢!!
答案 0 :(得分:1)
这是因为[O]
Py4JJavaError Traceback (most recent call last)
<ipython-input-101-31527190732e> in <module>()
----> 1 user_cnt = all_twt_rdd.flatMap(lambda line: line.split(" ")).take(2)
/home/notebook/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.pyc in take(self, num)
1295
1296 p = range(partsScanned, min(partsScanned + numPartsToTry, totalParts))
-> 1297 res = self.context.runJob(self, takeUpToNumLeft, p)
1298
1299 items += res
/home/notebook/spark-1.6.0-bin-hadoop2.6/python/pyspark/context.pyc in runJob(self, rdd, partitionFunc, partitions, allowLocal)
937 # SparkContext#runJob.
938 mappedRDD = rdd.mapPartitions(partitionFunc)
--> 939 port = self._jvm.PythonRDD.runJob(self._jsc.sc(), mappedRDD._jrdd, partitions)
940 return list(_load_from_socket(port, mappedRDD._jrdd_deserializer))
941
/home/notebook/spark-1.6.0-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:
/home/notebook/spark-1.6.0-bin-hadoop2.6/python/pyspark/sql/utils.pyc 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()
/home/notebook/spark-1.6.0-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 z:org.apache.spark.api.python.PythonRDD.runJob.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 50.0 failed 1 times, most recent failure: Lost task 0.0 in stage 50.0 (TID 456, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/home/notebook/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/home/notebook/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/home/notebook/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/home/notebook/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 1293, in takeUpToNumLeft
yield next(iterator)
File "<ipython-input-101-31527190732e>", line 1, in <lambda>
File "/home/notebook/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/sql/types.py", line 1272, in __getattr__
raise AttributeError(item)
AttributeError: split
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$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$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
at org.apache.spark.api.python.PythonRDD$.runJob(PythonRDD.scala:393)
at org.apache.spark.api.python.PythonRDD.runJob(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
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: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/home/notebook/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/home/notebook/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/home/notebook/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/home/notebook/spark-1.6.0-bin-hadoop2.6/python/pyspark/rdd.py", line 1293, in takeUpToNumLeft
yield next(iterator)
File "<ipython-input-101-31527190732e>", line 1, in <lambda>
File "/home/notebook/spark-1.6.0-bin-hadoop2.6/python/lib/pyspark.zip/pyspark/sql/types.py", line 1272, in __getattr__
raise AttributeError(item)
AttributeError: split
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
... 1 more
之类的调用 - 你的函数没有返回任何内容,这就是你看到print(answer1)
打印的原因。只是不要打印函数返回的内容:
None
或者,从函数返回check_answer(1, 2, 3, "+")
check_answer(1, 2, -1, "-")
check_answer(9, 5, 3, "+")
check_answer(8, 2, 4, "-")
并打印结果:
True/False
作为旁注,您可以使用operator
模块并将操作字符串映射到实际操作来简化您的功能。 def check_answer(number1, number2, answer, operator):
if operator == "+":
test = number1 + number2
return test == answer
if operator == "-":
test2 = number1 - number2
return test2 == answer
answer1 = check_answer(1, 2, 3, "+")
print (answer1)
answer2 = check_answer(1, 2, -1, "-")
print (answer2)
answer3 = check_answer(9, 5, 3, "+")
print (answer3)
answer4 = check_answer(8, 2, 4, "-")
print (answer4)
和+
的工作示例:
-