#load dataset
df = spark.sql("select * from ws_var_dataset2")
def labelData(data):
# label: row[end], features: row[0:end-1]
return data.map(lambda row: LabeledPoint(row[-1], row[:-1]))
training_data, testing_data = labelData(df.rdd).randomSplit([0.8, 0.2], seed=12345)
我在运行以下单元格时出错：
model = DecisionTree.trainClassifier(training_data, numClasses=2, maxDepth=2, categoricalFeaturesInfo={}, impurity='gini', maxBins=32)
错误：Py4JJava错误：调用 z：org.apache.spark.api.python.PythonRDD.runJob 时出错。
知道为什么会出错吗？
以下是供参考的完整错误堆栈：
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-66-43c2f1c0de4c> in <module>
----> 1 model = DecisionTree.trainClassifier(label_df, numClasses=2, maxDepth=2, categoricalFeaturesInfo={}, impurity='gini', maxBins=32)
/usr/local/spark/python/pyspark/mllib/tree.py in trainClassifier(cls, data, numClasses, categoricalFeaturesInfo, impurity, maxDepth, maxBins, minInstancesPerNode, minInfoGain)
214 """
215 return cls._train(data, "classification", numClasses, categoricalFeaturesInfo,
--> 216 impurity, maxDepth, maxBins, minInstancesPerNode, minInfoGain)
217
218 @classmethod
/usr/local/spark/python/pyspark/mllib/tree.py in _train(cls, data, type, numClasses, features, impurity, maxDepth, maxBins, minInstancesPerNode, minInfoGain)
138 def _train(cls, data, type, numClasses, features, impurity="gini", maxDepth=5, maxBins=32,
139 minInstancesPerNode=1, minInfoGain=0.0):
--> 140 first = data.first()
141 assert isinstance(first, LabeledPoint), "the data should be RDD of LabeledPoint"
142 model = callMLlibFunc("trainDecisionTreeModel", data, type, numClasses, features,
/usr/local/spark/python/pyspark/rdd.py in first(self)
1358 ValueError: RDD is empty
1359 """
-> 1360 rs = self.take(1)
1361 if rs:
1362 return rs[0]
/usr/local/spark/python/pyspark/rdd.py in take(self, num)
1340
1341 p = range(partsScanned, min(partsScanned + numPartsToTry, totalParts))
-> 1342 res = self.context.runJob(self, takeUpToNumLeft, p)
1343
1344 items += res
/usr/local/spark/python/pyspark/context.py in runJob(self, rdd, partitionFunc, partitions, allowLocal)
966 # SparkContext#runJob.
967 mappedRDD = rdd.mapPartitions(partitionFunc)
--> 968 port = self._jvm.PythonRDD.runJob(self._jsc.sc(), mappedRDD._jrdd, partitions)
969 return list(_load_from_socket(port, mappedRDD._jrdd_deserializer))
970
/usr/local/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py in __call__(self, *args)
1131 answer = self.gateway_client.send_command(command)
1132 return_value = get_return_value(
-> 1133 answer, self.gateway_client, self.target_id, self.name)
1134
1135 for temp_arg in temp_args:
/usr/local/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
/usr/local/spark/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
317 raise Py4JJavaError(
318 "An error occurred while calling {0}{1}{2}.n".
--> 319 format(target_id, ".", name), value)
320 else:
321 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 62.0 failed 4 times, most recent failure: Lost task 0.3 in stage 62.0 (TID 323, wlbimsprkprd01.opentext.net, executor 2): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/worker.py", line 160, in main
func, profiler, deserializer, serializer = read_command(pickleSer, infile)
File "/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/worker.py", line 54, in read_command
command = serializer._read_with_length(file)
File "/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/serializers.py", line 169, in _read_with_length
return self.loads(obj)
File "/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/serializers.py", line 451, in loads
return pickle.loads(obj, encoding=encoding)
File "/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/mllib/__init__.py", line 28, in <module>
import numpy
ModuleNotFoundError: No module named 'numpy'
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1925)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1938)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1951)
at org.apache.spark.api.python.PythonRDD$.runJob(PythonRDD.scala:441)
at org.apache.spark.api.python.PythonRDD.runJob(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
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(Unknown Source)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/worker.py", line 160, in main
func, profiler, deserializer, serializer = read_command(pickleSer, infile)
File "/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/worker.py", line 54, in read_command
command = serializer._read_with_length(file)
File "/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/serializers.py", line 169, in _read_with_length
return self.loads(obj)
File "/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/serializers.py", line 451, in loads
return pickle.loads(obj, encoding=encoding)
File "/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/mllib/__init__.py", line 28, in <module>
import numpy
ModuleNotFoundError: No module named 'numpy'
at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:193)
at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:234)
at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:152)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:63)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:322)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
数据通过sql函数加载并转换为RDD，以使用RDD的mlib定义树分类器函数，但由于某种原因，该函数在分类器上出错。任何意见或建议将不胜感激。
错误堆栈跟踪中提到了原因。
ModuleNotFoundError： 没有名为"numpy"的模块
你只需要安装 numpy
pip install numpy
一般来说，Spark 在将异常的实际原因返回给驱动程序方面做得并不好。您需要在错误堆栈跟踪中向下查找它。