我正在关注datacamp pyspark tutorial series and on chapter 04 Model tuning and selection in fitting the model ，当我执行这些行时出现此错误
best_lr = lr.fit(training)
错误
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-102-88042cb88c20> in <module>()
----> 1 best_lr = lr.fit(training)
/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/ml/base.py in fit(self, dataset, params)
130 return self.copy(params)._fit(dataset)
131 else:
--> 132 return self._fit(dataset)
133 else:
134 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/ml/wrapper.py in _fit(self, dataset)
286
287 def _fit(self, dataset):
--> 288 java_model = self._fit_java(dataset)
289 model = self._create_model(java_model)
290 return self._copyValues(model)
/usr/hdp/current/spark2-client/python/lib/pyspark.zip/pyspark/ml/wrapper.py in _fit_java(self, dataset)
283 """
284 self._transfer_params_to_java()
--> 285 return self._java_obj.fit(dataset._jdf)
286
287 def _fit(self, dataset):
/usr/hdp/current/spark2-client/python/lib/py4j-0.10.6-src.zip/py4j/java_gateway.py in __call__(self, *args)
1158 answer = self.gateway_client.send_command(command)
1159 return_value = get_return_value(
-> 1160 answer, self.gateway_client, self.target_id, self.name)
1161
1162 for temp_arg in temp_args:
/usr/hdp/current/spark2-client/python/lib/pyspark.zip/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/hdp/current/spark2-client/python/lib/py4j-0.10.6-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
318 raise Py4JJavaError(
319 "An error occurred while calling {0}{1}{2}.\n".
--> 320 format(target_id, ".", name), value)
321 else:
322 raise Py4JError(
Py4JJavaError: An error occurred while calling o596.fit.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 60.0 failed 1 times, most recent failure: Lost task 2.0 in stage 60.0 (TID 86, localhost, executor driver): org.apache.spark.SparkException: Failed to execute user defined function($anonfun$3: (struct<month_double_VectorAssembler_42f79ae7f99735f04859:double,air_time_double_VectorAssembler_42f79ae7f99735f04859:double,carrier_fact:vector,dest_fact:vector,plane_age_double_VectorAssembler_42f79ae7f99735f04859:double>) => vector)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.sort_addToSorter$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.storage.memory.MemoryStore.putIteratorAsValues(MemoryStore.scala:216)
at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1092)
at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1083)
at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:1018)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1083)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:809)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:335)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:286)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.SparkException: Values to assemble cannot be null.
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$assemble$1.apply(VectorAssembler.scala:163)
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$assemble$1.apply(VectorAssembler.scala:146)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.WrappedArray.foreach(WrappedArray.scala:35)
at org.apache.spark.ml.feature.VectorAssembler$.assemble(VectorAssembler.scala:146)
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$3.apply(VectorAssembler.scala:99)
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$3.apply(VectorAssembler.scala:98)
... 24 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1587)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1586)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1586)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1820)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1769)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1758)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:642)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2034)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2131)
at org.apache.spark.rdd.RDD$$anonfun$fold$1.apply(RDD.scala:1092)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.fold(RDD.scala:1086)
at org.apache.spark.rdd.RDD$$anonfun$treeAggregate$1.apply(RDD.scala:1155)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.treeAggregate(RDD.scala:1131)
at org.apache.spark.ml.classification.LogisticRegression.train(LogisticRegression.scala:518)
at org.apache.spark.ml.classification.LogisticRegression.train(LogisticRegression.scala:488)
at org.apache.spark.ml.classification.LogisticRegression.train(LogisticRegression.scala:278)
at org.apache.spark.ml.Predictor.fit(Predictor.scala:118)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
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:745)
Caused by: org.apache.spark.SparkException: Failed to execute user defined function($anonfun$3: (struct<month_double_VectorAssembler_42f79ae7f99735f04859:double,air_time_double_VectorAssembler_42f79ae7f99735f04859:double,carrier_fact:vector,dest_fact:vector,plane_age_double_VectorAssembler_42f79ae7f99735f04859:double>) => vector)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.sort_addToSorter$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage2.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$10$$anon$1.hasNext(WholeStageCodegenExec.scala:614)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.storage.memory.MemoryStore.putIteratorAsValues(MemoryStore.scala:216)
at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1092)
at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1083)
at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:1018)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1083)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:809)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:335)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:286)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
... 1 more
Caused by: org.apache.spark.SparkException: Values to assemble cannot be null.
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$assemble$1.apply(VectorAssembler.scala:163)
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$assemble$1.apply(VectorAssembler.scala:146)
at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
at scala.collection.mutable.WrappedArray.foreach(WrappedArray.scala:35)
at org.apache.spark.ml.feature.VectorAssembler$.assemble(VectorAssembler.scala:146)
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$3.apply(VectorAssembler.scala:99)
at org.apache.spark.ml.feature.VectorAssembler$$anonfun$3.apply(VectorAssembler.scala:98)
... 24 more
工具
我正在将在线 pyspark clutter 与 Cloudxlabs.com(试用版)一起使用
最佳答案
数据集中可能存在一些 NULL 值。你必须首先处理这些。
正如错误“要组装的值不能为空”所解释的。
关于machine-learning - LogesticRegression fit() 函数抛出此错误，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/53610972/