我已经生成了一个DataFrame，如下所示
resultWithId = production_df.withColumn("id", monotonically_increasing_id())
resultWithId.show(5, truncate=False)
resultWithId.printSchema()
结果：
+--------------------------------------------------------------------------------------+---+
|unigrams |id |
+--------------------------------------------------------------------------------------+---+
|[born, furyth, leaguenemesi, rise, (the, leaguenemesi, rise, seri, book] |0 |
|[short, tragic, life, robert, peacea, brilliant, young, man, left, newark, ivi, leagu]|1 |
|[mr., beauti, (up, air, book] |2 |
|[hous, raven, (the, nightfal, chronicl, book] |3 |
|[great, zoo, china] |4 |
+--------------------------------------------------------------------------------------+---+
only showing top 5 rows
root
|-- unigrams: array (nullable = true)
| |-- element: string (containsNull = true)
|-- id: long (nullable = false)
结果我尝试使用CountVectorizer如下：
cv_tmp = CountVectorizer(inputCol="unigrams", outputCol="tmp_vectors")
cv_tmp_model = cv_tmp.fit(resultWithId)
然而它会产生：
-------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-44-a64deb595190> in <module>()
1 #remove 20 most occuring documents, documents with non numeric characters, and documents with <= 3 characters
2 cv_tmp = CountVectorizer(inputCol="unigrams", outputCol="tmp_vectors")
----> 3 cv_tmp_model = cv_tmp.fit(resultWithId)
~/Documents/spark/spark-2.2.1-bin-hadoop2.7/python/pyspark/ml/base.py in fit(self, dataset, params)
62 return self.copy(params)._fit(dataset)
63 else:
---> 64 return self._fit(dataset)
65 else:
66 raise ValueError("Params must be either a param map or a list/tuple of param maps, "
~/Documents/spark/spark-2.2.1-bin-hadoop2.7/python/pyspark/ml/wrapper.py in _fit(self, dataset)
263
264 def _fit(self, dataset):
--> 265 java_model = self._fit_java(dataset)
266 return self._create_model(java_model)
267
~/Documents/spark/spark-2.2.1-bin-hadoop2.7/python/pyspark/ml/wrapper.py in _fit_java(self, dataset)
260 """
261 self._transfer_params_to_java()
--> 262 return self._java_obj.fit(dataset._jdf)
263
264 def _fit(self, dataset):
~/Documents/spark/spark-2.2.1-bin-hadoop2.7/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:
~/Documents/spark/spark-2.2.1-bin-hadoop2.7/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()
~/Documents/spark/spark-2.2.1-bin-hadoop2.7/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 o893.fit.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 40.0 failed 1 times, most recent failure: Lost task 1.0 in stage 40.0 (TID 87, localhost, executor driver): org.apache.spark.SparkException: Failed to execute user defined function($anonfun$createTransformFunc$1: (string) => array<string>)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificMutableProjection.apply(Unknown Source)
at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1$$anonfun$6.apply(BatchEvalPythonExec.scala:124)
at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1$$anonfun$6.apply(BatchEvalPythonExec.scala:122)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$GroupedIterator.takeDestructively(Iterator.scala:1076)
at scala.collection.Iterator$GroupedIterator.go(Iterator.scala:1091)
at scala.collection.Iterator$GroupedIterator.fill(Iterator.scala:1129)
at scala.collection.Iterator$GroupedIterator.hasNext(Iterator.scala:1132)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:518)
at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:333)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1948)
at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:269)
Caused by: java.lang.NullPointerException
at org.apache.spark.ml.feature.Tokenizer$$anonfun$createTransformFunc$1.apply(Tokenizer.scala:39)
at org.apache.spark.ml.feature.Tokenizer$$anonfun$createTransformFunc$1.apply(Tokenizer.scala:39)
... 15 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1517)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1505)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1504)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1504)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1732)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1687)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1676)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2029)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2050)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2069)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2094)
at org.apache.spark.rdd.RDD.count(RDD.scala:1158)
at org.apache.spark.ml.feature.CountVectorizer.fit(CountVectorizer.scala:176)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:214)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.SparkException: Failed to execute user defined function($anonfun$createTransformFunc$1: (string) => array<string>)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificMutableProjection.apply(Unknown Source)
at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1$$anonfun$6.apply(BatchEvalPythonExec.scala:124)
at org.apache.spark.sql.execution.python.BatchEvalPythonExec$$anonfun$doExecute$1$$anonfun$6.apply(BatchEvalPythonExec.scala:122)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$GroupedIterator.takeDestructively(Iterator.scala:1076)
at scala.collection.Iterator$GroupedIterator.go(Iterator.scala:1091)
at scala.collection.Iterator$GroupedIterator.fill(Iterator.scala:1129)
at scala.collection.Iterator$GroupedIterator.hasNext(Iterator.scala:1132)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:518)
at org.apache.spark.api.python.PythonRunner$WriterThread$$anonfun$run$3.apply(PythonRDD.scala:333)
at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1948)
at org.apache.spark.api.python.PythonRunner$WriterThread.run(PythonRDD.scala:269)
Caused by: java.lang.NullPointerException
at org.apache.spark.ml.feature.Tokenizer$$anonfun$createTransformFunc$1.apply(Tokenizer.scala:39)
at org.apache.spark.ml.feature.Tokenizer$$anonfun$createTransformFunc$1.apply(Tokenizer.scala:39)
... 15 more
我不确定导致此错误的原因。我怀疑“（”在数据框中，但可能我也可能是错的。无论如何，我如何删除它并且这有效？