我在Spark 1.3.0(和1.4.0)中遇到了cache()数据帧的问题。
根据文件: http://spark.apache.org/docs/latest/api/python/pyspark.sql.html#pyspark.sql.HiveContext
无论我是否使用以下任何一种方法: cache() - 保持默认存储级别(MEMORY_ONLY_SER)。 cacheTable(tableName) - 将指定的表缓存在内存中。
该方法在没有轰炸的情况下运行,但是当我在Spark中对我的框架或表执行后续操作时,它会给我这个错误消息。
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-7-7197055e2b30> in <module>()
1 frame.show(1)
2 frame.cache()
----> 3 frame.show(1)
/home/user/Documents/spark/python/pyspark/sql/dataframe.pyc in show(self, n)
271 5 Bob
272 """
--> 273 print self._jdf.showString(n).encode('utf8', 'ignore')
274
275 def __repr__(self):
/home/user/Documents/spark/python/lib/py4j-0.8.2.1-src.zip/py4j/java_gateway.py in __call__(self, *args)
536 answer = self.gateway_client.send_command(command)
537 return_value = get_return_value(answer, self.gateway_client,
--> 538 self.target_id, self.name)
539
540 for temp_arg in temp_args:
/home/user/Documents/spark/python/lib/py4j-0.8.2.1-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
298 raise Py4JJavaError(
299 'An error occurred while calling {0}{1}{2}.\n'.
--> 300 format(target_id, '.', name), value)
301 else:
302 raise Py4JError(
Py4JJavaError: An error occurred while calling o24.showString.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 4.0 failed 1 times, most recent failure: Lost task 0.0 in stage 4.0 (TID 6, localhost): java.lang.ClassCastException: org.apache.spark.sql.catalyst.expressions.MutableAny cannot be cast to org.apache.spark.sql.catalyst.expressions.MutableInt
at org.apache.spark.sql.catalyst.expressions.SpecificMutableRow.getInt(SpecificMutableRow.scala:248)
at org.apache.spark.sql.columnar.IntColumnStats.gatherStats(ColumnStats.scala:208)
at org.apache.spark.sql.columnar.NullableColumnBuilder$class.appendFrom(NullableColumnBuilder.scala:56)
at org.apache.spark.sql.columnar.NativeColumnBuilder.org$apache$spark$sql$columnar$compression$CompressibleColumnBuilder$$super$appendFrom(ColumnBuilder.scala:87)
at org.apache.spark.sql.columnar.compression.CompressibleColumnBuilder$class.appendFrom(CompressibleColumnBuilder.scala:78)
at org.apache.spark.sql.columnar.NativeColumnBuilder.appendFrom(ColumnBuilder.scala:87)
at org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:141)
at org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:117)
at org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:277)
at org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:172)
at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:79)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:242)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:64)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:210)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1239)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1230)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1229)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1229)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:700)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:700)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:700)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1423)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1384)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
感谢您的帮助!