我很新兴，在将.csv文件转换为数据帧时遇到错误。我使用pyspark_csv模块进行转换但出错了， 这里是错误的堆栈跟踪，可以给我任何一个解决此错误的建议
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-16-67fe725a8e27> in <module>()
----> 1 data_df = pycsv.csvToDataFrame(sqlCtx, data_body, sep=",", columns=data_header.split('\t')).cache()
/usr/spark-1.5.0/python/pyspark_csv.py in csvToDataFrame(sqlCtx, rdd, columns, sep, parseDate)
51 rdd_sql = rdd_array.zipWithIndex().filter(
52 lambda r_i: r_i[1] > 0).keys()
---> 53 column_types = evaluateType(rdd_sql, parseDate)
54
55 def toSqlRow(row):
/usr/spark-1.5.0/python/pyspark_csv.py in evaluateType(rdd_sql, parseDate)
177 def evaluateType(rdd_sql, parseDate):
178 if parseDate:
--> 179 return rdd_sql.map(getRowType).reduce(reduceTypes)
180 else:
181 return rdd_sql.map(getRowTypeNoDate).reduce(reduceTypes)
/usr/spark-1.5.0/python/pyspark/rdd.py in reduce(self, f)
797 yield reduce(f, iterator, initial)
798
--> 799 vals = self.mapPartitions(func).collect()
800 if vals:
801 return reduce(f, vals)
/usr/spark-1.5.0/python/pyspark/rdd.py in collect(self)
771 """
772 with SCCallSiteSync(self.context) as css:
--> 773 port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
774 return list(_load_from_socket(port, self._jrdd_deserializer))
775
/usr/spark-1.5.0/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:
/usr/spark-1.5.0/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 z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 10.0 failed 1 times, most recent failure: Lost task 0.0 in stage 10.0 (TID 20, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/usr/spark-1.5.0/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/usr/spark-1.5.0/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/usr/spark-1.5.0/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/usr/spark-1.5.0/python/pyspark/rdd.py", line 797, in func
yield reduce(f, iterator, initial)
File "/tmp/spark-d85b88bf-e4a4-46b8-8b51-eaf0f03e48ab/userFiles-40f9eb34-4efa-4ffb-aaf5-ebcb24a4ecb9/pyspark_csv.py", line 160, in reduceTypes
b_type = b[col]
IndexError: list index out of range
at org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:138)
at org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:179)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:97)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
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$$failJobAndIndependentStages(DAGScheduler.scala:1280)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1826)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1839)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1910)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:905)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:306)
at org.apache.spark.rdd.RDD.collect(RDD.scala:904)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:373)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
at py4j.Gateway.invoke(Gateway.java:259)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:207)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
File "/usr/spark-1.5.0/python/lib/pyspark.zip/pyspark/worker.py", line 111, in main
process()
File "/usr/spark-1.5.0/python/lib/pyspark.zip/pyspark/worker.py", line 106, in process
serializer.dump_stream(func(split_index, iterator), outfile)
File "/usr/spark-1.5.0/python/lib/pyspark.zip/pyspark/serializers.py", line 263, in dump_stream
vs = list(itertools.islice(iterator, batch))
File "/usr/spark-1.5.0/python/pyspark/rdd.py", line 797, in func
yield reduce(f, iterator, initial)
File "/tmp/spark-d85b88bf-e4a4-46b8-8b51-eaf0f03e48ab/userFiles-40f9eb34-4efa-4ffb-aaf5-ebcb24a4ecb9/pyspark_csv.py", line 160, in reduceTypes
b_type = b[col]
IndexError: list index out of range
at org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:138)
at org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:179)
at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:97)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
... 1 more
这是我的代码，最后声明它在从csv转换为dataframe时出现此错误
import findspark
findspark.init()
findspark.find()
import pyspark
sc=pyspark.SparkContext(appName="myAppName")
sqlCtx = pyspark.SQLContext
#csv to dataframe
sc.addPyFile('/usr/spark-1.5.0/python/pyspark_csv.py')
import pyspark_csv as pycsv
def skip_header(idx, iterator):
if(idx == 0):
next(iterator)
return iterator
data=sc.textFile('gdeltdata/20160427.CSV')
data_header = data.first()
data_body = data.mapPartitionsWithIndex(skip_header)
data_df = pycsv.csvToDataFrame(sqlCtx, data_body, sep=",", columns=data_header.split('\t'))
答案 0 :(得分：0)
我实际上无法发表评论，但是，如果没有任何代码，我将不得不猜测您正在尝试引用一个不存在的字符串中存在的索引 - 这将是与执行以下操作相同：
string = 'hello'
new_char = string[6]
这会尝试在5个字母的字符串上找到第7个字母 - 这会带来以下错误：
IndexError: string index out of range
由于我没有看到导致该错误的代码，因此我能够提供有关您的问题的所有内容。
答案 1 :(得分：0)
您的 CSV 文件格式似乎不正确。
实际错误有点深：
File "/tmp/spark-d85b88bf-e4a4-46b8-8b51-eaf0f03e48ab/userFiles-40f9eb34-4efa-4ffb-aaf5-ebcb24a4ecb9/pyspark_csv.py", line 160, in reduceTypes
b_type = b[col]
IndexError: list index out of range
这表示其中一行没有预期的列数（它可能是文件末尾的空白行）。