玩蛇网提供最新Python编程技术信息以及Python资源下载!

求指导python spark读入文件不能正常载入的原因

想尝试着处理一下文本,结果都载入不进来。。。
文件路径肯定没问题
求大神指教

fileName = "file:///Users/liuchong/Desktop/Animal Farm.txt"
liuDF = sqlContext.read.text(fileName).select('value')
print type(liuDF)
liuDF.show()

报错:


---------------------------------------------------------------------------
Py4JJavaError                             Traceback (most recent call last)
 in ()
      5 liuDF = sqlContext.read.text(fileName).select('value')
      6 print type(liuDF)
----> 7 liuDF.show()
      8 #print liuDF.count()
      9 def removePunctuation(column):

/databricks/spark/python/pyspark/sql/dataframe.py in show(self, n, truncate)
    255         +---+-----+
    256         """
--> 257         print(self._jdf.showString(n, truncate))
    258 
    259     def __repr__(self):

/databricks/spark/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py in __call__(self, *args)
    811         answer = self.gateway_client.send_command(command)
    812         return_value = get_return_value(
--> 813             answer, self.gateway_client, self.target_id, self.name)
    814 
    815         for temp_arg in temp_args:

/databricks/spark/python/pyspark/sql/utils.py in deco(*a, **kw)
     43     def deco(*a, **kw):
     44         try:
---> 45             return f(*a, **kw)
     46         except py4j.protocol.Py4JJavaError as e:
     47             s = e.java_exception.toString()

/databricks/spark/python/lib/py4j-0.9-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    306                 raise Py4JJavaError(
    307                     "An error occurred while calling {0}{1}{2}.\n".
--> 308                     format(target_id, ".", name), value)
    309             else:
    310                 raise Py4JError(
Py4JJavaError: An error occurred while calling o77.showString.
: java.io.IOException: No input paths specified in job
    at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:156)
    at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:208)
    at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:199)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
    at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
    at scala.Option.getOrElse(Option.scala:120)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
    at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:190)
    at org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:165)
    at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:174)
    at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499)
    at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499)
    at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
    at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2086)
    at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1498)
    at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1505)
    at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1375)
    at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1374)
    at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2099)
    at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1374)
    at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1456)
at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:170)
    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:497)
    at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
    at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:381)
    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:209)
    at java.lang.Thread.run(Thread.java:745)

你确定文本名称中间有空格?Animal Farm.txt"

 No input paths specified in job

log里面说清楚了,输入的路径不存在。

你是在集群里运行的?那建议把文件扔到hdfs里,路径改为hdfs url。

玩蛇网文章,转载请注明出处和文章网址:https://www.iplaypy.com/wenda/wd14072.html

相关文章 Recommend

玩蛇网Python互助QQ群,欢迎加入-->: 106381465 玩蛇网Python新手群
修订日期:2017年05月23日 - 16时54分03秒 发布自玩蛇网

您现在的位置: 玩蛇网首页 > Python问题解答 > 正文内容
我要分享到:

必知PYTHON教程 Must Know PYTHON Tutorials

必知PYTHON模块 Must Know PYTHON Modules