import os
import sys
os.chdir("/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/bin")
os.curdir
if 'SPARK_HOME' not in os.environ:
os.environ['SPARK_HOME'] = '/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7'
SPARK_HOME = os.environ['SPARK_HOME']
sys.path.insert(0,os.path.join(SPARK_HOME,"python"))
sys.path.insert(0,os.path.join(SPARK_HOME,"python","lib"))
sys.path.insert(0,os.path.join(SPARK_HOME,"python","lib","pyspark.zip"))
sys.path.insert(0,os.path.join(SPARK_HOME,"python","lib","py4j-0.9-src.zip"))
from pyspark import SparkContext
from pyspark import SparkConf
# Optionally configure Spark Settings
conf=SparkConf()
conf.set("spark.executor.memory", "1g")
conf.set("spark.cores.max", "2")
conf.setAppName("V2 Maestros")
## Initialize SparkContext. Run only once. Otherwise you get multiple
#Context Error.
sc = SparkContext('local', conf=conf)
#Test to make sure everything works.
lines=sc.textFile("auto-data.csv")
lines.count()
这是发生的错误。这是一个简单的程序计算文件的输入次数,但出现了这个错误。我将文件保存在代码中提到的两个位置,即使结果是相同的。
Py4JJavaError Traceback (most recent call last)
<ipython-input-6-5c9242495358> in <module>()
1 lines = sc.textFile("auto-save.csv")
----> 2 lines.count()
/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/python/pyspark/rdd.pyc in count(self)
1006 3
1007 """
-> 1008 return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum()
1009
1010 def stats(self):
/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/python/pyspark/rdd.pyc in sum(self)
997 6.0
998 """
--> 999 return self.mapPartitions(lambda x: [sum(x)]).fold(0, operator.add)
1000
1001 def count(self):
/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/python/pyspark/rdd.pyc in fold(self, zeroValue, op)
871 # zeroValue provided to each partition is unique from the one provided
872 # to the final reduce call
--> 873 vals = self.mapPartitions(func).collect()
874 return reduce(op, vals, zeroValue)
875
/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/python/pyspark/rdd.pyc in collect(self)
774 """
775 with SCCallSiteSync(self.context) as css:
--> 776 port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
777 return list(_load_from_socket(port, self._jrdd_deserializer))
778
/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/python/lib/py4j-0.10.1-src.zip/py4j/java_gateway.py in __call__(self, *args)
931 answer = self.gateway_client.send_command(command)
932 return_value = get_return_value(
--> 933 answer, self.gateway_client, self.target_id, self.name)
934
935 for temp_arg in temp_args:
/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/python/pyspark/sql/utils.pyc 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()
/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/python/lib/py4j-0.10.1-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
310 raise Py4JJavaError(
311 "An error occurred while calling {0}{1}{2}.\n".
--> 312 format(target_id, ".", name), value)
313 else:
314 raise Py4JError(
Py4JJavaError: An error occurred while calling z:org.apache.spark.api.python.PythonRDD.collectAndServe.
: org.apache.hadoop.mapred.InvalidInputException: Input path does not exist: file:/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/auto-save.csv
at org.apache.hadoop.mapred.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:287)
at org.apache.hadoop.mapred.FileInputFormat.listStatus(FileInputFormat.java:229)
at org.apache.hadoop.mapred.FileInputFormat.getSplits(FileInputFormat.java:315)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:200)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:248)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:246)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:246)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:248)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:246)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:246)
at org.apache.spark.api.python.PythonRDD.getPartitions(PythonRDD.scala:53)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:248)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:246)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:246)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1911)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:893)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.collect(RDD.scala:892)
at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:453)
at org.apache.spark.api.python.PythonRDD.collectAndServe(PythonRDD.scala)
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:237)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:280)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:128)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:211)
at java.lang.Thread.run(Thread.java:745)
答案 0 :(得分:1)
我遇到了同样的错误,我解决了。如果我们将Spark上下文配置为比系统支持更多的核心作为工作线程。就像我有3核系统一样,但是在我的代码中,当我在下面提到代码时,由于我没有4核,所以它将无法工作。
我收到Py4JJavaerror的不受支持的Spark上下文配置代码:
from pyspark import SparkContext, SparkConf
conf = SparkConf().setAppName("Collinear Points").setMaster("local[4]") #Initialize spark context using 4 local cores as workers
sc = SparkContext(conf=conf)
from pyspark.rdd import RDD
所有类型的系统都支持SparkContext配置代码,因为在下面,我们没有将核心明确地初始化为工作器。
from pyspark import SparkContext, SparkConf
conf = SparkConf().setAppName("Collinear Points")
sc = SparkContext('local',conf=conf)
from pyspark.rdd import RDD
答案 1 :(得分:0)
您应该将输出保存为
lines=sc.textFile("hdfs:///tmp/auto-data.csv")
或只是
lines=sc.textFile("/tmp/auto-data.csv")
此命令会将输出写入hdfs
答案 2 :(得分:0)
例外是不言自明的。尝试给出auto-save.csv
的绝对路径
lines=sc.textFile("auto-data.csv")
或将auto-save.csv
移至/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/
thonRDD.collectAndServe.
: org.apache.hadoop.mapred.InvalidInputException: Input path does not exist: file:/home/hp/Downloads/spark-2.0.0-bin-hadoop2.7/auto-save.csv