从reduceByKey（）调用函数时在单元测试期间导入错误

时间：2016-01-11 14:44:18

标签： unit-testing python-3.x apache-spark pyspark

我的测试脚本的当前目录结构如下：

project/
    script/
        __init__.py 
        map.py
    test/
        __init.py__
        test_map.py

我的map.py定义如下：

def add(x,y):
    return x+y

def map_add(df):
    result = df.map(lambda x: (x.key, x.value)).reduceByKey(add)
    return result

test_map.py如下所示：

def add_pyspark_path():
    """
    Add PySpark to the PYTHONPATH
    """
    import sys
    import os
    try:
        sys.path.append(os.path.join(os.environ['SPARK_HOME'], "python"))
        # Spark 1.6
        sys.path.append(os.path.join(os.environ['SPARK_HOME'],
                                     "python", "lib", "py4j-0.9-src.zip"))
    except KeyError:
        print("SPARK_HOME not set")
        sys.exit(1)

# To import pyspark
add_pyspark_path()

import unittest

from pyspark import SparkContext, SparkConf
from pyspark.sql import SQLContext
from script.map import map_add


class PySparkTestCase(unittest.TestCase):
    def setUp(self):
        # Setup a new spark context for each test
        conf = SparkConf()
        conf.set("spark.executor.memory", "1g")
        conf.set("spark.cores.max", "1")
        conf.set("spark.app.name", "nosetest")
        self.sc = SparkContext(conf=conf)

    def tearDown(self):
        self.sc.stop()


# This would go in tests/project_test.py
class MapTests(PySparkTestCase):

    def MockDataFrame(self):
        # Get a mock dataframe to test the script
        sqlContext = SQLContext(self.sc)
        rdd = self.sc.parallelize([(1,0), (1,1), (2,0), (2,2)])
        schema = [
            "key",
            "value"
        ]
        dataset = sqlContext.createDataFrame(rdd, schema)
        return dataset

    def test_add(self):
        df = self.MockDataFrame()
        result = map_add(df)
        print(result.collect())
        self.assertEqual(result.count(), 2)

当我在测试目录中运行nosetest时，测试失败。我找不到名为“script”的模块。 但是，当我修改map_add函数以替换要在map.py中的reduceByKey中添加的调用时，如下所示：

def map_add(df):
    result = df.map(lambda x: (x.key, x.value)).reduceByKey(lambda x,y: x+y)
    return result

测试通过。

此外，当我从项目目录运行原始test_map.py时，测试通过。

我无法弄清楚为什么测试在测试目录中没有检测到脚本模块。

以下是错误的日志片段：

test_add (test.test_map.MapTests) ... 16/01/11 15:38:10 ERROR Executor: Exception in task 0.0 in stage 2.0 (TID 5)
org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/pyspark.zip/pyspark/worker.py", line 98, in main
    command = pickleSer._read_with_length(infile)
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/pyspark.zip/pyspark/serializers.py", line 164, in _read_with_length
    return self.loads(obj)
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/pyspark.zip/pyspark/serializers.py", line 419, in loads
    return pickle.loads(obj, encoding=encoding)
ImportError: No module named 'script'

    at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
    at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
    at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.api.python.PairwiseRDD.compute(PythonRDD.scala:342)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
    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)
16/01/11 15:38:10 ERROR TaskSetManager: Task 0 in stage 2.0 failed 1 times; aborting job
ERROR

======================================================================
ERROR: test_add (test.test_map.MapTests)
----------------------------------------------------------------------
Traceback (most recent call last):
  File "/Users/datitran/Desktop/pyspark_test/test/test_map.py", line 56, in test_add
    print(result.collect())
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/pyspark/rdd.py", line 771, in collect
    port = self.ctx._jvm.PythonRDD.collectAndServe(self._jrdd.rdd())
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/py4j-0.9-src.zip/py4j/java_gateway.py", line 813, in __call__
    answer, self.gateway_client, self.target_id, self.name)
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/pyspark/sql/utils.py", line 45, in deco
    return f(*a, **kw)
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/py4j-0.9-src.zip/py4j/protocol.py", line 308, in get_return_value
    format(target_id, ".", name), value)
nose.proxy.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 2.0 failed 1 times, most recent failure: Lost task 0.0 in stage 2.0 (TID 5, localhost): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/pyspark.zip/pyspark/worker.py", line 98, in main
    command = pickleSer._read_with_length(infile)
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/pyspark.zip/pyspark/serializers.py", line 164, in _read_with_length
    return self.loads(obj)
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/pyspark.zip/pyspark/serializers.py", line 419, in loads
    return pickle.loads(obj, encoding=encoding)
ImportError: No module named 'script'

    at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
    at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
    at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.api.python.PairwiseRDD.compute(PythonRDD.scala:342)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
    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$$failJobAndIndependentStages(DAGScheduler.scala:1431)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
    at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
    at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
    at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
    at scala.Option.foreach(Option.scala:236)
    at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
    at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
    at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
    at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1845)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1858)
    at org.apache.spark.SparkContext.runJob(SparkContext.scala:1929)
    at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:927)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
    at org.apache.spark.rdd.RDD.collect(RDD.scala:926)
    at org.apache.spark.api.python.PythonRDD$.collectAndServe(PythonRDD.scala:405)
    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: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)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/pyspark.zip/pyspark/worker.py", line 98, in main
    command = pickleSer._read_with_length(infile)
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/pyspark.zip/pyspark/serializers.py", line 164, in _read_with_length
    return self.loads(obj)
  File "/usr/local/Cellar/apache-spark/1.6.0/libexec/python/lib/pyspark.zip/pyspark/serializers.py", line 419, in loads
    return pickle.loads(obj, encoding=encoding)
ImportError: No module named 'script'

    at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRDD.scala:166)
    at org.apache.spark.api.python.PythonRunner$$anon$1.<init>(PythonRDD.scala:207)
    at org.apache.spark.api.python.PythonRunner.compute(PythonRDD.scala:125)
    at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:70)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.api.python.PairwiseRDD.compute(PythonRDD.scala:342)
    at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
    at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
    at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
    at org.apache.spark.scheduler.Task.run(Task.scala:89)
    at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    ... 1 more

任何帮助将不胜感激。

1 个答案:

答案 0 :(得分：3)

找到了这个问题的答案，并认为将此分享给社区是一个好主意。如果将代码库拆分为不同的文件夹，这可能很有用。 所以，不知何故，相对重要性不适用于pyspark，因为工作人员没有进口，但我找到了解决这个问题的方法。

首先，在主目录中创建另一个_ init _.py文件，在这种情况下称为“project”，因此结构将如下所示：

project/
    __init__.py
    script/
        __init__.py 
        map.py
    test/
        __init.py__
        test_map.py

其次，将PYTHONPATH表达式添加到spark环境中，以便每个工作人员都知道在哪里搜索导入：

class PySparkTestCase(unittest.TestCase):
    def setUp(self):
        conf = SparkConf()
        conf.set("spark.executor.memory", "1g")
        conf.set("spark.cores.max", "1")
        conf.set("spark.app.name", "nosetest")
        conf.setExecutorEnv("PYTHONPATH", "$PYTHONPATH:" +
                            os.path.abspath(os.path.join(os.path.join(os.path.dirname(os.path.abspath(__file__)), os.pardir), os.pardir)))
        self.sc = SparkContext(conf=conf)

最后，我们需要在python脚本之上导入模块：

from project.script.map import map_add

然后执行spark工作现在就可以了！

相关问题
最新问题