/usr/bin/python3 /root/PycharmProjects/als_movie/collab_filter.py
25/04/22 06:25:24 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
Training: 3563128, validation: 1189844, test: 1188989

[(21708, 165, 3.5), (21708, 168, 1.0), (21708, 208, 2.0)]
[(21708, 110, 4.5), (21708, 1641, 1.5), (21708, 1682, 4.5)]
[(21708, 95, 3.5), (21708, 153, 1.5), (21708, 161, 4.0)]
1189844
25/04/22 06:25:52 ERROR TaskSetManager: Task 0 in stage 17.0 failed 4 times; aborting job
Traceback (most recent call last):
  File "/root/PycharmProjects/als_movie/collab_filter.py", line 54, in <module>
    lambda_=regularizationParameter)
  File "/usr/local/bin/python3.6/lib/python3.6/site-packages/pyspark/mllib/recommendation.py", line 274, in train
    lambda_, blocks, nonnegative, seed)
  File "/usr/local/bin/python3.6/lib/python3.6/site-packages/pyspark/mllib/common.py", line 130, in callMLlibFunc
    return callJavaFunc(sc, api, *args)
  File "/usr/local/bin/python3.6/lib/python3.6/site-packages/pyspark/mllib/common.py", line 123, in callJavaFunc
    return _java2py(sc, func(*args))
  File "/usr/local/bin/python3.6/lib/python3.6/site-packages/py4j/java_gateway.py", line 1257, in __call__
    answer, self.gateway_client, self.target_id, self.name)
  File "/usr/local/bin/python3.6/lib/python3.6/site-packages/py4j/protocol.py", line 328, in get_return_value
    format(target_id, ".", name), value)
py4j.protocol.Py4JJavaError: An error occurred while calling o135.trainALSModel.
: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 17.0 failed 4 times, most recent failure: Lost task 0.3 in stage 17.0 (TID 17, 100.64.0.10, executor 0): org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/opt/module/spark-2.4.8-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 364, in main
    func, profiler, deserializer, serializer = read_command(pickleSer, infile)
  File "/opt/module/spark-2.4.8-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 69, in read_command
    command = serializer._read_with_length(file)
  File "/opt/module/spark-2.4.8-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/serializers.py", line 173, in _read_with_length
    return self.loads(obj)
  File "/opt/module/spark-2.4.8-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/serializers.py", line 587, in loads
    return pickle.loads(obj, encoding=encoding)
  File "/opt/module/spark-2.4.8-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/mllib/__init__.py", line 28, in <module>
    import numpy
ModuleNotFoundError: No module named 'numpy'

	at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:456)
	at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:592)
	at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:575)
	at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:410)
	at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
	at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
	at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:390)
	at scala.collection.Iterator$class.foreach(Iterator.scala:891)
	at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
	at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
	at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
	at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
	at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:310)
	at scala.collection.AbstractIterator.to(Iterator.scala:1334)
	at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:302)
	at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1334)
	at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:289)
	at scala.collection.AbstractIterator.toArray(Iterator.scala:1334)
	at org.apache.spark.rdd.RDD$$anonfun$take$1$$anonfun$31.apply(RDD.scala:1409)
	at org.apache.spark.rdd.RDD$$anonfun$take$1$$anonfun$31.apply(RDD.scala:1409)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2107)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2107)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
	at org.apache.spark.scheduler.Task.run(Task.scala:123)
	at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:411)
	at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:417)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
	at java.lang.Thread.run(Thread.java:748)

Driver stacktrace:
	at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1925)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1913)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1912)
	at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
	at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
	at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1912)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:948)
	at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:948)
	at scala.Option.foreach(Option.scala:257)
	at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:948)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2146)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2095)
	at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2084)
	at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49)
	at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:759)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:2067)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:2088)
	at org.apache.spark.SparkContext.runJob(SparkContext.scala:2107)
	at org.apache.spark.rdd.RDD$$anonfun$take$1.apply(RDD.scala:1409)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:385)
	at org.apache.spark.rdd.RDD.take(RDD.scala:1382)
	at org.apache.spark.rdd.RDD$$anonfun$isEmpty$1.apply$mcZ$sp(RDD.scala:1517)
	at org.apache.spark.rdd.RDD$$anonfun$isEmpty$1.apply(RDD.scala:1517)
	at org.apache.spark.rdd.RDD$$anonfun$isEmpty$1.apply(RDD.scala:1517)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:385)
	at org.apache.spark.rdd.RDD.isEmpty(RDD.scala:1516)
	at org.apache.spark.mllib.recommendation.ALS.run(ALS.scala:240)
	at org.apache.spark.mllib.api.python.PythonMLLibAPI.trainALSModel(PythonMLLibAPI.scala:488)
	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:498)
	at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
	at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
	at py4j.Gateway.invoke(Gateway.java:282)
	at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
	at py4j.commands.CallCommand.execute(CallCommand.java:79)
	at py4j.GatewayConnection.run(GatewayConnection.java:238)
	at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/opt/module/spark-2.4.8-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 364, in main
    func, profiler, deserializer, serializer = read_command(pickleSer, infile)
  File "/opt/module/spark-2.4.8-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/worker.py", line 69, in read_command
    command = serializer._read_with_length(file)
  File "/opt/module/spark-2.4.8-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/serializers.py", line 173, in _read_with_length
    return self.loads(obj)
  File "/opt/module/spark-2.4.8-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/serializers.py", line 587, in loads
    return pickle.loads(obj, encoding=encoding)
  File "/opt/module/spark-2.4.8-bin-hadoop2.7/python/lib/pyspark.zip/pyspark/mllib/__init__.py", line 28, in <module>
    import numpy
ModuleNotFoundError: No module named 'numpy'

	at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.handlePythonException(PythonRunner.scala:456)
	at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:592)
	at org.apache.spark.api.python.PythonRunner$$anon$1.read(PythonRunner.scala:575)
	at org.apache.spark.api.python.BasePythonRunner$ReaderIterator.hasNext(PythonRunner.scala:410)
	at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:37)
	at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:440)
	at scala.collection.Iterator$$anon$10.hasNext(Iterator.scala:390)
	at scala.collection.Iterator$class.foreach(Iterator.scala:891)
	at scala.collection.AbstractIterator.foreach(Iterator.scala:1334)
	at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:59)
	at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:104)
	at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:48)
	at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:310)
	at scala.collection.AbstractIterator.to(Iterator.scala:1334)
	at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:302)
	at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1334)
	at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:289)
	at scala.collection.AbstractIterator.toArray(Iterator.scala:1334)
	at org.apache.spark.rdd.RDD$$anonfun$take$1$$anonfun$31.apply(RDD.scala:1409)
	at org.apache.spark.rdd.RDD$$anonfun$take$1$$anonfun$31.apply(RDD.scala:1409)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2107)
	at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:2107)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
	at org.apache.spark.scheduler.Task.run(Task.scala:123)
	at org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:411)
	at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:417)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
	... 1 more


Process finished with exit code 1