python stats.py
2018-05-25 14:36:34 WARN  NativeCodeLoader:62 - Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
Traceback (most recent call last):
  File "stats.py", line 108, in <module>
    run()
  File "stats.py", line 81, in run
    .map(assign_bins) \
  File "/home/m0hawk/.local/share/virtualenvs/large-scale-data-poc6M778/lib/python3.6/site-packages/pyspark/rdd.py", line 1945, in groupByKey
    shuffled = locally_combined.partitionBy(numPartitions, partitionFunc)
  File "/home/m0hawk/.local/share/virtualenvs/large-scale-data-poc6M778/lib/python3.6/site-packages/pyspark/rdd.py", line 1746, in partitionBy
    numPartitions = self._defaultReducePartitions()
  File "/home/m0hawk/.local/share/virtualenvs/large-scale-data-poc6M778/lib/python3.6/site-packages/pyspark/rdd.py", line 2259, in _defaultReducePartitions
    return self.getNumPartitions()
  File "/home/m0hawk/.local/share/virtualenvs/large-scale-data-poc6M778/lib/python3.6/site-packages/pyspark/rdd.py", line 2455, in getNumPartitions
    return self._prev_jrdd.partitions().size()
  File "/home/m0hawk/.local/share/virtualenvs/large-scale-data-poc6M778/lib/python3.6/site-packages/py4j/java_gateway.py", line 1160, in __call__
    answer, self.gateway_client, self.target_id, self.name)
  File "/home/m0hawk/.local/share/virtualenvs/large-scale-data-poc6M778/lib/python3.6/site-packages/py4j/protocol.py", line 320, in get_return_value
    format(target_id, ".", name), value)
py4j.protocol.Py4JJavaError: An error occurred while calling o20.partitions.
: org.apache.hadoop.mapred.InvalidInputException: Input path does not exist: file:/home/m0hawk/Documents/dev/chalmers/large-scale-data/lab4/datasets/5_m_n_input
    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$$anonfun$partitions$2.apply(RDD.scala:253)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
    at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
    at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
    at scala.Option.getOrElse(Option.scala:121)
    at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
    at org.apache.spark.api.java.JavaRDDLike$class.partitions(JavaRDDLike.scala:61)
    at org.apache.spark.api.java.AbstractJavaRDDLike.partitions(JavaRDDLike.scala:45)
    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:214)
    at java.lang.Thread.run(Thread.java:748)