spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Joseph K. Bradley (JIRA)" <j...@apache.org>
Subject [jira] [Created] (SPARK-6126) RDD[LabeledPoint].toDF().toJSON() fails
Date Tue, 03 Mar 2015 00:28:04 GMT
Joseph K. Bradley created SPARK-6126:
----------------------------------------

             Summary: RDD[LabeledPoint].toDF().toJSON() fails
                 Key: SPARK-6126
                 URL: https://issues.apache.org/jira/browse/SPARK-6126
             Project: Spark
          Issue Type: Bug
          Components: SQL
    Affects Versions: 1.3.0
            Reporter: Joseph K. Bradley
            Priority: Blocker


Reproduce bug in Python:
{code}
from pyspark.mllib.util import MLUtils
data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")
data.toDF().toJSON().count()
{code}

Reproduce bug in Scala:
{code}
import org.apache.spark.mllib.util.MLUtils
val data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_libsvm_data.txt")
data.toDF().toJSON.count()
{code}

Fails with:
{code}
15/03/02 16:02:45 ERROR PythonRDD: Python worker exited unexpectedly (crashed)
org.apache.spark.api.python.PythonException: Traceback (most recent call last):
  File "/Users/josephkb/spark/python/pyspark/worker.py", line 88, in main
    command = pickleSer._read_with_length(infile)
  File "/Users/josephkb/spark/python/pyspark/serializers.py", line 148, in _read_with_length
    length = read_int(stream)
  File "/Users/josephkb/spark/python/pyspark/serializers.py", line 528, in read_int
    raise EOFError
EOFError

	at org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:135)
	at org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:176)
	at org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:94)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
	at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
	at org.apache.spark.scheduler.Task.run(Task.scala:64)
	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:197)
	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
	at java.lang.Thread.run(Thread.java:745)
Caused by: scala.MatchError: (StructType(StructField(type,ByteType,false), StructField(size,IntegerType,true),
StructField(indices,ArrayType(IntegerType,false),true), StructField(values,ArrayType(DoubleType,false),true)),(692,[127,128,129,130,131,154,155,156,157,158,159,181,182,183,184,185,186,187,188,189,207,208,209,210,211,212,213,214,215,216,217,235,236,237,238,239,240,241,242,243,244,245,262,263,264,265,266,267,268,269,270,271,272,273,289,290,291,292,293,294,295,296,297,300,301,302,316,317,318,319,320,321,328,329,330,343,344,345,346,347,348,349,356,357,358,371,372,373,374,384,385,386,399,400,401,412,413,414,426,427,428,429,440,441,442,454,455,456,457,466,467,468,469,470,482,483,484,493,494,495,496,497,510,511,512,520,521,522,523,538,539,540,547,548,549,550,566,567,568,569,570,571,572,573,574,575,576,577,578,594,595,596,597,598,599,600,601,602,603,604,622,623,624,625,626,627,628,629,630,651,652,653,654,655,656,657],[51.0,159.0,253.0,159.0,50.0,48.0,238.0,252.0,252.0,252.0,237.0,54.0,227.0,253.0,252.0,239.0,233.0,252.0,57.0,6.0,10.0,60.0,224.0,252.0,253.0,252.0,202.0,84.0,252.0,253.0,122.0,163.0,252.0,252.0,252.0,253.0,252.0,252.0,96.0,189.0,253.0,167.0,51.0,238.0,253.0,253.0,190.0,114.0,253.0,228.0,47.0,79.0,255.0,168.0,48.0,238.0,252.0,252.0,179.0,12.0,75.0,121.0,21.0,253.0,243.0,50.0,38.0,165.0,253.0,233.0,208.0,84.0,253.0,252.0,165.0,7.0,178.0,252.0,240.0,71.0,19.0,28.0,253.0,252.0,195.0,57.0,252.0,252.0,63.0,253.0,252.0,195.0,198.0,253.0,190.0,255.0,253.0,196.0,76.0,246.0,252.0,112.0,253.0,252.0,148.0,85.0,252.0,230.0,25.0,7.0,135.0,253.0,186.0,12.0,85.0,252.0,223.0,7.0,131.0,252.0,225.0,71.0,85.0,252.0,145.0,48.0,165.0,252.0,173.0,86.0,253.0,225.0,114.0,238.0,253.0,162.0,85.0,252.0,249.0,146.0,48.0,29.0,85.0,178.0,225.0,253.0,223.0,167.0,56.0,85.0,252.0,252.0,252.0,229.0,215.0,252.0,252.0,252.0,196.0,130.0,28.0,199.0,252.0,252.0,253.0,252.0,252.0,233.0,145.0,25.0,128.0,252.0,253.0,252.0,141.0,37.0]))
(of class scala.Tuple2)
	at org.apache.spark.sql.json.JsonRDD$$anonfun$org$apache$spark$sql$json$JsonRDD$$valWriter$1$1.apply(JsonRDD.scala:447)
	at org.apache.spark.sql.json.JsonRDD$$anonfun$org$apache$spark$sql$json$JsonRDD$$valWriter$1$1.apply(JsonRDD.scala:447)
	at org.apache.spark.sql.json.JsonRDD$$anonfun$org$apache$spark$sql$json$JsonRDD$$valWriter$1$1.apply(JsonRDD.scala:461)
	at org.apache.spark.sql.json.JsonRDD$$anonfun$org$apache$spark$sql$json$JsonRDD$$valWriter$1$1.apply(JsonRDD.scala:447)
	at org.apache.spark.sql.json.JsonRDD$$anonfun$org$apache$spark$sql$json$JsonRDD$$valWriter$1$1$$anonfun$apply$7.apply(JsonRDD.scala:482)
	at org.apache.spark.sql.json.JsonRDD$$anonfun$org$apache$spark$sql$json$JsonRDD$$valWriter$1$1$$anonfun$apply$7.apply(JsonRDD.scala:478)
	at scala.collection.IndexedSeqOptimized$class.foreach(IndexedSeqOptimized.scala:33)
	at scala.collection.mutable.ArrayOps$ofRef.foreach(ArrayOps.scala:108)
	at org.apache.spark.sql.json.JsonRDD$$anonfun$org$apache$spark$sql$json$JsonRDD$$valWriter$1$1.apply(JsonRDD.scala:478)
	at org.apache.spark.sql.json.JsonRDD$$anonfun$org$apache$spark$sql$json$JsonRDD$$valWriter$1$1.apply(JsonRDD.scala:447)
	at org.apache.spark.sql.json.JsonRDD$.rowToJSON(JsonRDD.scala:487)
	at org.apache.spark.sql.DataFrame$$anonfun$toJSON$1$$anon$1.next(DataFrame.scala:1132)
	at org.apache.spark.sql.DataFrame$$anonfun$toJSON$1$$anon$1.next(DataFrame.scala:1129)
	at scala.collection.Iterator$class.foreach(Iterator.scala:727)
	at org.apache.spark.sql.DataFrame$$anonfun$toJSON$1$$anon$1.foreach(DataFrame.scala:1129)
	at org.apache.spark.api.python.PythonRDD$.writeIteratorToStream(PythonRDD.scala:405)
	at org.apache.spark.api.python.PythonRDD$WriterThread$$anonfun$run$1.apply(PythonRDD.scala:243)
	at org.apache.spark.util.Utils$.logUncaughtExceptions(Utils.scala:1642)
	at org.apache.spark.api.python.PythonRDD$WriterThread.run(PythonRDD.scala:205)
{code}



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org


Mime
View raw message