Null Pointer Exception running DictionaryVectorizer with ngram=2 on Reuters
dataset
-----------------------------------------------------------------------------------
Key: MAHOUT-486
URL: https://issues.apache.org/jira/browse/MAHOUT-486
Project: Mahout
Issue Type: Bug
Components: Utils
Affects Versions: 0.4
Reporter: Robin Anil
Assignee: Drew Farris
Fix For: 0.4
java.io.IOException: Spill failed
at
org.apache.hadoop.mapred.MapTask$MapOutputBuffer.collect(MapTask.java:860)
at
org.apache.hadoop.mapred.MapTask$NewOutputCollector.write(MapTask.java:541)
at
org.apache.hadoop.mapreduce.TaskInputOutputContext.write(TaskInputOutputContext.java:80)
at
org.apache.mahout.utils.nlp.collocations.llr.CollocMapper$1.apply(CollocMapper.java:127)
at
org.apache.mahout.utils.nlp.collocations.llr.CollocMapper$1.apply(CollocMapper.java:114)
at
org.apache.mahout.math.map.OpenObjectIntHashMap.forEachPair(OpenObjectIntHashMap.java:186)
at
org.apache.mahout.utils.nlp.collocations.llr.CollocMapper.map(CollocMapper.java:114)
at
org.apache.mahout.utils.nlp.collocations.llr.CollocMapper.map(CollocMapper.java:41)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:144)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:621)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:305)
at
org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:177)
Caused by: java.lang.NullPointerException
at java.io.ByteArrayOutputStream.write(ByteArrayOutputStream.java:86)
at java.io.DataOutputStream.write(DataOutputStream.java:90)
at
org.apache.mahout.utils.nlp.collocations.llr.Gram.write(Gram.java:181)
at
org.apache.hadoop.io.serializer.WritableSerialization$WritableSerializer.serialize(WritableSerialization.java:90)
at
org.apache.hadoop.io.serializer.WritableSerialization$WritableSerializer.serialize(WritableSerialization.java:77)
at org.apache.hadoop.mapred.IFile$Writer.append(IFile.java:179)
at
org.apache.hadoop.mapred.Task$CombineOutputCollector.collect(Task.java:880)
at
org.apache.hadoop.mapred.Task$NewCombinerRunner$OutputConverter.write(Task.java:1201)
at
org.apache.hadoop.mapreduce.TaskInputOutputContext.write(TaskInputOutputContext.java:80)
at
org.apache.mahout.utils.nlp.collocations.llr.CollocCombiner.reduce(CollocCombiner.java:40)
at
org.apache.mahout.utils.nlp.collocations.llr.CollocCombiner.reduce(CollocCombiner.java:25)
at org.apache.hadoop.mapreduce.Reducer.run(Reducer.java:176)
at
org.apache.hadoop.mapred.Task$NewCombinerRunner.combine(Task.java:1222)
at
org.apache.hadoop.mapred.MapTask$MapOutputBuffer.sortAndSpill(MapTask.java:1265)
at
org.apache.hadoop.mapred.MapTask$MapOutputBuffer.access$1800(MapTask.java:686)
at
org.apache.hadoop.mapred.MapTask$MapOutputBuffer$SpillThread.run(MapTask.java:1173)
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
