[ https://issues.apache.org/jira/browse/MAHOUT-1594?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
jaehoon ko updated MAHOUT-1594: ------------------------------- Attachment: (was: MAHOUT-1594.patch) > Example factorize-movielens-1M.sh does not use HDFS > --------------------------------------------------- > > Key: MAHOUT-1594 > URL: https://issues.apache.org/jira/browse/MAHOUT-1594 > Project: Mahout > Issue Type: Bug > Components: Examples > Environment: Hadoop version: 2.4.0.2.1.1.0-385 > Git hash: 2b65475c3ab682ebd47cffdc6b502698799cd2c8 (trunk) > Reporter: jaehoon ko > Priority: Minor > Labels: newbie, patch > Fix For: 1.0 > > > It seems that factorize-movielens-1M.sh does not use HDFS at all. All paths > look local paths, not HDFS. So the example crashes immeidately because it > cannot find input data from HDFS: > {code} > Exception in thread "main" > org.apache.hadoop.mapreduce.lib.input.InvalidInputException: Input path does > not exist: /tmp/mahout-work-hoseog.lee/movielens/ratings.csv > at > org.apache.hadoop.mapreduce.lib.input.FileInputFormat.singleThreadedListStatus(FileInputFormat.java:320) > at > org.apache.hadoop.mapreduce.lib.input.FileInputFormat.listStatus(FileInputFormat.java:263) > at > org.apache.hadoop.mapreduce.lib.input.FileInputFormat.getSplits(FileInputFormat.java:375) > at > org.apache.hadoop.mapreduce.JobSubmitter.writeNewSplits(JobSubmitter.java:493) > at > org.apache.hadoop.mapreduce.JobSubmitter.writeSplits(JobSubmitter.java:510) > at > org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:394) > at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1285) > at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1282) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:415) > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1557) > at org.apache.hadoop.mapreduce.Job.submit(Job.java:1282) > at org.apache.hadoop.mapreduce.Job.waitForCompletion(Job.java:1303) > at > org.apache.mahout.cf.taste.hadoop.als.DatasetSplitter.run(DatasetSplitter.java:94) > at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:70) > at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:84) > at > org.apache.mahout.cf.taste.hadoop.als.DatasetSplitter.main(DatasetSplitter.java:64) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at > org.apache.hadoop.util.ProgramDriver$ProgramDescription.invoke(ProgramDriver.java:72) > at org.apache.hadoop.util.ProgramDriver.run(ProgramDriver.java:145) > at org.apache.hadoop.util.ProgramDriver.driver(ProgramDriver.java:153) > at org.apache.mahout.driver.MahoutDriver.main(MahoutDriver.java:195) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:606) > at org.apache.hadoop.util.RunJar.main(RunJar.java:212) > {code} -- This message was sent by Atlassian JIRA (v6.2#6252)