diff options
| author | Patrick Simianer <p@simianer.de> | 2011-11-28 11:34:41 +0100 |
|---|---|---|
| committer | Patrick Simianer <p@simianer.de> | 2011-11-28 11:34:41 +0100 |
| commit | 6e4367db4136e7a7de3771edf964a16c2fdf08a6 (patch) | |
| tree | d8e705ae35ecfae235c39e799740d62c289bd3d5 /dtrain/hstreaming/hadoop-streaming-job.sh | |
| parent | 8aa98e9aa2a786151aab1e9398bb03a6ba1ca383 (diff) | |
hstreaming stuff
Diffstat (limited to 'dtrain/hstreaming/hadoop-streaming-job.sh')
| -rwxr-xr-x | dtrain/hstreaming/hadoop-streaming-job.sh | 16 |
1 files changed, 8 insertions, 8 deletions
diff --git a/dtrain/hstreaming/hadoop-streaming-job.sh b/dtrain/hstreaming/hadoop-streaming-job.sh index 788c9fd1..4c0238f3 100755 --- a/dtrain/hstreaming/hadoop-streaming-job.sh +++ b/dtrain/hstreaming/hadoop-streaming-job.sh @@ -1,26 +1,26 @@ #!/bin/bash -ID= EXP=test HADOOP_HOME=/usr/lib/hadoop-0.20 JAR=contrib/streaming/hadoop-streaming-0.20.2-cdh3u1.jar HSTREAMING="$HADOOP_HOME/bin/hadoop jar $HADOOP_HOME/$JAR" -IN=nc-v6.de-en/nc-v6.de-en-dtrain.1500m -OUT=nc-v6.de-en/nc-v6.de-en-dtrain.1500m-weights + IN=nc-v6.de-en.cs.giza.loo/nc-v6.de-en.cs.giza.loo-dtrain1.sz2 +OUT=out/$EXP-weights $HSTREAMING \ - -mapper "dtrain -c dtrain.ini --hstreaming" \ + -mapper "dtrain.sh" \ -reducer "red-avg.rb" \ -input $IN \ -output $OUT \ + -file dtrain.sh \ -file red-avg.rb \ - -file ../dtrain \ + -file ~/exp/cdec-dtrain-ro/dtrain/dtrain \ -file dtrain.ini \ -file cdec.ini \ - -file nc-wmt11.en.srilm.3.gz \ + -file ~/exp/data/nc-v6.en.3.unk.probing.kenv5 \ -jobconf mapred.reduce.tasks=1 \ - -jobconf mapred.max.map.failures.percent=100 \ - -jobconf mapred.job.name="dtrain $ID $EXP" + -jobconf mapred.max.map.failures.percent=0 \ + -jobconf mapred.job.name="dtrain $EXP" |