diff options
| author | Michael Denkowski <michael.j.denkowski@gmail.com> | 2012-12-22 16:01:23 -0500 |
|---|---|---|
| committer | Michael Denkowski <michael.j.denkowski@gmail.com> | 2012-12-22 16:01:23 -0500 |
| commit | 778a4cec55f82bcc66b3f52de7cc871e8daaeb92 (patch) | |
| tree | 2a5bccaa85965855104c4e8ac3738b2e1c77f164 /training/dtrain/hstreaming/hadoop-streaming-job.sh | |
| parent | 57fff9eea5ba0e71fb958fdb4f32d17f2fe31108 (diff) | |
| parent | d21491daa5e50b4456c7c5f9c2e51d25afd2a757 (diff) | |
Merge branch 'master' of git://github.com/redpony/cdec
Diffstat (limited to 'training/dtrain/hstreaming/hadoop-streaming-job.sh')
| -rwxr-xr-x | training/dtrain/hstreaming/hadoop-streaming-job.sh | 30 |
1 files changed, 30 insertions, 0 deletions
diff --git a/training/dtrain/hstreaming/hadoop-streaming-job.sh b/training/dtrain/hstreaming/hadoop-streaming-job.sh new file mode 100755 index 00000000..92419956 --- /dev/null +++ b/training/dtrain/hstreaming/hadoop-streaming-job.sh @@ -0,0 +1,30 @@ +#!/bin/sh + +EXP=a_simple_test + +# change these vars to fit your hadoop installation +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=input_on_hdfs +OUT=output_weights_on_hdfs + +# you can -reducer to NONE if you want to +# do feature selection/averaging locally (e.g. to +# keep weights of all epochs) +$HSTREAMING \ + -mapper "dtrain.sh" \ + -reducer "ruby lplp.rb l2 select_k 100000" \ + -input $IN \ + -output $OUT \ + -file dtrain.sh \ + -file lplp.rb \ + -file ../dtrain \ + -file dtrain.ini \ + -file cdec.ini \ + -file ../test/example/nc-wmt11.en.srilm.gz \ + -jobconf mapred.reduce.tasks=30 \ + -jobconf mapred.max.map.failures.percent=0 \ + -jobconf mapred.job.name="dtrain $EXP" + |