diff options
author | Paul Baltescu <pauldb89@gmail.com> | 2013-04-24 17:18:10 +0100 |
---|---|---|
committer | Paul Baltescu <pauldb89@gmail.com> | 2013-04-24 17:18:10 +0100 |
commit | e8b412577b9d3fe2090b9f48443f919cd268c809 (patch) | |
tree | b46a7b51d365519dfb5170d71bac33be6d3e29b9 /training/dtrain/hstreaming/hadoop-streaming-job.sh | |
parent | d189426a7ea56b71eb6e25ed02a7b0993cfb56a8 (diff) | |
parent | 5aee54869aa19cfe9be965e67a472e94449d16da (diff) |
Merge branch 'master' of https://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, 0 insertions, 30 deletions
diff --git a/training/dtrain/hstreaming/hadoop-streaming-job.sh b/training/dtrain/hstreaming/hadoop-streaming-job.sh deleted file mode 100755 index 92419956..00000000 --- a/training/dtrain/hstreaming/hadoop-streaming-job.sh +++ /dev/null @@ -1,30 +0,0 @@ -#!/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" - |