summaryrefslogtreecommitdiff
path: root/dtrain/hstreaming/hadoop-streaming-job.sh
diff options
context:
space:
mode:
Diffstat (limited to 'dtrain/hstreaming/hadoop-streaming-job.sh')
-rwxr-xr-xdtrain/hstreaming/hadoop-streaming-job.sh31
1 files changed, 31 insertions, 0 deletions
diff --git a/dtrain/hstreaming/hadoop-streaming-job.sh b/dtrain/hstreaming/hadoop-streaming-job.sh
new file mode 100755
index 00000000..90c2b790
--- /dev/null
+++ b/dtrain/hstreaming/hadoop-streaming-job.sh
@@ -0,0 +1,31 @@
+#!/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 remove the -reducer line if you want to
+# do feature selection/averaging locally (e.g. to
+# keep weights of the iterations)
+$HSTREAMING \
+ -mapper "dtrain.sh" \
+ -reducer "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"
+