summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2011-10-14 17:34:58 +0200
committerPatrick Simianer <p@simianer.de>2011-10-14 17:34:58 +0200
commit68f158b11df9f4072699fe6a4c8022ea54102b28 (patch)
tree7806a1b660921eda128cc049c0f6b843e0915dbf
parent85c8b5036ad69f468017034f1e3b7959f0cb221d (diff)
hstreaming, readme
-rw-r--r--dtrain/README.md8
-rwxr-xr-xdtrain/hstreaming/hadoop-streaming-job.sh6
2 files changed, 9 insertions, 5 deletions
diff --git a/dtrain/README.md b/dtrain/README.md
index 4ed31d43..1ee3823e 100644
--- a/dtrain/README.md
+++ b/dtrain/README.md
@@ -51,11 +51,11 @@ Data
nc-v6.de-en peg
nc-v6.de-en.loo peg
nc-v6.de-en.giza.loo peg
-nc-v6.de-en.symgiza.loo pe
-nv-v6.de-en.cs pe
-nc-v6.de-en.cs.loo pe
+nc-v6.de-en.symgiza.loo peg
+nv-v6.de-en.cs peg
+nc-v6.de-en.cs.loo peg
--
-ep-v6.de-en.cs p
+ep-v6.de-en.cs pe
ep-v6.de-en.cs.loo p
p: prep, e: extract, g: grammar, d: dtrain
diff --git a/dtrain/hstreaming/hadoop-streaming-job.sh b/dtrain/hstreaming/hadoop-streaming-job.sh
index f51b6024..8eb9ac0e 100755
--- a/dtrain/hstreaming/hadoop-streaming-job.sh
+++ b/dtrain/hstreaming/hadoop-streaming-job.sh
@@ -1,5 +1,8 @@
#!/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"
@@ -18,5 +21,6 @@ $HSTREAMING \
-file cdec.ini \
-file nc-wmt11.en.srilm.3.gz \
-jobconf mapred.reduce.tasks=1 \
- -jobconf mapred.max.map.failures.percent=100
+ -jobconf mapred.max.map.failures.percent=100 \
+ -jobconf mapred.job.name="dtrain $ID $EXP"