From 1b8181bf0d6e9137e6b9ccdbe414aec37377a1a9 Mon Sep 17 00:00:00 2001
From: Chris Dyer <cdyer@allegro.clab.cs.cmu.edu>
Date: Sun, 18 Nov 2012 13:35:42 -0500
Subject: major restructure of the training code

---
 dtrain/hstreaming/hadoop-streaming-job.sh | 30 ------------------------------
 1 file changed, 30 deletions(-)
 delete mode 100755 dtrain/hstreaming/hadoop-streaming-job.sh

(limited to 'dtrain/hstreaming/hadoop-streaming-job.sh')

diff --git a/dtrain/hstreaming/hadoop-streaming-job.sh b/dtrain/hstreaming/hadoop-streaming-job.sh
deleted file mode 100755
index 92419956..00000000
--- a/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"
-
-- 
cgit v1.2.3