polish

5 files changed, 20 insertions, 11 deletions

diff --git a/dtrain/hstreaming/avg.rb b/dtrain/hstreaming/avg.rb
index e0899144..91d4e29a 100755
--- a/dtrain/hstreaming/avg.rb
+++ b/dtrain/hstreaming/avg.rb
@@ -1,4 +1,4 @@
-# avg.rb
+#!/usr/bin/env ruby
 
 shard_count_key = "__SHARD_COUNT__"
 
diff --git a/dtrain/hstreaming/cdec.ini b/dtrain/hstreaming/cdec.ini
index ce1e1ae2..61f13e86 100644
--- a/dtrain/hstreaming/cdec.ini
+++ b/dtrain/hstreaming/cdec.ini
@@ -4,7 +4,7 @@ scfg_max_span_limit=15
 intersection_strategy=cube_pruning
 cubepruning_pop_limit=200
 feature_function=WordPenalty
-feature_function=KLanguageModel test/example/nc-wmt11.en.srilm.gz
+feature_function=KLanguageModel nc-wmt11.en.srilm.gz
 #feature_function=ArityPenalty
 #feature_function=CMR2008ReorderingFeatures
 #feature_function=InputIndicator
diff --git a/dtrain/hstreaming/hadoop-streaming-job.sh b/dtrain/hstreaming/hadoop-streaming-job.sh
index 4c0238f3..90c2b790 100755
--- a/dtrain/hstreaming/hadoop-streaming-job.sh
+++ b/dtrain/hstreaming/hadoop-streaming-job.sh
@@ -1,26 +1,31 @@
-#!/bin/bash
+#!/bin/sh
 
-EXP=test
+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=nc-v6.de-en.cs.giza.loo/nc-v6.de-en.cs.giza.loo-dtrain1.sz2
-OUT=out/$EXP-weights
+ 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 "red-avg.rb" \
+    -reducer "lplp.rb l2 select_k 100000" \
     -input $IN \
     -output $OUT \
     -file dtrain.sh \
-    -file red-avg.rb \
-    -file ~/exp/cdec-dtrain-ro/dtrain/dtrain \
+    -file lplp.rb \
+    -file ../dtrain \
     -file dtrain.ini \
     -file cdec.ini \
-    -file ~/exp/data/nc-v6.en.3.unk.probing.kenv5 \
-    -jobconf mapred.reduce.tasks=1 \
+    -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"
 
diff --git a/dtrain/hstreaming/rule_count/red.rb b/dtrain/hstreaming/rule_count/red.rb
index 8f9109cc..874ae7ac 100644
--- a/dtrain/hstreaming/rule_count/red.rb
+++ b/dtrain/hstreaming/rule_count/red.rb
@@ -1,3 +1,5 @@
+#!/usr/bin/env ruby
+
 STDIN.set_encoding 'utf-8'
 STDOUT.set_encoding 'utf-8'
 
diff --git a/dtrain/hstreaming/rule_count/rulecount.rb b/dtrain/hstreaming/rule_count/rulecount.rb
index 035bdf06..67361fa4 100644
--- a/dtrain/hstreaming/rule_count/rulecount.rb
+++ b/dtrain/hstreaming/rule_count/rulecount.rb
@@ -1,3 +1,5 @@
+#!/usr/bin/env ruby
+
 STDIN.set_encoding 'utf-8'
 STDOUT.set_encoding 'utf-8'