Squashed 'subtree/rabit/' changes from 4db0a62..d4ec037

d4ec037 fix rabit
6612fcf Merge branch 'master' of ssh://github.com/tqchen/rabit
d29892c add mock option statis
4fa054e new tracker
75c647c update tracker for host IP
e4ce8ef add hadoop linear example
76ecb4a add hadoop linear example
2e1c4c9 add hadoop linear example

git-subtree-dir: subtree/rabit
git-subtree-split: d4ec037f2e

rabit-learn/linear/README.md

@@ -1,8 +1,10 @@
 Linear and Logistic Regression
 ====
 * input format: LibSVM
-* Example: [run-linear.sh](run-linear.sh)
-
+* Local Example: [run-linear.sh](run-linear.sh)
+* Runnig on Hadoop: [run-hadoop.sh](run-hadoop.sh)
+  - Set input data to stdin, and model_out=stdout
+    
 Parameters
 ===
 All the parameters can be set by param=value

rabit-learn/linear/run-hadoop.sh

@@ -0,0 +1,20 @@
+#!/bin/bash
+if [ "$#" -lt 3 ];
+then
+	echo "Usage: <nworkers> <path_in_HDFS> [param=val]"
+	exit -1
+fi
+
+# put the local training file to HDFS
+hadoop fs -rm -r -f $2/data
+hadoop fs -rm -r -f $2/mushroom.linear.model
+hadoop fs -mkdir $2/data
+hadoop fs -put ../data/agaricus.txt.train $2/data
+
+# submit to hadoop
+../../tracker/rabit_hadoop.py --host_ip ip  -n $1 -i $2/data/agaricus.txt.train -o $2/mushroom.linear.model linear.rabit stdin model_out=stdout "${*:3}" 
+
+# get the final model file
+hadoop fs -get $2/mushroom.linear.model/part-00000 ./linear.model
+
+./linear.rabit ../data/agaricus.txt.test task=pred model_in=linear.model