From 24f99220cbd7955f51e047e2feff030d5e7423a3 Mon Sep 17 00:00:00 2001
From: Boliang Chen <cblsjtu@gmail.com>
Date: Sat, 10 Jan 2015 23:59:25 +0800
Subject: [PATCH] fix bugs

---
 .../hadoop/run_binary_classification.sh       | 43 +++++++++++++++++++
 1 file changed, 43 insertions(+)
 create mode 100755 multi-node/hadoop/run_binary_classification.sh

diff --git a/multi-node/hadoop/run_binary_classification.sh b/multi-node/hadoop/run_binary_classification.sh
new file mode 100755
index 000000000..740a468cf
--- /dev/null
+++ b/multi-node/hadoop/run_binary_classification.sh
@@ -0,0 +1,43 @@
+#!/bin/bash
+
+if [ "$#" -lt 2 ];
+then
+    echo "Usage: <nworkers> <path_in_HDFS>"
+    exit -1
+fi
+
+curDir=`pwd`
+dataDir=../../demo/binary_classification
+trainFile=$dataDir/agaricus.txt.train
+input=$2
+output=$2/model
+
+# generate the training file if it doesnot exist
+if [ ! -f "$trainFile" ];
+then 
+  echo "Generating training file:"
+  cd $dataDir
+  # map feature using indicator encoding, also produce featmap.txt
+  python mapfeat.py
+  # split train and test
+  python mknfold.py agaricus.txt 1
+  cd $curDir
+fi
+
+hadoop fs -mkdir $input
+hadoop fs -put $trainFile $input
+#hadoop fs -rm -skipTrash -r $output
+
+# training and output the final model file
+python ../../rabit/tracker/rabit_hadoop.py -n $1 -i $input/agaricus.txt.train -o $output -f $dataDir/mushroom.hadoop.conf \
+    --jobname xgboost_hadoop ../../xgboost mushroom.hadoop.conf data=stdin model_out=stdout
+
+# get the final model file
+hadoop fs -get $output/part-00000 ./final.model
+# output prediction task=pred 
+../../xgboost $dataDir/mushroom.hadoop.conf task=pred model_in=final.model
+# print the boosters of 00002.model in dump.raw.txt
+../../xgboost $dataDir/mushroom.hadoop.conf task=dump model_in=final.model name_dump=dump.raw.txt
+# use the feature map in printing for better visualization
+../../xgboost $dataDir/mushroom.hadoop.conf task=dump model_in=final.model fmap=$dataDir/featmap.txt name_dump=dump.nice.txt
+cat dump.nice.txt