From c34367b2077bdee159efecdbe115e6eb5fd28677 Mon Sep 17 00:00:00 2001
From: tqchen <tianqi.tchen@gmail.com>
Date: Mon, 26 Jan 2015 10:27:44 -0800
Subject: [PATCH] add msd

---
 .gitignore                     |  2 ++
 demo/.gitignore                |  1 +
 demo/yearpredMSD/csv2libsvm.py | 14 ++++++++++++++
 demo/yearpredMSD/runexp.sh     | 20 ++++++++++++++++++++
 4 files changed, 37 insertions(+)
 create mode 100644 demo/.gitignore
 create mode 100755 demo/yearpredMSD/csv2libsvm.py
 create mode 100755 demo/yearpredMSD/runexp.sh

diff --git a/.gitignore b/.gitignore
index d454c6d1d..ee5928043 100644
--- a/.gitignore
+++ b/.gitignore
@@ -45,3 +45,5 @@ Debug
 *save
 *csv
 .Rproj.user
+xgboost
+xgboost.mock
diff --git a/demo/.gitignore b/demo/.gitignore
new file mode 100644
index 000000000..e52797d15
--- /dev/null
+++ b/demo/.gitignore
@@ -0,0 +1 @@
+*.libsvm
\ No newline at end of file
diff --git a/demo/yearpredMSD/csv2libsvm.py b/demo/yearpredMSD/csv2libsvm.py
new file mode 100755
index 000000000..d7c1d15c1
--- /dev/null
+++ b/demo/yearpredMSD/csv2libsvm.py
@@ -0,0 +1,14 @@
+#!/usr/bin/python
+import sys
+
+if len(sys.argv) < 3:
+    print 'Usage: <csv> <libsvm>'
+    print 'convert a all numerical csv to libsvm'
+
+fo = open(sys.argv[2], 'w')
+for l in open(sys.argv[1]):
+    arr = l.split(',')
+    fo.write('%s' % arr[0])
+    for i in xrange(len(arr) - 1):
+        fo.write(' %d:%s' % (i, arr[i+1]))
+fo.close()
diff --git a/demo/yearpredMSD/runexp.sh b/demo/yearpredMSD/runexp.sh
new file mode 100755
index 000000000..fa75b837e
--- /dev/null
+++ b/demo/yearpredMSD/runexp.sh
@@ -0,0 +1,20 @@
+#!/bin/bash
+
+if [ -f YearPredictionMSD.txt ]
+then
+    echo "use existing data to run experiment"
+else
+    echo "getting data from uci, make sure you are connected to internet"
+    wget https://archive.ics.uci.edu/ml/machine-learning-databases/00203/YearPredictionMSD.txt.zip
+    unzip YearPredictionMSD.txt.zip
+fi
+echo "start making data.."
+# map feature using indicator encoding, also produce featmap.txt
+python csv2libsvm.py YearPredictionMSD.txt yearpredMSD.libsvm
+head -n 463715 yearpredMSD.libsvm > yearpredMSD.libsvm.train
+tail -n 51630 yearpredMSD.libsvm > yearpredMSD.libsvm.test
+echo "finish making the data"
+../../xgboost yearpredMSD.conf
+
+
+ 
\ No newline at end of file