From e0a0343ae671138a0e119c7f954c7ce798554547 Mon Sep 17 00:00:00 2001
From: antinucleon <antinucleon@gmail.com>
Date: Fri, 16 May 2014 17:48:03 -0600
Subject: [PATCH] speedtest

---
 demo/kaggle-higgs/speedtest.py | 63 ++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)
 create mode 100755 demo/kaggle-higgs/speedtest.py

diff --git a/demo/kaggle-higgs/speedtest.py b/demo/kaggle-higgs/speedtest.py
new file mode 100755
index 000000000..1b07d4619
--- /dev/null
+++ b/demo/kaggle-higgs/speedtest.py
@@ -0,0 +1,63 @@
+#!/usr/local/bin/python
+# this is the example script to use xgboost to train
+import sys
+import numpy as np
+# add path of xgboost python module
+sys.path.append('../../python/')
+import xgboost as xgb
+from sklearn.ensemble import GradientBoostingClassifier
+import time
+test_size = 550000
+
+# path to where the data lies
+dpath = 'data'
+
+# load in training data, directly use numpy
+dtrain = np.loadtxt( dpath+'/training.csv', delimiter=',', skiprows=1, converters={32: lambda x:int(x=='s') } )
+print 'finish loading from csv '
+
+label  = dtrain[:,32]
+data   = dtrain[:,1:31]
+# rescale weight to make it same as test set
+weight = dtrain[:,31] * float(test_size) / len(label)
+
+sum_wpos = sum( weight[i] for i in xrange(len(label)) if label[i] == 1.0  )
+sum_wneg = sum( weight[i] for i in xrange(len(label)) if label[i] == 0.0  )
+
+# print weight statistics
+print 'weight statistics: wpos=%g, wneg=%g, ratio=%g' % ( sum_wpos, sum_wneg, sum_wneg/sum_wpos )
+
+# construct xgboost.DMatrix from numpy array, treat -999.0 as missing value
+xgmat = xgb.DMatrix( data, label=label, missing = -999.0, weight=weight )
+
+# setup parameters for xgboost
+param = {}
+# use logistic regression loss
+param['loss_type'] = 1
+# scale weight of positive examples
+param['scale_pos_weight'] = sum_wneg/sum_wpos
+param['bst:eta'] = 0.1
+param['bst:max_depth'] = 6
+param['eval_metric'] = 'auc'
+param['silent'] = 1
+param['nthread'] = 4
+
+# you can directly throw param in, though we want to watch multiple metrics here
+plst = param.items()+[('eval_metric', 'ams@0.15')]
+
+watchlist = [ (xgmat,'train') ]
+# boost 135 tres
+num_round = 135
+print 'loading data end, start to boost trees'
+print "training GBM from sklearn"
+tmp = time.time()
+gbm = GradientBoostingClassifier(n_estimators=135, max_depth=6, verbose=2)
+gbm.fit(data, label)
+print "GBM costs: %s seconds" % str(time.time() - tmp)
+#raw_input()
+print "training xgboost"
+tmp = time.time()
+bst = xgb.train( plst, xgmat, num_round, watchlist );
+print "XGBoost costs: %s seconds" % str(time.time() - tmp)
+
+print 'finish training'