Merge branch 'dev' of https://github.com/tqchen/xgboost into dev

Conflicts:
	demo/rank/mq2008.conf
	demo/rank/runexp.sh
	regrank/xgboost_regrank_obj.h

demo/binary_classification/mushroom.conf

@@ -2,7 +2,7 @@
 # choose the tree booster, 0: tree, 1: linear
 booster_type = 0 
 # choose logistic regression loss function for binary classification
-loss_type = 2 
+objective = binary:logistic
 
 # Tree Booster Parameters
 # step size shrinkage

demo/kaggle-higgs/README.md

@@ -17,4 +17,4 @@ make
 
 
 
-
+speedtest.py compares xgboost's speed on this dataset with sklearn.GBM

demo/kaggle-higgs/higgs-numpy.py

@@ -31,8 +31,9 @@ xgmat = xgb.DMatrix( data, label=label, missing = -999.0, weight=weight )
 
 # setup parameters for xgboost
 param = {}
-# use logistic regression loss
-param['loss_type'] = 3
+# use logistic regression loss, use raw prediction before logistic transformation
+# since we only need the rank
+param['objective'] = 'binary:logitraw'
 # scale weight of positive examples
 param['scale_pos_weight'] = sum_wneg/sum_wpos
 param['bst:eta'] = 0.1 

demo/kaggle-higgs/run.sh

@@ -1,4 +1,4 @@
 #!/bin/bash
 
-./higgs-numpy.py
-./higgs-pred.py
+python higgs-numpy.py
+python higgs-pred.py

demo/kaggle-higgs/speedtest.py

@@ -0,0 +1,66 @@
+#!/usr/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['objective'] = 'binary:logitraw'
+# 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
+
+plst = param.items()+[('eval_metric', 'ams@0.15')]
+
+watchlist = [ (xgmat,'train') ]
+# boost 10 tres
+num_round = 10
+print 'loading data end, start to boost trees'
+print "training GBM from sklearn"
+tmp = time.time()
+gbm = GradientBoostingClassifier(n_estimators=num_round, max_depth=6, verbose=2)
+gbm.fit(data, label)
+print "sklearn.GBM costs: %s seconds" % str(time.time() - tmp)
+#raw_input()
+print "training xgboost"
+threads = [1, 2, 4, 16]
+for i in threads:
+    param['nthread'] = i
+    tmp = time.time()
+    plst = param.items()+[('eval_metric', 'ams@0.15')]
+    bst = xgb.train( plst, xgmat, num_round, watchlist );
+    print "XGBoost with %d thread costs: %s seconds" % (i, str(time.time() - tmp))
+
+print 'finish training'

demo/rank/README

@@ -1 +1,13 @@
-The dataset for ranking demo is from LETOR04 MQ2008 fold1,http://research.microsoft.com/en-us/um/beijing/projects/letor/letor4download.aspx
+Instructions:
+The dataset for ranking demo is from LETOR04 MQ2008 fold1, 
+You can use the following command to run the example
+
+
+Get the data: ./wgetdata.sh
+Run the example: ./runexp.sh
+
+
+
+
+
+

demo/rank/mq2008.conf

@@ -2,10 +2,8 @@
 # choose the tree booster, 0: tree, 1: linear
 booster_type = 0 
 
+# so far, we have pairwise rank
 objective="rank:pairwise"
-#objective="rank:softmax"
-#objective="rank:map"
-#objective="rank:ndcg"
 
 # Tree Booster Parameters
 # step size shrinkage
@@ -16,8 +14,7 @@ bst:gamma = 1.0
 bst:min_child_weight = 0.1
 # maximum depth of a tree
 bst:max_depth = 6
-eval_metric = "ndcg"
-eval_metric = "map"
+
 # Task parameters
 # the number of round to do boosting
 num_round = 4

demo/rank/wgetdata.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+wget http://research.microsoft.com/en-us/um/beijing/projects/letor/LETOR4.0/Data/MQ2008.rar
+unrar x MQ2008.rar
+mv -f MQ2008/Fold1/*.txt .

demo/regression/machine.conf

@@ -1,9 +1,9 @@
 # General Parameters, see comment for each definition
 # choose the tree booster, 0: tree, 1: linear
 booster_type = 0 
-# this is the only difference with classification, use 0: linear regression
-# when labels are in [0,1] we can also use 1: logistic regression
-loss_type = 0
+# this is the only difference with classification, use reg:linear to do linear classification
+# when labels are in [0,1] we can also use reg:logistic
+objective = reg:linear
 
 # Tree Booster Parameters
 # step size shrinkage