Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Compatibility with both Python 2(.7) and 3

Browse Source
This commit is contained in:
Joerg Rings
2014-05-19 11:23:53 -05:00
parent 991634a58e
commit 93d83ca077
12 changed files with 93 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
demo/kaggle-higgs/speedtest.py
View File

@@ -14,18 +14,18 @@ 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 '
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 )
sum_wpos = sum( weight[i] for i in range(len(label)) if label[i] == 1.0 )
sum_wneg = sum( weight[i] for i in range(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 )
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 )
@@ -47,20 +47,20 @@ 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"
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)
print ("sklearn.GBM costs: %s seconds" % str(time.time() - tmp))
#raw_input()
print "training xgboost"
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 ("XGBoost with %d thread costs: %s seconds" % (i, str(time.time() - tmp)))
print 'finish training'
print ('finish training')