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

new speed test

Browse Source
This commit is contained in:
antinucleon 2014-05-16 18:05:17 -06:00
parent 4bcf947408
commit 4bf23cfbb1
1 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
demo/kaggle-higgs/speedtest.py
View File

@ -42,22 +42,25 @@ param['eval_metric'] = 'auc'
param['silent'] = 1 param['silent'] = 1
param['nthread'] = 4 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')] plst = param.items()+[('eval_metric', 'ams@0.15')]
watchlist = [ (xgmat,'train') ] watchlist = [ (xgmat,'train') ]
# boost 135 tres # boost 10 tres
num_round = 135 num_round = 10
print 'loading data end, start to boost trees' print 'loading data end, start to boost trees'
print "training GBM from sklearn" print "training GBM from sklearn"
tmp = time.time() tmp = time.time()
gbm = GradientBoostingClassifier(n_estimators=135, max_depth=6, verbose=2) gbm = GradientBoostingClassifier(n_estimators=num_round, max_depth=6, verbose=2)
gbm.fit(data, label) gbm.fit(data, label)
print "GBM costs: %s seconds" % str(time.time() - tmp) print "GBM costs: %s seconds" % str(time.time() - tmp)
#raw_input() #raw_input()
print "training xgboost" print "training xgboost"
tmp = time.time() threads = [1, 2, 4, 16]
bst = xgb.train( plst, xgmat, num_round, watchlist ); for i in threads:
print "XGBoost costs: %s seconds" % str(time.time() - tmp) 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' print 'finish training'