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

24
demo/kaggle-higgs/higgs-numpy.py
View File

@@ -1,9 +1,15 @@
#!/usr/bin/python
# this is the example script to use xgboost to train
import inspect
import os
import sys
import numpy as np
# add path of xgboost python module
sys.path.append('../../python/')
code_path = os.path.join(
os.path.split(inspect.getfile(inspect.currentframe()))[0], "../../python")
sys.path.append(code_path)
import xgboost as xgb
test_size = 550000
@@ -12,19 +18,19 @@ test_size = 550000
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 '
dtrain = np.loadtxt( dpath+'/training.csv', delimiter=',', skiprows=1, converters={32: lambda x:int(x=='s'.encode('utf-8')) } )
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 )
@@ -43,14 +49,14 @@ param['silent'] = 1
param['nthread'] = 16
# you can directly throw param in, though we want to watch multiple metrics here
plst = param.items()+[('eval_metric', 'ams@0.15')]
plst = list(param.items())+[('eval_metric', 'ams@0.15')]
watchlist = [ (xgmat,'train') ]
# boost 120 tres
num_round = 120
print 'loading data end, start to boost trees'
print ('loading data end, start to boost trees')
bst = xgb.train( plst, xgmat, num_round, watchlist );
# save out model
bst.save_model('higgs.model')
print 'finish training'
print ('finish training')

6
demo/kaggle-higgs/higgs-pred.py
View File

@@ -19,13 +19,13 @@ dtest = np.loadtxt( dpath+'/test.csv', delimiter=',', skiprows=1 )
data = dtest[:,1:31]
idx = dtest[:,0]
print 'finish loading from csv '
print ('finish loading from csv ')
xgmat = xgb.DMatrix( data, missing = -999.0 )
bst = xgb.Booster({'nthread':16})
bst.load_model( modelfile )
ypred = bst.predict( xgmat )
res = [ ( int(idx[i]), ypred[i] ) for i in xrange(len(ypred)) ]
res = [ ( int(idx[i]), ypred[i] ) for i in range(len(ypred)) ]
rorder = {}
for k, v in sorted( res, key = lambda x:-x[1] ):
@@ -47,7 +47,7 @@ for k, v in res:
ntot += 1
fo.close()
print 'finished writing into prediction file'
print ('finished writing into prediction file')

14
demo/kaggle-higgs/run.sh
View File

@@ -1,4 +1,14 @@
#!/bin/bash
python higgs-numpy.py
python higgs-pred.py
python -u higgs-numpy.py
ret=$?
if [[ $ret != 0 ]]; then
echo "ERROR in higgs-numpy.py"
exit $ret
fi
python -u higgs-pred.py
ret=$?
if [[ $ret != 0 ]]; then
echo "ERROR in higgs-pred.py"
exit $ret
fi

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')