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

4
demo/binary_classification/mapfeat.py
View File

@@ -24,7 +24,7 @@ def loadfmap( fname ):
return fmap, nmap
def write_nmap( fo, nmap ):
for i in xrange( len(nmap) ):
for i in range( len(nmap) ):
fo.write('%d\t%s\ti\n' % (i, nmap[i]) )
# start here
@@ -41,7 +41,7 @@ for l in open( 'agaricus-lepiota.data' ):
else:
assert arr[0] == 'e'
fo.write('0')
for i in xrange( 1,len(arr) ):
for i in range( 1,len(arr) ):
fo.write( ' %d:1' % fmap[i][arr[i].strip()] )
fo.write('\n')

2
demo/binary_classification/mknfold.py
View File

@@ -3,7 +3,7 @@ import sys
import random
if len(sys.argv) < 2:
print 'Usage:<filename> <k> [nfold = 5]'
print ('Usage:<filename> <k> [nfold = 5]')
exit(0)
random.seed( 10 )

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')

2
demo/multiclass_classification/train.py
View File

@@ -37,6 +37,6 @@ bst = xgb.train(param, xg_train, num_round, watchlist );
# get prediction
pred = bst.predict( xg_test );
print 'predicting, classification error=%f' % (sum( int(pred[i]) != test_Y[i] for i in xrange(len(test_Y))) / float(len(test_Y)) )
print ('predicting, classification error=%f' % (sum( int(pred[i]) != test_Y[i] for i in range(len(test_Y))) / float(len(test_Y)) ))

26
demo/rank/trans_data.py
View File

@@ -2,18 +2,18 @@ import sys
def save_data(group_data,output_feature,output_group):
if len(group_data) == 0:
return
return
output_group.write(str(len(group_data))+"\n")
for data in group_data:
# only include nonzero features
feats = [ p for p in data[2:] if float(p.split(':')[1]) != 0.0 ]
output_feature.write(data[0] + " " + " ".join(feats) + "\n")
output_feature.write(data[0] + " " + " ".join(feats) + "\n")
if __name__ == "__main__":
if len(sys.argv) != 4:
print "Usage: python trans_data.py [Ranksvm Format Input] [Output Feature File] [Output Group File]"
sys.exit(0)
print ("Usage: python trans_data.py [Ranksvm Format Input] [Output Feature File] [Output Group File]")
sys.exit(0)
fi = open(sys.argv[1])
output_feature = open(sys.argv[2],"w")
@@ -22,16 +22,16 @@ if __name__ == "__main__":
group_data = []
group = ""
for line in fi:
if not line:
break
if "#" in line:
line = line[:line.index("#")]
if not line:
break
if "#" in line:
line = line[:line.index("#")]
splits = line.strip().split(" ")
if splits[1] != group:
save_data(group_data,output_feature,output_group)
group_data = []
group = splits[1]
group_data.append(splits)
if splits[1] != group:
save_data(group_data,output_feature,output_group)
group_data = []
group = splits[1]
group_data.append(splits)
save_data(group_data,output_feature,output_group)

6
demo/regression/mapfeat.py
View File

@@ -7,7 +7,7 @@ fmap = {}
for l in open( 'machine.data' ):
arr = l.split(',')
fo.write(arr[8])
for i in xrange( 0,6 ):
for i in range( 0,6 ):
fo.write( ' %d:%s' %(i,arr[i+2]) )
if arr[0] not in fmap:
@@ -24,9 +24,9 @@ fo = open('featmap.txt', 'w')
# list from machine.names
names = ['vendor','MYCT', 'MMIN', 'MMAX', 'CACH', 'CHMIN', 'CHMAX', 'PRP', 'ERP' ];
for i in xrange(0,6):
for i in range(0,6):
fo.write( '%d\t%s\tint\n' % (i, names[i+1]))
for v, k in sorted( fmap.iteritems(), key = lambda x:x[1] ):
for v, k in sorted( fmap.items(), key = lambda x:x[1] ):
fo.write( '%d\tvendor=%s\ti\n' % (k, v))
fo.close()

2
demo/regression/mknfold.py
View File

@@ -3,7 +3,7 @@ import sys
import random
if len(sys.argv) < 2:
print 'Usage:<filename> <k> [nfold = 5]'
print ('Usage:<filename> <k> [nfold = 5]')
exit(0)
random.seed( 10 )