97 lines
3.2 KiB
Python
Executable File
97 lines
3.2 KiB
Python
Executable File
#!/usr/bin/python
|
|
import sys
|
|
import numpy as np
|
|
import scipy.sparse
|
|
# append the path to xgboost, you may need to change the following line
|
|
sys.path.append('../')
|
|
import xgboost as xgb
|
|
|
|
### simple example
|
|
# load file from text file, also binary buffer generated by xgboost
|
|
dtrain = xgb.DMatrix('agaricus.txt.train')
|
|
dtest = xgb.DMatrix('agaricus.txt.test')
|
|
|
|
# specify parameters via map, definition are same as c++ version
|
|
param = {'bst:max_depth':2, 'bst:eta':1, 'silent':1, 'objective':'binary:logistic' }
|
|
|
|
# specify validations set to watch performance
|
|
evallist = [(dtest,'eval'), (dtrain,'train')]
|
|
num_round = 2
|
|
bst = xgb.train( param, dtrain, num_round, evallist )
|
|
|
|
# this is prediction
|
|
preds = bst.predict( dtest )
|
|
labels = dtest.get_label()
|
|
print 'error=%f' % ( sum(1 for i in xrange(len(preds)) if int(preds[i]>0.5)!=labels[i]) /float(len(preds)))
|
|
bst.save_model('0001.model')
|
|
# dump model
|
|
bst.dump_model('dump.raw.txt')
|
|
# dump model with feature map
|
|
bst.dump_model('dump.raw.txt','featmap.txt')
|
|
|
|
###
|
|
# build dmatrix in python iteratively
|
|
#
|
|
print 'start running example of build DMatrix in python'
|
|
dtrain = xgb.DMatrix()
|
|
labels = []
|
|
for l in open('agaricus.txt.train'):
|
|
arr = l.split()
|
|
labels.append( int(arr[0]))
|
|
feats = []
|
|
for it in arr[1:]:
|
|
k,v = it.split(':')
|
|
feats.append( (int(k), float(v)) )
|
|
dtrain.add_row( feats )
|
|
dtrain.set_label( labels )
|
|
evallist = [(dtest,'eval'), (dtrain,'train')]
|
|
|
|
bst = xgb.train( param, dtrain, num_round, evallist )
|
|
|
|
###
|
|
# build dmatrix from scipy.sparse
|
|
print 'start running example of build DMatrix from scipy.sparse'
|
|
labels = []
|
|
row = []; col = []; dat = []
|
|
i = 0
|
|
for l in open('agaricus.txt.train'):
|
|
arr = l.split()
|
|
labels.append( int(arr[0]))
|
|
for it in arr[1:]:
|
|
k,v = it.split(':')
|
|
row.append(i); col.append(int(k)); dat.append(float(v))
|
|
i += 1
|
|
|
|
csr = scipy.sparse.csr_matrix( (dat, (row,col)) )
|
|
dtrain = xgb.DMatrix( csr )
|
|
dtrain.set_label(labels)
|
|
evallist = [(dtest,'eval'), (dtrain,'train')]
|
|
bst = xgb.train( param, dtrain, num_round, evallist )
|
|
|
|
print 'start running example of build DMatrix from numpy array'
|
|
# NOTE: npymat is numpy array, we will convert it into scipy.sparse.csr_matrix in internal implementation,then convert to DMatrix
|
|
npymat = csr.todense()
|
|
dtrain = xgb.DMatrix( npymat )
|
|
dtrain.set_label(labels)
|
|
evallist = [(dtest,'eval'), (dtrain,'train')]
|
|
bst = xgb.train( param, dtrain, num_round, evallist )
|
|
|
|
###
|
|
# advanced: cutomsized loss function, set loss_type to 0, so that predict get untransformed score
|
|
#
|
|
print 'start running example to used cutomized objective function'
|
|
|
|
# note: set loss_type properly, loss_type=2 means the prediction will get logistic transformed
|
|
# in most case, we may want to set loss_type = 0, to get untransformed score to compute gradient
|
|
bst = param = {'bst:max_depth':2, 'bst:eta':1, 'silent':1, 'loss_type':2 }
|
|
|
|
# user define objective function, given prediction, return gradient and second order gradient
|
|
def logregobj( preds, dtrain ):
|
|
labels = dtrain.get_label()
|
|
grad = preds - labels
|
|
hess = preds * (1.0-preds)
|
|
return grad, hess
|
|
|
|
# training with customized objective, we can also do step by step training, simply look at xgboost.py's implementation of train
|
|
bst = xgb.train( param, dtrain, num_round, evallist, logregobj )
|