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

allow booster to be pickable, add copy function

Browse Source
This commit is contained in:
tqchen 2015-05-16 12:59:55 -07:00
parent 39f1da08d2
commit e6b8b23a2c
1 changed files with 19 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
demo/guide-python/basic_walkthrough.py
View File

@ -1,7 +1,9 @@
#!/usr/bin/python #!/usr/bin/python
import numpy as np import numpy as np
import scipy.sparse import scipy.sparse
import pickle
import xgboost as xgb import xgboost as xgb
import copy
### simple example ### simple example
# load file from text file, also binary buffer generated by xgboost # load file from text file, also binary buffer generated by xgboost
@ -19,7 +21,7 @@ bst = xgb.train(param, dtrain, num_round, watchlist)
# this is prediction # this is prediction
preds = bst.predict(dtest) preds = bst.predict(dtest)
labels = dtest.get_label() labels = dtest.get_label()
print ('error=%f' % ( sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) /float(len(preds)))) print ('error=%f' % ( sum(1 for i in range(len(preds)) if int(preds[i]>0.5)!=labels[i]) /float(len(preds))))
bst.save_model('0001.model') bst.save_model('0001.model')
# dump model # dump model
bst.dump_model('dump.raw.txt') bst.dump_model('dump.raw.txt')
@ -28,6 +30,7 @@ bst.dump_model('dump.nice.txt','../data/featmap.txt')
# save dmatrix into binary buffer # save dmatrix into binary buffer
dtest.save_binary('dtest.buffer') dtest.save_binary('dtest.buffer')
# save model
bst.save_model('xgb.model') bst.save_model('xgb.model')
# load model and data in # load model and data in
bst2 = xgb.Booster(model_file='xgb.model') bst2 = xgb.Booster(model_file='xgb.model')
@ -36,6 +39,14 @@ preds2 = bst2.predict(dtest2)
# assert they are the same # assert they are the same
assert np.sum(np.abs(preds2-preds)) == 0 assert np.sum(np.abs(preds2-preds)) == 0
# alternatively, you can pickle the booster
pks = pickle.dumps(bst2)
# load model and data in
bst3 = pickle.loads(pks)
preds3 = bst2.predict(dtest2)
# assert they are the same
assert np.sum(np.abs(preds3-preds)) == 0
### ###
# build dmatrix from scipy.sparse # build dmatrix from scipy.sparse
print ('start running example of build DMatrix from scipy.sparse CSR Matrix') print ('start running example of build DMatrix from scipy.sparse CSR Matrix')
@ -44,22 +55,22 @@ row = []; col = []; dat = []
i = 0 i = 0
for l in open('../data/agaricus.txt.train'): for l in open('../data/agaricus.txt.train'):
arr = l.split() arr = l.split()
labels.append( int(arr[0])) labels.append(int(arr[0]))
for it in arr[1:]: for it in arr[1:]:
k,v = it.split(':') k,v = it.split(':')
row.append(i); col.append(int(k)); dat.append(float(v)) row.append(i); col.append(int(k)); dat.append(float(v))
i += 1 i += 1
csr = scipy.sparse.csr_matrix( (dat, (row,col)) ) csr = scipy.sparse.csr_matrix((dat, (row,col)))
dtrain = xgb.DMatrix( csr, label = labels ) dtrain = xgb.DMatrix(csr, label = labels)
watchlist = [(dtest,'eval'), (dtrain,'train')] watchlist = [(dtest,'eval'), (dtrain,'train')]
bst = xgb.train( param, dtrain, num_round, watchlist ) bst = xgb.train(param, dtrain, num_round, watchlist)
print ('start running example of build DMatrix from scipy.sparse CSC Matrix') print ('start running example of build DMatrix from scipy.sparse CSC Matrix')
# we can also construct from csc matrix # we can also construct from csc matrix
csc = scipy.sparse.csc_matrix( (dat, (row,col)) ) csc = scipy.sparse.csc_matrix((dat, (row,col)))
dtrain = xgb.DMatrix(csc, label=labels) dtrain = xgb.DMatrix(csc, label=labels)
watchlist = [(dtest,'eval'), (dtrain,'train')] watchlist = [(dtest,'eval'), (dtrain,'train')]
bst = xgb.train( param, dtrain, num_round, watchlist ) bst = xgb.train(param, dtrain, num_round, watchlist)
print ('start running example of build DMatrix from numpy array') 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 # NOTE: npymat is numpy array, we will convert it into scipy.sparse.csr_matrix in internal implementation
@ -67,6 +78,6 @@ print ('start running example of build DMatrix from numpy array')
npymat = csr.todense() npymat = csr.todense()
dtrain = xgb.DMatrix(npymat, label = labels) dtrain = xgb.DMatrix(npymat, label = labels)
watchlist = [(dtest,'eval'), (dtrain,'train')] watchlist = [(dtest,'eval'), (dtrain,'train')]
bst = xgb.train( param, dtrain, num_round, watchlist ) bst = xgb.train(param, dtrain, num_round, watchlist)