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

Minor edits to coding style (#2835)

Browse Source 
* Some minor changes to the code style

Some minor changes to the code style in file basic_walkthrough.py

* coding style changes

* coding style changes arrcording PEP8

* Update basic_walkthrough.py
This commit is contained in:
LevineHuang
2017-10-27 11:12:54 +08:00
committed by Yuan (Terry) Tang
parent d9d5293cdb
commit 91af8f7106
10 changed files with 51 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
demo/guide-python/basic_walkthrough.py
View File

@@ -10,22 +10,22 @@ dtrain = xgb.DMatrix('../data/agaricus.txt.train')
dtest = xgb.DMatrix('../data/agaricus.txt.test')
# specify parameters via map, definition are same as c++ version
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic' }
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
# specify validations set to watch performance
watchlist = [(dtest,'eval'), (dtrain,'train')]
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 2
bst = xgb.train(param, dtrain, num_round, watchlist)
# this is prediction
preds = bst.predict(dtest)
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')
# dump model
bst.dump_model('dump.raw.txt')
# dump model with feature map
bst.dump_model('dump.nice.txt','../data/featmap.txt')
bst.dump_model('dump.nice.txt', '../data/featmap.txt')
# save dmatrix into binary buffer
dtest.save_binary('dtest.buffer')
@@ -36,7 +36,7 @@ bst2 = xgb.Booster(model_file='xgb.model')
dtest2 = xgb.DMatrix('dtest.buffer')
preds2 = bst2.predict(dtest2)
# 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)
@@ -44,11 +44,11 @@ pks = pickle.dumps(bst2)
bst3 = pickle.loads(pks)
preds3 = bst3.predict(dtest2)
# assert they are the same
assert np.sum(np.abs(preds3-preds)) == 0
assert np.sum(np.abs(preds3 - preds)) == 0
###
# 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')
labels = []
row = []; col = []; dat = []
i = 0
@@ -59,24 +59,22 @@ for l in open('../data/agaricus.txt.train'):
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, label = labels)
watchlist = [(dtest,'eval'), (dtrain,'train')]
csr = scipy.sparse.csr_matrix((dat, (row, col)))
dtrain = xgb.DMatrix(csr, label=labels)
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
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
csc = scipy.sparse.csc_matrix((dat, (row,col)))
csc = scipy.sparse.csc_matrix((dat, (row, col)))
dtrain = xgb.DMatrix(csc, label=labels)
watchlist = [(dtest,'eval'), (dtrain,'train')]
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
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
# then convert to DMatrix
npymat = csr.todense()
dtrain = xgb.DMatrix(npymat, label = labels)
watchlist = [(dtest,'eval'), (dtrain,'train')]
dtrain = xgb.DMatrix(npymat, label=labels)
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
bst = xgb.train(param, dtrain, num_round, watchlist)