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
Show Stats 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)

5
demo/guide-python/boost_from_prediction.py
View File

@ -20,5 +20,6 @@ ptest = bst.predict(dtest, output_margin=True)
dtrain.set_base_margin(ptrain)
dtest.set_base_margin(ptest)
print ('this is result of running from initial prediction')
bst = xgb.train(param, dtrain, 1, watchlist)
print('this is result of running from initial prediction')
bst = xgb.train(param, dtrain, 1, watchlist)

24
demo/guide-python/cross_validation.py
View File

@ -7,30 +7,30 @@ dtrain = xgb.DMatrix('../data/agaricus.txt.train')
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
num_round = 2
print ('running cross validation')
print('running cross validation')
# do cross validation, this will print result out as
# [iteration] metric_name:mean_value+std_value
# std_value is standard deviation of the metric
xgb.cv(param, dtrain, num_round, nfold=5,
metrics={'error'}, seed = 0,
metrics={'error'}, seed=0,
callbacks=[xgb.callback.print_evaluation(show_stdv=True)])
print ('running cross validation, disable standard deviation display')
print('running cross validation, disable standard deviation display')
# do cross validation, this will print result out as
# [iteration] metric_name:mean_value
res = xgb.cv(param, dtrain, num_boost_round=10, nfold=5,
metrics={'error'}, seed = 0,
metrics={'error'}, seed=0,
callbacks=[xgb.callback.print_evaluation(show_stdv=False),
xgb.callback.early_stop(3)])
print (res)
print ('running cross validation, with preprocessing function')
print(res)
print('running cross validation, with preprocessing function')
# define the preprocessing function
# used to return the preprocessed training, test data, and parameter
# we can use this to do weight rescale, etc.
# as a example, we try to set scale_pos_weight
def fpreproc(dtrain, dtest, param):
label = dtrain.get_label()
ratio = float(np.sum(label == 0)) / np.sum(label==1)
ratio = float(np.sum(label == 0)) / np.sum(label == 1)
param['scale_pos_weight'] = ratio
return (dtrain, dtest, param)
@ -39,18 +39,18 @@ def fpreproc(dtrain, dtest, param):
# then the return value of fpreproc will be used to generate
# results of that fold
xgb.cv(param, dtrain, num_round, nfold=5,
metrics={'auc'}, seed = 0, fpreproc = fpreproc)
metrics={'auc'}, seed=0, fpreproc=fpreproc)
###
# you can also do cross validation with cutomized loss function
# See custom_objective.py
##
print ('running cross validation, with cutomsized loss function')
print('running cross validation, with cutomsized loss function')
def logregobj(preds, dtrain):
labels = dtrain.get_label()
preds = 1.0 / (1.0 + np.exp(-preds))
grad = preds - labels
hess = preds * (1.0-preds)
hess = preds * (1.0 - preds)
return grad, hess
def evalerror(preds, dtrain):
labels = dtrain.get_label()
@ -58,5 +58,5 @@ def evalerror(preds, dtrain):
param = {'max_depth':2, 'eta':1, 'silent':1}
# train with customized objective
xgb.cv(param, dtrain, num_round, nfold = 5, seed = 0,
obj = logregobj, feval=evalerror)
xgb.cv(param, dtrain, num_round, nfold=5, seed=0,
obj=logregobj, feval=evalerror)

4
demo/guide-python/custom_objective.py
View File

@ -4,7 +4,7 @@ import xgboost as xgb
###
# advanced: customized loss function
#
print ('start running example to used customized objective function')
print('start running example to used customized objective function')
dtrain = xgb.DMatrix('../data/agaricus.txt.train')
dtest = xgb.DMatrix('../data/agaricus.txt.test')
@ -22,7 +22,7 @@ def logregobj(preds, dtrain):
labels = dtrain.get_label()
preds = 1.0 / (1.0 + np.exp(-preds))
grad = preds - labels
hess = preds * (1.0-preds)
hess = preds * (1.0 - preds)
return grad, hess
# user defined evaluation function, return a pair metric_name, result

4
demo/guide-python/external_memory.py
View File

@ -12,13 +12,13 @@ dtrain = xgb.DMatrix('../data/agaricus.txt.train#dtrain.cache')
dtest = xgb.DMatrix('../data/agaricus.txt.test#dtest.cache')
# specify validations set to watch performance
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic' }
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
# performance notice: set nthread to be the number of your real cpu
# some cpu offer two threads per core, for example, a 4 core cpu with 8 threads, in such case set nthread=4
#param['nthread']=num_real_cpu
watchlist = [(dtest,'eval'), (dtrain,'train')]
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 2
bst = xgb.train(param, dtrain, num_round, watchlist)

4
demo/guide-python/gamma_regression.py
View File

@ -15,11 +15,11 @@ dtest = xgb.DMatrix(data[4741:6773, 0:34], data[4741:6773, 34])
param = {'silent':1, 'objective':'reg:gamma', 'booster':'gbtree', 'base_score':3}
# the rest of settings are the same
watchlist = [(dtest,'eval'), (dtrain,'train')]
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 30
# training and evaluation
bst = xgb.train(param, dtrain, num_round, watchlist)
preds = bst.predict(dtest)
labels = dtest.get_label()
print ('test deviance=%f' % (2 * np.sum((labels - preds) / preds - np.log(labels) + np.log(preds))))
print('test deviance=%f' % (2 * np.sum((labels - preds) / preds - np.log(labels) + np.log(preds))))

6
demo/guide-python/generalized_linear_model.py
View File

@ -11,7 +11,7 @@ dtest = xgb.DMatrix('../data/agaricus.txt.test')
# lambda is the L2 regularizer
# you can also set lambda_bias which is L2 regularizer on the bias term
param = {'silent':1, 'objective':'binary:logistic', 'booster':'gblinear',
'alpha': 0.0001, 'lambda': 1 }
'alpha': 0.0001, 'lambda': 1}
# normally, you do not need to set eta (step_size)
# XGBoost uses a parallel coordinate descent algorithm (shotgun),
@ -22,9 +22,9 @@ param = {'silent':1, 'objective':'binary:logistic', 'booster':'gblinear',
##
# the rest of settings are the same
##
watchlist = [(dtest,'eval'), (dtrain,'train')]
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 4
bst = xgb.train(param, dtrain, num_round, watchlist)
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))))

10
demo/guide-python/predict_first_ntree.py
View File

@ -5,16 +5,16 @@ import xgboost as xgb
### load data in do training
dtrain = xgb.DMatrix('../data/agaricus.txt.train')
dtest = xgb.DMatrix('../data/agaricus.txt.test')
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic' }
watchlist = [(dtest,'eval'), (dtrain,'train')]
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 3
bst = xgb.train(param, dtrain, num_round, watchlist)
print ('start testing prediction from first n trees')
print('start testing prediction from first n trees')
### predict using first 1 tree
label = dtest.get_label()
ypred1 = bst.predict(dtest, ntree_limit=1)
# by default, we predict using all the trees
ypred2 = bst.predict(dtest)
print ('error of ypred1=%f' % (np.sum((ypred1>0.5)!=label) /float(len(label))))
print ('error of ypred2=%f' % (np.sum((ypred2>0.5)!=label) /float(len(label))))
print('error of ypred1=%f' % (np.sum((ypred1 > 0.5) != label) / float(len(label))))
print('error of ypred2=%f' % (np.sum((ypred2 > 0.5) != label) / float(len(label))))

6
demo/guide-python/predict_leaf_indices.py
View File

@ -4,8 +4,8 @@ import xgboost as xgb
### load data in do training
dtrain = xgb.DMatrix('../data/agaricus.txt.train')
dtest = xgb.DMatrix('../data/agaricus.txt.test')
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic' }
watchlist = [(dtest,'eval'), (dtrain,'train')]
param = {'max_depth':2, 'eta':1, 'silent':1, 'objective':'binary:logistic'}
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 3
bst = xgb.train(param, dtrain, num_round, watchlist)
@ -15,5 +15,5 @@ leafindex = bst.predict(dtest, ntree_limit=2, pred_leaf=True)
print(leafindex.shape)
print(leafindex)
### predict all trees
leafindex = bst.predict(dtest, pred_leaf = True)
leafindex = bst.predict(dtest, pred_leaf=True)
print(leafindex.shape)

6
demo/guide-python/sklearn_examples.py
View File

@ -20,7 +20,7 @@ y = digits['target']
X = digits['data']
kf = KFold(n_splits=2, shuffle=True, random_state=rng)
for train_index, test_index in kf.split(X):
xgb_model = xgb.XGBClassifier().fit(X[train_index],y[train_index])
xgb_model = xgb.XGBClassifier().fit(X[train_index], y[train_index])
predictions = xgb_model.predict(X[test_index])
actuals = y[test_index]
print(confusion_matrix(actuals, predictions))
@ -31,7 +31,7 @@ y = iris['target']
X = iris['data']
kf = KFold(n_splits=2, shuffle=True, random_state=rng)
for train_index, test_index in kf.split(X):
xgb_model = xgb.XGBClassifier().fit(X[train_index],y[train_index])
xgb_model = xgb.XGBClassifier().fit(X[train_index], y[train_index])
predictions = xgb_model.predict(X[test_index])
actuals = y[test_index]
print(confusion_matrix(actuals, predictions))
@ -42,7 +42,7 @@ y = boston['target']
X = boston['data']
kf = KFold(n_splits=2, shuffle=True, random_state=rng)
for train_index, test_index in kf.split(X):
xgb_model = xgb.XGBRegressor().fit(X[train_index],y[train_index])
xgb_model = xgb.XGBRegressor().fit(X[train_index], y[train_index])
predictions = xgb_model.predict(X[test_index])
actuals = y[test_index]
print(mean_squared_error(actuals, predictions))