1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
|
"""
Demo for using cross validation
===============================
"""
import os
import numpy as np
import xgboost as xgb
# load data in do training
CURRENT_DIR = os.path.dirname(__file__)
dtrain = xgb.DMatrix(
os.path.join(CURRENT_DIR, "../data/agaricus.txt.train?format=libsvm")
)
param = {"max_depth": 2, "eta": 1, "objective": "binary:logistic"}
num_round = 2
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,
callbacks=[xgb.callback.EvaluationMonitor(show_stdv=True)],
)
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,
callbacks=[
xgb.callback.EvaluationMonitor(show_stdv=False),
xgb.callback.EarlyStopping(3),
],
)
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)
param["scale_pos_weight"] = ratio
return (dtrain, dtest, param)
# do cross validation, for each fold
# the dtrain, dtest, param will be passed into fpreproc
# 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)
###
# you can also do cross validation with customized loss function
# See custom_objective.py
##
print("running cross validation, with customized 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)
return grad, hess
def evalerror(preds, dtrain):
labels = dtrain.get_label()
preds = 1.0 / (1.0 + np.exp(-preds))
return "error", float(sum(labels != (preds > 0.0))) / len(labels)
param = {"max_depth": 2, "eta": 1}
# train with customized objective
xgb.cv(
param, dtrain, num_round, nfold=5, seed=0, obj=logregobj, custom_metric=evalerror
)
|
