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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
|
import os
import numpy as np
import xgboost
kRounds = 2
kRows = 1000
kCols = 4
kForests = 2
kMaxDepth = 2
kClasses = 3
X = np.random.randn(kRows, kCols)
w = np.random.uniform(size=kRows)
version = xgboost.__version__
np.random.seed(1994)
target_dir = 'models'
def booster_bin(model):
return os.path.join(target_dir,
'xgboost-' + version + '.' + model + '.bin')
def booster_json(model):
return os.path.join(target_dir,
'xgboost-' + version + '.' + model + '.json')
def skl_bin(model):
return os.path.join(target_dir,
'xgboost_scikit-' + version + '.' + model + '.bin')
def skl_json(model):
return os.path.join(target_dir,
'xgboost_scikit-' + version + '.' + model + '.json')
def generate_regression_model():
print('Regression')
y = np.random.randn(kRows)
data = xgboost.DMatrix(X, label=y, weight=w)
booster = xgboost.train({'tree_method': 'hist',
'num_parallel_tree': kForests,
'max_depth': kMaxDepth},
num_boost_round=kRounds, dtrain=data)
booster.save_model(booster_bin('reg'))
booster.save_model(booster_json('reg'))
reg = xgboost.XGBRegressor(tree_method='hist',
num_parallel_tree=kForests,
max_depth=kMaxDepth,
n_estimators=kRounds)
reg.fit(X, y, w)
reg.save_model(skl_bin('reg'))
reg.save_model(skl_json('reg'))
def generate_logistic_model():
print('Logistic')
y = np.random.randint(0, 2, size=kRows)
assert y.max() == 1 and y.min() == 0
for objective, name in [('binary:logistic', 'logit'), ('binary:logitraw', 'logitraw')]:
data = xgboost.DMatrix(X, label=y, weight=w)
booster = xgboost.train({'tree_method': 'hist',
'num_parallel_tree': kForests,
'max_depth': kMaxDepth,
'objective': objective},
num_boost_round=kRounds, dtrain=data)
booster.save_model(booster_bin(name))
booster.save_model(booster_json(name))
reg = xgboost.XGBClassifier(tree_method='hist',
num_parallel_tree=kForests,
max_depth=kMaxDepth,
n_estimators=kRounds,
objective=objective)
reg.fit(X, y, w)
reg.save_model(skl_bin(name))
reg.save_model(skl_json(name))
def generate_classification_model():
print('Classification')
y = np.random.randint(0, kClasses, size=kRows)
data = xgboost.DMatrix(X, label=y, weight=w)
booster = xgboost.train({'num_class': kClasses,
'tree_method': 'hist',
'num_parallel_tree': kForests,
'max_depth': kMaxDepth},
num_boost_round=kRounds, dtrain=data)
booster.save_model(booster_bin('cls'))
booster.save_model(booster_json('cls'))
cls = xgboost.XGBClassifier(tree_method='hist',
num_parallel_tree=kForests,
max_depth=kMaxDepth,
n_estimators=kRounds)
cls.fit(X, y, w)
cls.save_model(skl_bin('cls'))
cls.save_model(skl_json('cls'))
def generate_ranking_model():
print('Learning to Rank')
y = np.random.randint(5, size=kRows)
w = np.random.uniform(size=20)
g = np.repeat(50, 20)
data = xgboost.DMatrix(X, y, weight=w)
data.set_group(g)
booster = xgboost.train({'objective': 'rank:ndcg',
'num_parallel_tree': kForests,
'tree_method': 'hist',
'max_depth': kMaxDepth},
num_boost_round=kRounds,
dtrain=data)
booster.save_model(booster_bin('ltr'))
booster.save_model(booster_json('ltr'))
ranker = xgboost.sklearn.XGBRanker(n_estimators=kRounds,
tree_method='hist',
objective='rank:ndcg',
max_depth=kMaxDepth,
num_parallel_tree=kForests)
ranker.fit(X, y, g, sample_weight=w)
ranker.save_model(skl_bin('ltr'))
ranker.save_model(skl_json('ltr'))
def write_versions():
versions = {'numpy': np.__version__,
'xgboost': version}
with open(os.path.join(target_dir, 'version'), 'w') as fd:
fd.write(str(versions))
if __name__ == '__main__':
if not os.path.exists(target_dir):
os.mkdir(target_dir)
generate_regression_model()
generate_logistic_model()
generate_classification_model()
generate_ranking_model()
write_versions()
|
