-
-
Notifications
You must be signed in to change notification settings - Fork 8.7k
/
test_cli.py
185 lines (157 loc) · 6.73 KB
/
test_cli.py
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
import os
import tempfile
import platform
import xgboost
import subprocess
import numpy
import json
import testing as tm
class TestCLI:
template = '''
booster = gbtree
objective = reg:squarederror
eta = 1.0
gamma = 1.0
seed = {seed}
min_child_weight = 0
max_depth = 3
task = {task}
model_in = {model_in}
model_out = {model_out}
test_path = {test_path}
name_pred = {name_pred}
model_dir = {model_dir}
num_round = 10
data = {data_path}
eval[test] = {data_path}
'''
PROJECT_ROOT = tm.PROJECT_ROOT
def get_exe(self):
if platform.system() == 'Windows':
exe = 'xgboost.exe'
else:
exe = 'xgboost'
exe = os.path.join(self.PROJECT_ROOT, exe)
assert os.path.exists(exe)
return exe
def test_cli_model(self):
data_path = "{root}/demo/data/agaricus.txt.train?format=libsvm".format(
root=self.PROJECT_ROOT)
exe = self.get_exe()
seed = 1994
with tempfile.TemporaryDirectory() as tmpdir:
model_out_cli = os.path.join(
tmpdir, 'test_load_cli_model-cli.json')
model_out_py = os.path.join(
tmpdir, 'test_cli_model-py.json')
config_path = os.path.join(
tmpdir, 'test_load_cli_model.conf')
train_conf = self.template.format(data_path=data_path,
seed=seed,
task='train',
model_in='NULL',
model_out=model_out_cli,
test_path='NULL',
name_pred='NULL',
model_dir='NULL')
with open(config_path, 'w') as fd:
fd.write(train_conf)
subprocess.run([exe, config_path])
predict_out = os.path.join(tmpdir,
'test_load_cli_model-prediction')
predict_conf = self.template.format(task='pred',
seed=seed,
data_path=data_path,
model_in=model_out_cli,
model_out='NULL',
test_path=data_path,
name_pred=predict_out,
model_dir='NULL')
with open(config_path, 'w') as fd:
fd.write(predict_conf)
subprocess.run([exe, config_path])
cli_predt = numpy.loadtxt(predict_out)
parameters = {
'booster': 'gbtree',
'objective': 'reg:squarederror',
'eta': 1.0,
'gamma': 1.0,
'seed': seed,
'min_child_weight': 0,
'max_depth': 3
}
data = xgboost.DMatrix(data_path)
booster = xgboost.train(parameters, data, num_boost_round=10)
booster.save_model(model_out_py)
py_predt = booster.predict(data)
numpy.testing.assert_allclose(cli_predt, py_predt)
cli_model = xgboost.Booster(model_file=model_out_cli)
cli_predt = cli_model.predict(data)
numpy.testing.assert_allclose(cli_predt, py_predt)
with open(model_out_cli, 'rb') as fd:
cli_model_bin = fd.read()
with open(model_out_py, 'rb') as fd:
py_model_bin = fd.read()
assert hash(cli_model_bin) == hash(py_model_bin)
def test_cli_help(self):
exe = self.get_exe()
completed = subprocess.run([exe], stdout=subprocess.PIPE)
error_msg = completed.stdout.decode('utf-8')
ret = completed.returncode
assert ret == 1
assert error_msg.find('Usage') != -1
assert error_msg.find('eval[NAME]') != -1
completed = subprocess.run([exe, '-V'], stdout=subprocess.PIPE)
msg = completed.stdout.decode('utf-8')
assert msg.find('XGBoost') != -1
v = xgboost.__version__
if v.find('SNAPSHOT') != -1:
assert msg.split(':')[1].strip() == v.split('-')[0]
elif v.find('rc') != -1:
assert msg.split(':')[1].strip() == v.split('rc')[0]
else:
assert msg.split(':')[1].strip() == v
def test_cli_model_json(self):
exe = self.get_exe()
data_path = "{root}/demo/data/agaricus.txt.train?format=libsvm".format(
root=self.PROJECT_ROOT)
seed = 1994
with tempfile.TemporaryDirectory() as tmpdir:
model_out_cli = os.path.join(
tmpdir, 'test_load_cli_model-cli.json')
config_path = os.path.join(tmpdir, 'test_load_cli_model.conf')
train_conf = self.template.format(data_path=data_path,
seed=seed,
task='train',
model_in='NULL',
model_out=model_out_cli,
test_path='NULL',
name_pred='NULL',
model_dir='NULL')
with open(config_path, 'w') as fd:
fd.write(train_conf)
subprocess.run([exe, config_path])
with open(model_out_cli, 'r') as fd:
model = json.load(fd)
assert model['learner']['gradient_booster']['name'] == 'gbtree'
def test_cli_save_model(self):
'''Test save on final round'''
exe = self.get_exe()
data_path = "{root}/demo/data/agaricus.txt.train?format=libsvm".format(
root=self.PROJECT_ROOT)
seed = 1994
with tempfile.TemporaryDirectory() as tmpdir:
model_out_cli = os.path.join(tmpdir, '0010.model')
config_path = os.path.join(tmpdir, 'test_load_cli_model.conf')
train_conf = self.template.format(data_path=data_path,
seed=seed,
task='train',
model_in='NULL',
model_out='NULL',
test_path='NULL',
name_pred='NULL',
model_dir=tmpdir)
with open(config_path, 'w') as fd:
fd.write(train_conf)
subprocess.run([exe, config_path])
assert os.path.exists(model_out_cli)