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
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
|
"""Scikit-optimize plotting tests."""
import matplotlib.pyplot as plt
import numpy as np
import pytest
from numpy.testing import assert_array_almost_equal
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import cross_val_score
from sklearn.tree import DecisionTreeClassifier
from skopt import (
Optimizer,
expected_minimum,
expected_minimum_random_sampling,
gp_minimize,
plots,
)
from skopt.benchmarks import bench3
from skopt.plots import (
_evaluate_min_params,
partial_dependence_1D,
partial_dependence_2D,
)
from skopt.space import Categorical, Integer
def save_axes(ax, filename):
"""Save matplotlib axes `ax` to an image `filename`."""
fig = plt.gcf()
fig.add_axes(ax)
fig.savefig(filename)
@pytest.mark.slow_test
def test_plots_work():
"""Basic smoke tests to make sure plotting doesn't crash."""
SPACE = [
Integer(1, 20, name='max_depth'),
Integer(2, 100, name='min_samples_split'),
Integer(5, 30, name='min_samples_leaf'),
Integer(1, 30, name='max_features'),
Categorical(['gini', 'entropy'], name='criterion'),
Categorical(list('abcdefghij'), name='dummy'),
]
def objective(params):
clf = DecisionTreeClassifier(
random_state=3,
**{dim.name: val for dim, val in zip(SPACE, params) if dim.name != 'dummy'}
)
X, y = load_breast_cancer(return_X_y=True)
return -np.mean(cross_val_score(clf, X, y))
res = gp_minimize(objective, SPACE, n_calls=10, random_state=3)
x = [
[11, 52, 8, 14, 'entropy', 'f'],
[14, 90, 10, 2, 'gini', 'a'],
[7, 90, 6, 14, 'entropy', 'f'],
]
samples = res.space.transform(x)
xi_ = [1.0, 10.5, 20.0]
yi_ = [-0.9240883492576596, -0.9240745890422687, -0.9240586402439884]
xi, yi = partial_dependence_1D(res.space, res.models[-1], 0, samples, n_points=3)
assert_array_almost_equal(xi, xi_)
assert_array_almost_equal(yi, yi_, 2)
xi_ = [0, 1]
yi_ = [-0.9241087603770617, -0.9240188905968352]
xi, yi = partial_dependence_1D(res.space, res.models[-1], 4, samples, n_points=3)
assert_array_almost_equal(xi, xi_)
assert_array_almost_equal(yi, yi_, 2)
xi_ = [0, 1]
yi_ = [1.0, 10.5, 20.0]
zi_ = [
[-0.92412562, -0.92403575],
[-0.92411186, -0.92402199],
[-0.92409591, -0.92400604],
]
xi, yi, zi = partial_dependence_2D(
res.space, res.models[-1], 0, 4, samples, n_points=3
)
assert_array_almost_equal(xi, xi_)
assert_array_almost_equal(yi, yi_)
assert_array_almost_equal(zi, zi_, 2)
x_min, f_min = expected_minimum_random_sampling(res, random_state=1)
x_min2, f_min2 = expected_minimum(res, random_state=1)
assert x_min == x_min2
assert f_min == f_min2
plots.plot_convergence(res)
plots.plot_evaluations(res)
plots.plot_objective(res)
plots.plot_objective(res, dimensions=["a", "b", "c", "d", "e", "f"])
plots.plot_objective(res, minimum='expected_minimum_random')
plots.plot_objective(
res, sample_source='expected_minimum_random', n_minimum_search=10000
)
plots.plot_objective(res, sample_source='result')
plots.plot_regret(res)
plots.plot_objective_2D(res, 0, 4)
plots.plot_histogram(res, 0, 4)
# TODO: Compare plots to known good results?
# Look into how matplotlib does this.
@pytest.mark.slow_test
def test_plots_work_without_cat():
"""Basic smoke tests to make sure plotting doesn't crash."""
SPACE = [
Integer(1, 20, name='max_depth'),
Integer(2, 100, name='min_samples_split'),
Integer(5, 30, name='min_samples_leaf'),
Integer(1, 30, name='max_features'),
]
def objective(params):
clf = DecisionTreeClassifier(
random_state=3,
**{dim.name: val for dim, val in zip(SPACE, params) if dim.name != 'dummy'}
)
X, y = load_breast_cancer(return_X_y=True)
return -np.mean(cross_val_score(clf, X, y))
res = gp_minimize(objective, SPACE, n_calls=10, random_state=3)
plots.plot_convergence(res)
plots.plot_evaluations(res)
plots.plot_objective(res)
plots.plot_objective(res, minimum='expected_minimum')
plots.plot_objective(res, sample_source='expected_minimum', n_minimum_search=10)
plots.plot_objective(res, sample_source='result')
plots.plot_regret(res)
# TODO: Compare plots to known good results?
# Look into how matplotlib does this.
def test_plots_skip_constant():
"""Test that constant dimension are properly skipped."""
SPACE = [
Categorical([0], name="dummy"),
Categorical([0], name="dummy"),
Integer(1, 20, name='max_depth'),
Integer(1, 20, name='max_depth'),
]
X, y = load_breast_cancer(return_X_y=True)
def objective(params):
clf = DecisionTreeClassifier(
random_state=3,
**{dim.name: val for dim, val in zip(SPACE, params) if dim.name != 'dummy'}
)
return -np.mean(cross_val_score(clf, X, y))
res = gp_minimize(objective, SPACE, n_calls=10, random_state=3)
print(res.space)
print(plots._map_categories(res.space, res.x_iters, res.x))
plots.plot_evaluations(res)
@pytest.mark.fast_test
def test_evaluate_min_params():
res = gp_minimize(
bench3,
[(-2.0, 2.0)],
x0=[0.0],
noise=1e-8,
n_calls=8,
n_random_starts=3,
random_state=1,
)
x_min, f_min = expected_minimum(res, random_state=1)
x_min2, f_min2 = expected_minimum_random_sampling(
res, n_random_starts=1000, random_state=1
)
plots.plot_gaussian_process(res)
assert _evaluate_min_params(res, params='result') == res.x
assert _evaluate_min_params(res, params=[1.0]) == [1.0]
assert _evaluate_min_params(res, params='expected_minimum', random_state=1) == x_min
assert (
_evaluate_min_params(
res, params='expected_minimum', n_minimum_search=20, random_state=1
)
== x_min
)
assert (
_evaluate_min_params(
res, params='expected_minimum_random', n_minimum_search=1000, random_state=1
)
== x_min2
)
def test_names_dimensions():
# Define objective
def objective(x, noise_level=0.1):
return (
np.sin(5 * x[0]) * (1 - np.tanh(x[0] ** 2))
+ np.random.randn() * noise_level
)
# Initialize Optimizer
opt = Optimizer([(-2.0, 2.0)], n_initial_points=2)
# Optimize
for _ in range(3):
next_x = opt.ask()
f_val = objective(next_x)
res = opt.tell(next_x, f_val)
# Plot results
plots.plot_objective(res)
@pytest.mark.slow_test
@pytest.mark.parametrize('acq_func', ['EI', 'EIps', 'PI', 'PIps', 'gp_hedge', 'LCB'])
def test_plot_gaussian_process_works(acq_func):
def objective(x):
return x[0] ** 2
def objective_ps(x):
return x[0] ** 2, x[0] + 1
if acq_func.endswith("ps"):
obj = objective_ps
else:
obj = objective
res = gp_minimize(
obj, [(-1, 1)], n_calls=2, n_initial_points=2, random_state=1, acq_func=acq_func
)
plots.plot_gaussian_process(res)
|
