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
|
import numpy as np
import pytest
from numpy.testing import assert_array_equal
from skopt.learning import ExtraTreesRegressor, RandomForestRegressor
def truth(X):
return 0.5 * np.sin(1.75 * X[:, 0])
@pytest.mark.fast_test
def test_random_forest():
# toy sample
X = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1]]
y = [-1, -1, -1, 1, 1, 1]
T = [[-1, -1], [2, 2], [3, 2]]
true_result = [-1, 1, 1]
clf = RandomForestRegressor(n_estimators=10, random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
clf = RandomForestRegressor(
n_estimators=10, min_impurity_decrease=0.1, random_state=1
)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
clf = RandomForestRegressor(
n_estimators=10,
criterion="squared_error",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.0,
max_features=None,
max_leaf_nodes=None,
min_impurity_decrease=0.0,
bootstrap=True,
oob_score=False,
n_jobs=1,
random_state=1,
verbose=0,
warm_start=False,
)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
clf = RandomForestRegressor(n_estimators=10, max_features=1, random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
# also test apply
leaf_indices = clf.apply(X)
assert leaf_indices.shape == (len(X), clf.n_estimators)
@pytest.mark.fast_test
def test_extra_forest():
# toy sample
X = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1]]
y = [-1, -1, -1, 1, 1, 1]
T = [[-1, -1], [2, 2], [3, 2]]
true_result = [-1, 1, 1]
clf = ExtraTreesRegressor(n_estimators=10, random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
clf = ExtraTreesRegressor(
n_estimators=10, min_impurity_decrease=0.1, random_state=1
)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
clf = ExtraTreesRegressor(
n_estimators=10,
criterion="squared_error",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.0,
max_features=None,
max_leaf_nodes=None,
min_impurity_decrease=0.0,
bootstrap=False,
oob_score=False,
n_jobs=1,
random_state=1,
verbose=0,
warm_start=False,
)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
clf = ExtraTreesRegressor(n_estimators=10, max_features=1, random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert 10 == len(clf)
# also test apply
leaf_indices = clf.apply(X)
assert leaf_indices.shape == (len(X), clf.n_estimators)
|
