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
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
|
"""
Testing for the forest module (sklearn.ensemble.forest).
"""
# Authors: Gilles Louppe, Brian Holt
# License: BSD 3
import numpy as np
from numpy.testing import assert_array_equal
from numpy.testing import assert_array_almost_equal
from numpy.testing import assert_equal
from numpy.testing import assert_almost_equal
from nose.tools import assert_true
from sklearn.utils.testing import assert_less, assert_greater
from sklearn.grid_search import GridSearchCV
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import RandomForestRegressor
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.ensemble import ExtraTreesRegressor
from sklearn import datasets
# 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]
# also load the iris dataset
# and randomly permute it
iris = datasets.load_iris()
rng = np.random.RandomState(0)
perm = rng.permutation(iris.target.size)
iris.data = iris.data[perm]
iris.target = iris.target[perm]
# also load the boston dataset
# and randomly permute it
boston = datasets.load_boston()
perm = rng.permutation(boston.target.size)
boston.data = boston.data[perm]
boston.target = boston.target[perm]
def test_classification_toy():
"""Check classification on a toy dataset."""
# Random forest
clf = RandomForestClassifier(n_estimators=10, random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert_equal(10, len(clf))
clf = RandomForestClassifier(n_estimators=10, max_features=1,
random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert_equal(10, len(clf))
# Extra-trees
clf = ExtraTreesClassifier(n_estimators=10, random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert_equal(10, len(clf))
clf = ExtraTreesClassifier(n_estimators=10, max_features=1,
random_state=1)
clf.fit(X, y)
assert_array_equal(clf.predict(T), true_result)
assert_equal(10, len(clf))
def test_iris():
"""Check consistency on dataset iris."""
for c in ("gini", "entropy"):
# Random forest
clf = RandomForestClassifier(n_estimators=10, criterion=c,
random_state=1)
clf.fit(iris.data, iris.target)
score = clf.score(iris.data, iris.target)
assert score > 0.9, "Failed with criterion %s and score = %f" % (c,
score)
clf = RandomForestClassifier(n_estimators=10, criterion=c,
max_features=2, random_state=1)
clf.fit(iris.data, iris.target)
score = clf.score(iris.data, iris.target)
assert score > 0.5, "Failed with criterion %s and score = %f" % (c,
score)
# Extra-trees
clf = ExtraTreesClassifier(n_estimators=10, criterion=c,
random_state=1)
clf.fit(iris.data, iris.target)
score = clf.score(iris.data, iris.target)
assert score > 0.9, "Failed with criterion %s and score = %f" % (c,
score)
clf = ExtraTreesClassifier(n_estimators=10, criterion=c,
max_features=2, random_state=1)
clf.fit(iris.data, iris.target)
score = clf.score(iris.data, iris.target)
assert score > 0.9, "Failed with criterion %s and score = %f" % (c,
score)
def test_boston():
"""Check consistency on dataset boston house prices."""
for c in ("mse",):
# Random forest
clf = RandomForestRegressor(n_estimators=5, criterion=c,
random_state=1)
clf.fit(boston.data, boston.target)
score = clf.score(boston.data, boston.target)
assert score < 3, ("Failed with max_features=None, "
"criterion %s and score = %f" % (c, score))
clf = RandomForestRegressor(n_estimators=5, criterion=c,
max_features=6, random_state=1)
clf.fit(boston.data, boston.target)
score = clf.score(boston.data, boston.target)
assert score < 3, ("Failed with max_features=None, "
"criterion %s and score = %f" % (c, score))
# Extra-trees
clf = ExtraTreesRegressor(n_estimators=5, criterion=c, random_state=1)
clf.fit(boston.data, boston.target)
score = clf.score(boston.data, boston.target)
assert score < 3, ("Failed with max_features=None, "
"criterion %s and score = %f" % (c, score))
clf = ExtraTreesRegressor(n_estimators=5, criterion=c, max_features=6,
random_state=1)
clf.fit(boston.data, boston.target)
score = clf.score(boston.data, boston.target)
assert score < 3, ("Failed with max_features=None, "
"criterion %s and score = %f" % (c, score))
def test_probability():
"""Predict probabilities."""
# Random forest
clf = RandomForestClassifier(n_estimators=10, random_state=1,
max_features=1, max_depth=1)
clf.fit(iris.data, iris.target)
assert_array_almost_equal(np.sum(clf.predict_proba(iris.data), axis=1),
np.ones(iris.data.shape[0]))
assert_array_almost_equal(clf.predict_proba(iris.data),
np.exp(clf.predict_log_proba(iris.data)))
# Extra-trees
clf = ExtraTreesClassifier(n_estimators=10, random_state=1, max_features=1,
max_depth=1)
clf.fit(iris.data, iris.target)
assert_array_almost_equal(np.sum(clf.predict_proba(iris.data), axis=1),
np.ones(iris.data.shape[0]))
assert_array_almost_equal(clf.predict_proba(iris.data),
np.exp(clf.predict_log_proba(iris.data)))
def test_importances():
"""Check variable importances."""
X, y = datasets.make_classification(n_samples=1000,
n_features=10,
n_informative=3,
n_redundant=0,
n_repeated=0,
shuffle=False,
random_state=0)
clf = RandomForestClassifier(n_estimators=10, compute_importances=True)
clf.fit(X, y)
importances = clf.feature_importances_
n_important = sum(importances > 0.1)
assert_equal(importances.shape[0], 10)
assert_equal(n_important, 3)
X_new = clf.transform(X, threshold="mean")
assert_less(0 < X_new.shape[1], X.shape[1])
clf = RandomForestClassifier(n_estimators=10)
clf.fit(X, y)
assert_true(clf.feature_importances_ is None)
def test_oob_score_classification():
"""Check that oob prediction is as acurate as
usual prediction on the training set.
Not really a good test that prediction is independent."""
clf = RandomForestClassifier(oob_score=True, random_state=rng)
clf.fit(X, y)
training_score = clf.score(X, y)
assert_almost_equal(training_score, clf.oob_score_)
def test_oob_score_regression():
"""Check that oob prediction is pessimistic estimate.
Not really a good test that prediction is independent."""
clf = RandomForestRegressor(n_estimators=50, oob_score=True,
random_state=rng)
n_samples = boston.data.shape[0]
clf.fit(boston.data[:n_samples / 2, :], boston.target[:n_samples / 2])
test_score = clf.score(boston.data[n_samples / 2:, :],
boston.target[n_samples / 2:])
assert_greater(test_score, clf.oob_score_)
assert_greater(clf.oob_score_, .8)
def test_gridsearch():
"""Check that base trees can be grid-searched."""
# Random forest
forest = RandomForestClassifier()
parameters = {'n_estimators': (1, 2),
'max_depth': (1, 2)}
clf = GridSearchCV(forest, parameters)
clf.fit(iris.data, iris.target)
# Extra-trees
forest = ExtraTreesClassifier()
parameters = {'n_estimators': (1, 2),
'max_depth': (1, 2)}
clf = GridSearchCV(forest, parameters)
clf.fit(iris.data, iris.target)
def test_parallel():
"""Check parallel computations."""
# Classification
forest = RandomForestClassifier(n_estimators=10, n_jobs=3, random_state=0)
forest.fit(iris.data, iris.target)
assert_true(10 == len(forest))
forest.set_params(n_jobs=1)
y1 = forest.predict(iris.data)
forest.set_params(n_jobs=2)
y2 = forest.predict(iris.data)
assert_array_equal(y1, y2)
# Regression
forest = RandomForestRegressor(n_estimators=10, n_jobs=3, random_state=0)
forest.fit(boston.data, boston.target)
assert_true(10 == len(forest))
forest.set_params(n_jobs=1)
y1 = forest.predict(boston.data)
forest.set_params(n_jobs=2)
y2 = forest.predict(boston.data)
assert_array_almost_equal(y1, y2, 3)
# Use all cores on the classification dataset
forest = RandomForestClassifier(n_jobs=-1)
forest.fit(iris.data, iris.target)
def test_pickle():
"""Check pickability."""
import pickle
# Random forest
obj = RandomForestClassifier()
obj.fit(iris.data, iris.target)
score = obj.score(iris.data, iris.target)
s = pickle.dumps(obj)
obj2 = pickle.loads(s)
assert_equal(type(obj2), obj.__class__)
score2 = obj2.score(iris.data, iris.target)
assert_true(score == score2)
obj = RandomForestRegressor()
obj.fit(boston.data, boston.target)
score = obj.score(boston.data, boston.target)
s = pickle.dumps(obj)
obj2 = pickle.loads(s)
assert_equal(type(obj2), obj.__class__)
score2 = obj2.score(boston.data, boston.target)
assert_true(score == score2)
# Extra-trees
obj = ExtraTreesClassifier()
obj.fit(iris.data, iris.target)
score = obj.score(iris.data, iris.target)
s = pickle.dumps(obj)
obj2 = pickle.loads(s)
assert_equal(type(obj2), obj.__class__)
score2 = obj2.score(iris.data, iris.target)
assert_true(score == score2)
obj = ExtraTreesRegressor()
obj.fit(boston.data, boston.target)
score = obj.score(boston.data, boston.target)
s = pickle.dumps(obj)
obj2 = pickle.loads(s)
assert_equal(type(obj2), obj.__class__)
score2 = obj2.score(boston.data, boston.target)
assert_true(score == score2)
if __name__ == "__main__":
import nose
nose.runmodule()
|
