/usr/lib/python3/dist-packages/sklearn/ensemble/tests/test_voting_classifier.py is in python3-sklearn 0.17.0-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | """Testing for the boost module (sklearn.ensemble.boost)."""
import numpy as np
from sklearn.utils.testing import assert_almost_equal
from sklearn.utils.testing import assert_equal
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import VotingClassifier
from sklearn.grid_search import GridSearchCV
from sklearn import datasets
from sklearn import cross_validation
from sklearn.datasets import make_multilabel_classification
from sklearn.svm import SVC
from sklearn.multiclass import OneVsRestClassifier
# Load the iris dataset and randomly permute it
iris = datasets.load_iris()
X, y = iris.data[:, 1:3], iris.target
def test_majority_label_iris():
"""Check classification by majority label on dataset iris."""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = GaussianNB()
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='hard')
scores = cross_validation.cross_val_score(eclf,
X,
y,
cv=5,
scoring='accuracy')
assert_almost_equal(scores.mean(), 0.95, decimal=2)
def test_tie_situation():
"""Check voting classifier selects smaller class label in tie situation."""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
eclf = VotingClassifier(estimators=[('lr', clf1), ('rf', clf2)],
voting='hard')
assert_equal(clf1.fit(X, y).predict(X)[73], 2)
assert_equal(clf2.fit(X, y).predict(X)[73], 1)
assert_equal(eclf.fit(X, y).predict(X)[73], 1)
def test_weights_iris():
"""Check classification by average probabilities on dataset iris."""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = GaussianNB()
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
weights=[1, 2, 10])
scores = cross_validation.cross_val_score(eclf,
X,
y,
cv=5,
scoring='accuracy')
assert_almost_equal(scores.mean(), 0.93, decimal=2)
def test_predict_on_toy_problem():
"""Manually check predicted class labels for toy dataset."""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = GaussianNB()
X = np.array([[-1.1, -1.5],
[-1.2, -1.4],
[-3.4, -2.2],
[1.1, 1.2],
[2.1, 1.4],
[3.1, 2.3]])
y = np.array([1, 1, 1, 2, 2, 2])
assert_equal(all(clf1.fit(X, y).predict(X)), all([1, 1, 1, 2, 2, 2]))
assert_equal(all(clf2.fit(X, y).predict(X)), all([1, 1, 1, 2, 2, 2]))
assert_equal(all(clf3.fit(X, y).predict(X)), all([1, 1, 1, 2, 2, 2]))
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='hard',
weights=[1, 1, 1])
assert_equal(all(eclf.fit(X, y).predict(X)), all([1, 1, 1, 2, 2, 2]))
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
weights=[1, 1, 1])
assert_equal(all(eclf.fit(X, y).predict(X)), all([1, 1, 1, 2, 2, 2]))
def test_predict_proba_on_toy_problem():
"""Calculate predicted probabilities on toy dataset."""
clf1 = LogisticRegression(random_state=123)
clf2 = RandomForestClassifier(random_state=123)
clf3 = GaussianNB()
X = np.array([[-1.1, -1.5], [-1.2, -1.4], [-3.4, -2.2], [1.1, 1.2]])
y = np.array([1, 1, 2, 2])
clf1_res = np.array([[0.59790391, 0.40209609],
[0.57622162, 0.42377838],
[0.50728456, 0.49271544],
[0.40241774, 0.59758226]])
clf2_res = np.array([[0.8, 0.2],
[0.8, 0.2],
[0.2, 0.8],
[0.3, 0.7]])
clf3_res = np.array([[0.9985082, 0.0014918],
[0.99845843, 0.00154157],
[0., 1.],
[0., 1.]])
t00 = (2*clf1_res[0][0] + clf2_res[0][0] + clf3_res[0][0]) / 4
t11 = (2*clf1_res[1][1] + clf2_res[1][1] + clf3_res[1][1]) / 4
t21 = (2*clf1_res[2][1] + clf2_res[2][1] + clf3_res[2][1]) / 4
t31 = (2*clf1_res[3][1] + clf2_res[3][1] + clf3_res[3][1]) / 4
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft',
weights=[2, 1, 1])
eclf_res = eclf.fit(X, y).predict_proba(X)
assert_almost_equal(t00, eclf_res[0][0], decimal=1)
assert_almost_equal(t11, eclf_res[1][1], decimal=1)
assert_almost_equal(t21, eclf_res[2][1], decimal=1)
assert_almost_equal(t31, eclf_res[3][1], decimal=1)
try:
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='hard')
eclf.fit(X, y).predict_proba(X)
except AttributeError:
pass
else:
raise AssertionError('AttributeError for voting == "hard"'
' and with predict_proba not raised')
def test_multilabel():
"""Check if error is raised for multilabel classification."""
X, y = make_multilabel_classification(n_classes=2, n_labels=1,
allow_unlabeled=False,
random_state=123)
clf = OneVsRestClassifier(SVC(kernel='linear'))
eclf = VotingClassifier(estimators=[('ovr', clf)], voting='hard')
try:
eclf.fit(X, y)
except NotImplementedError:
return
def test_gridsearch():
"""Check GridSearch support."""
clf1 = LogisticRegression(random_state=1)
clf2 = RandomForestClassifier(random_state=1)
clf3 = GaussianNB()
eclf = VotingClassifier(estimators=[
('lr', clf1), ('rf', clf2), ('gnb', clf3)],
voting='soft')
params = {'lr__C': [1.0, 100.0],
'voting': ['soft', 'hard'],
'weights': [[0.5, 0.5, 0.5], [1.0, 0.5, 0.5]]}
grid = GridSearchCV(estimator=eclf, param_grid=params, cv=5)
grid.fit(iris.data, iris.target)
|