def test_multioutput():
"""Check estimators on multi-output problems."""
X = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [-2, 1],
[-1, 1], [-1, 2], [2, -1], [1, -1], [1, -2]]
y = [[-1, 0], [-1, 0], [-1, 0], [1, 1], [1, 1], [1, 1], [-1, 2], [-1, 2],
[-1, 2], [1, 3], [1, 3], [1, 3]]
T = [[-1, -1], [1, 1], [-1, 1], [1, -1]]
y_true = [[-1, 0], [1, 1], [-1, 2], [1, 3]]
# toy classification problem
clf = ExtraTreesClassifier(random_state=0)
y_hat = clf.fit(X, y).predict(T)
assert_array_equal(y_hat, y_true)
assert_equal(y_hat.shape, (4, 2))
proba = clf.predict_proba(T)
assert_equal(len(proba), 2)
assert_equal(proba[0].shape, (4, 2))
assert_equal(proba[1].shape, (4, 4))
log_proba = clf.predict_log_proba(T)
assert_equal(len(log_proba), 2)
assert_equal(log_proba[0].shape, (4, 2))
assert_equal(log_proba[1].shape, (4, 4))
# toy regression problem
clf = ExtraTreesRegressor(random_state=5)
y_hat = clf.fit(X, y).predict(T)
assert_almost_equal(y_hat, y_true)
assert_equal(y_hat.shape, (4, 2))
def test_multioutput():
"""Check estimators on multi-output problems."""
olderr = np.seterr(divide="ignore")
X = [[-2, -1], [-1, -1], [-1, -2], [1, 1], [1, 2], [2, 1], [-2, 1], [-1, 1], [-1, 2], [2, -1], [1, -1], [1, -2]]
y = [[-1, 0], [-1, 0], [-1, 0], [1, 1], [1, 1], [1, 1], [-1, 2], [-1, 2], [-1, 2], [1, 3], [1, 3], [1, 3]]
T = [[-1, -1], [1, 1], [-1, 1], [1, -1]]
y_true = [[-1, 0], [1, 1], [-1, 2], [1, 3]]
# toy classification problem
clf = ExtraTreesClassifier(random_state=0)
y_hat = clf.fit(X, y).predict(T)
assert_array_equal(y_hat, y_true)
assert_equal(y_hat.shape, (4, 2))
proba = clf.predict_proba(T)
assert_equal(len(proba), 2)
assert_equal(proba[0].shape, (4, 2))
assert_equal(proba[1].shape, (4, 4))
log_proba = clf.predict_log_proba(T)
assert_equal(len(log_proba), 2)
assert_equal(log_proba[0].shape, (4, 2))
assert_equal(log_proba[1].shape, (4, 4))
# toy regression problem
clf = ExtraTreesRegressor(random_state=5)
y_hat = clf.fit(X, y).predict(T)
assert_almost_equal(y_hat, y_true)
assert_equal(y_hat.shape, (4, 2))
np.seterr(**olderr)
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
bootstrap=False,
max_features='auto')
# 模型训练
algo.fit(X_train, Y_train)
# 模型效果评估
print('训练集上的准确率：{}'.format(algo.score(X_train, Y_train)))
print('测试集上的准确率：{}'.format(algo.score(X_test, Y_test)))
# 查看下API属性
X_test = [[6.9, 3.1, 5.1, 2.3], [6.1, 2.8, 4.0, 1.3], [5.2, 3.4, 1.4, 0.2]]
print('样本的预测值：')
print(algo.predict(X_test))
print('样本预测值概率：')
print(algo.predict_log_proba(X_test))
print('样本预测概率值的Log转换：')
print(algo.predict_log_proba(X_test))
# print('训练好的所有子模型：{}'.format(algo.estimators_))
for index, estimators in enumerate(algo.estimators_):
print('第{}个子模型对于数据的预测值为：{}'.format(index + 1, algo.predict(X_test)))
print('各个特征属性的重要性权重列表：\n{}'.format(algo.feature_importances_))
# print('Bagging模型的袋外准确率：\n{}'.format(algo.oob_score_))
# 所有子模型可视化
for index, estimators in enumerate(algo.estimators_):
dot_data = tree.export_graphviz(decision_tree=estimators,
out_file=None,
feature_names=['c1', 'c2', 'c3', 'c4'],
class_names=['A', 'B', 'C'],
