Multiclass and multilabel
OvR （One-Vs-The-Rest）
基于iris数据集的多分类问题
1
2
3
4
5
6
>>> from sklearn import datasets
>>> from sklearn.multiclass import OneVsRestClassifier
>>> iris = datasets.load_iris()
>>> X, y = iris.data, iris.target
>>> from sklearn.svm import LinearSVC
>>> OneVsRestClassifier(LinearSVC(random_state=0)).fit(X, y).predict(X)
OvO （One-Versus-One）
1
2
3
4
5
6
>>> from sklearn import datasets
>>> from sklearn.multiclass import OneVsOneClassifier
>>> from sklearn.svm import LinearSVC
>>> iris = datasets.load_iris()
>>> X, y = iris.data, iris.target
>>> OneVsOneClassifier(LinearSVC(random_state=0)).fit(X, y).predict(X)
分类结果
1
2
3
4
5
6
7
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])
其中iris属性数据iris.data 也就X。
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
>>> X
array([[ 5.1, 3.5, 1.4, 0.2],
[ 4.9, 3. , 1.4, 0.2],
[ 4.7, 3.2, 1.3, 0.2],
[ 4.6, 3.1, 1.5, 0.2],
[ 5. , 3.6, 1.4, 0.2],
[ 5.4, 3.9, 1.7, 0.4],
[ 4.6, 3.4, 1.4, 0.3],
[ 5. , 3.4, 1.5, 0.2],
[ 4.4, 2.9, 1.4, 0.2],
[ 4.9, 3.1, 1.5, 0.1],
[ 5.4, 3.7, 1.5, 0.2],
[ 4.8, 3.4, 1.6, 0.2],
[ 4.8, 3. , 1.4, 0.1],
[ 4.3, 3. , 1.1, 0.1],
[ 5.8, 4. , 1.2, 0.2],
[ 5.7, 4.4, 1.5, 0.4],
[ 5.4, 3.9, 1.3, 0.4],
[ 5.1, 3.5, 1.4, 0.3],
[ 5.7, 3.8, 1.7, 0.3],
[ 5.1, 3.8, 1.5, 0.3],
[ 5.4, 3.4, 1.7, 0.2],
[ 5.1, 3.7, 1.5, 0.4],
[ 4.6, 3.6, 1. , 0.2],
[ 5.1, 3.3, 1.7, 0.5],
[ 4.8, 3.4, 1.9, 0.2],
[ 5. , 3. , 1.6, 0.2],
[ 5. , 3.4, 1.6, 0.4],
[ 5.2, 3.5, 1.5, 0.2],
[ 5.2, 3.4, 1.4, 0.2],
[ 4.7, 3.2, 1.6, 0.2],
[ 4.8, 3.1, 1.6, 0.2],
[ 5.4, 3.4, 1.5, 0.4],
[ 5.2, 4.1, 1.5, 0.1],
[ 5.5, 4.2, 1.4, 0.2],
[ 4.9, 3.1, 1.5, 0.1],
[ 5. , 3.2, 1.2, 0.2],
[ 5.5, 3.5, 1.3, 0.2],
[ 4.9, 3.1, 1.5, 0.1],
[ 4.4, 3. , 1.3, 0.2],
[ 5.1, 3.4, 1.5, 0.2],
[ 5. , 3.5, 1.3, 0.3],
[ 4.5, 2.3, 1.3, 0.3],
[ 4.4, 3.2, 1.3, 0.2],
[ 5. , 3.5, 1.6, 0.6],
[ 5.1, 3.8, 1.9, 0.4],
[ 4.8, 3. , 1.4, 0.3],
[ 5.1, 3.8, 1.6, 0.2],
[ 4.6, 3.2, 1.4, 0.2],
[ 5.3, 3.7, 1.5, 0.2],
[ 5. , 3.3, 1.4, 0.2],
[ 7. , 3.2, 4.7, 1.4],
[ 6.4, 3.2, 4.5, 1.5],
[ 6.9, 3.1, 4.9, 1.5],
[ 5.5, 2.3, 4. , 1.3],
[ 6.5, 2.8, 4.6, 1.5],
[ 5.7, 2.8, 4.5, 1.3],
[ 6.3, 3.3, 4.7, 1.6],
[ 4.9, 2.4, 3.3, 1. ],
[ 6.6, 2.9, 4.6, 1.3],
[ 5.2, 2.7, 3.9, 1.4],
[ 5. , 2. , 3.5, 1. ],
[ 5.9, 3. , 4.2, 1.5],
[ 6. , 2.2, 4. , 1. ],
[ 6.1, 2.9, 4.7, 1.4],
[ 5.6, 2.9, 3.6, 1.3],
[ 6.7, 3.1, 4.4, 1.4],
[ 5.6, 3. , 4.5, 1.5],
[ 5.8, 2.7, 4.1, 1. ],
[ 6.2, 2.2, 4.5, 1.5],
[ 5.6, 2.5, 3.9, 1.1],
[ 5.9, 3.2, 4.8, 1.8],
[ 6.1, 2.8, 4. , 1.3],
[ 6.3, 2.5, 4.9, 1.5],
[ 6.1, 2.8, 4.7, 1.2],
[ 6.4, 2.9, 4.3, 1.3],
[ 6.6, 3. , 4.4, 1.4],
[ 6.8, 2.8, 4.8, 1.4],
[ 6.7, 3. , 5. , 1.7],
[ 6. , 2.9, 4.5, 1.5],
[ 5.7, 2.6, 3.5, 1. ],
[ 5.5, 2.4, 3.8, 1.1],
[ 5.5, 2.4, 3.7, 1. ],
[ 5.8, 2.7, 3.9, 1.2],
[ 6. , 2.7, 5.1, 1.6],
[ 5.4, 3. , 4.5, 1.5],
[ 6. , 3.4, 4.5, 1.6],
[ 6.7, 3.1, 4.7, 1.5],
[ 6.3, 2.3, 4.4, 1.3],
[ 5.6, 3. , 4.1, 1.3],
[ 5.5, 2.5, 4. , 1.3],
[ 5.5, 2.6, 4.4, 1.2],
[ 6.1, 3. , 4.6, 1.4],
[ 5.8, 2.6, 4. , 1.2],
[ 5. , 2.3, 3.3, 1. ],
[ 5.6, 2.7, 4.2, 1.3],
[ 5.7, 3. , 4.2, 1.2],
[ 5.7, 2.9, 4.2, 1.3],
[ 6.2, 2.9, 4.3, 1.3],
[ 5.1, 2.5, 3. , 1.1],
[ 5.7, 2.8, 4.1, 1.3],
[ 6.3, 3.3, 6. , 2.5],
[ 5.8, 2.7, 5.1, 1.9],
[ 7.1, 3. , 5.9, 2.1],
[ 6.3, 2.9, 5.6, 1.8],
[ 6.5, 3. , 5.8, 2.2],
[ 7.6, 3. , 6.6, 2.1],
[ 4.9, 2.5, 4.5, 1.7],
[ 7.3, 2.9, 6.3, 1.8],
[ 6.7, 2.5, 5.8, 1.8],
[ 7.2, 3.6, 6.1, 2.5],
[ 6.5, 3.2, 5.1, 2. ],
[ 6.4, 2.7, 5.3, 1.9],
[ 6.8, 3. , 5.5, 2.1],
[ 5.7, 2.5, 5. , 2. ],
[ 5.8, 2.8, 5.1, 2.4],
[ 6.4, 3.2, 5.3, 2.3],
[ 6.5, 3. , 5.5, 1.8],
[ 7.7, 3.8, 6.7, 2.2],
[ 7.7, 2.6, 6.9, 2.3],
[ 6. , 2.2, 5. , 1.5],
[ 6.9, 3.2, 5.7, 2.3],
[ 5.6, 2.8, 4.9, 2. ],
[ 7.7, 2.8, 6.7, 2. ],
[ 6.3, 2.7, 4.9, 1.8],
[ 6.7, 3.3, 5.7, 2.1],
[ 7.2, 3.2, 6. , 1.8],
[ 6.2, 2.8, 4.8, 1.8],
[ 6.1, 3. , 4.9, 1.8],
[ 6.4, 2.8, 5.6, 2.1],
[ 7.2, 3.2, 6. , 1.8],
[ 6.2, 2.8, 4.8, 1.8],
[ 6.1, 3. , 4.9, 1.8],
[ 6.4, 2.8, 5.6, 2.1],
[ 7.2, 3. , 5.8, 1.6],
[ 7.4, 2.8, 6.1, 1.9],
[ 7.9, 3.8, 6.4, 2. ],
[ 6.4, 2.8, 5.6, 2.2],
[ 6.3, 2.8, 5.1, 1.5],
[ 6.1, 2.6, 5.6, 1.4],
[ 7.7, 3. , 6.1, 2.3],
[ 6.3, 3.4, 5.6, 2.4],
[ 6.4, 3.1, 5.5, 1.8],
[ 6. , 3. , 4.8, 1.8],
[ 6.9, 3.1, 5.4, 2.1],
[ 6.7, 3.1, 5.6, 2.4],
[ 6.9, 3.1, 5.1, 2.3],
[ 5.8, 2.7, 5.1, 1.9],
[ 6.8, 3.2, 5.9, 2.3],
[ 6.7, 3.3, 5.7, 2.5],
[ 6.7, 3. , 5.2, 2.3],
[ 6.3, 2.5, 5. , 1.9],
[ 6.5, 3. , 5.2, 2. ],
[ 6.2, 3.4, 5.4, 2.3],
[ 5.9, 3. , 5.1, 1.8]])
目标属性，iris.target
1
2
3
4
5
6
7
8
>>> y
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])
Gradient Boosting regression
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
print(__doc__)
# Author: Peter Prettenhofer <peter.prettenhofer@gmail.com>
#
# License: BSD 3 clause
import numpy as np
import matplotlib.pyplot as plt
from sklearn import ensemble
from sklearn import datasets
from sklearn.utils import shuffle
from sklearn.metrics import mean_squared_error
###############################################################################
# Load data
boston = datasets.load_boston()
X, y = shuffle(boston.data, boston.target, random_state=13)
X = X.astype(np.float32)
offset = int(X.shape[0] * 0.9)
X_train, y_train = X[:offset], y[:offset]
X_test, y_test = X[offset:], y[offset:]
###############################################################################
# Fit regression model
params = {'n_estimators': 500, 'max_depth': 4, 'min_samples_split': 1,
'learning_rate': 0.01, 'loss': 'ls'}
clf = ensemble.GradientBoostingRegressor(**params)
clf.fit(X_train, y_train)
mse = mean_squared_error(y_test, clf.predict(X_test))
print("MSE: %.4f" % mse)
###############################################################################
# Plot training deviance
# compute test set deviance
test_score = np.zeros((params['n_estimators'],), dtype=np.float64)
for i, y_pred in enumerate(clf.staged_predict(X_test)):
test_score[i] = clf.loss_(y_test, y_pred)
plt.figure(figsize=(12, 6))
plt.subplot(1, 2, 1)
plt.title('Deviance')
plt.plot(np.arange(params['n_estimators']) + 1, clf.train_score_, 'b-',
label='Training Set Deviance')
plt.plot(np.arange(params['n_estimators']) + 1, test_score, 'r-',
label='Test Set Deviance')
plt.legend(loc='upper right')
plt.xlabel('Boosting Iterations')
plt.ylabel('Deviance')
###############################################################################
# Plot feature importance
feature_importance = clf.feature_importances_
# make importances relative to max importance
feature_importance = 100.0 * (feature_importance / feature_importance.max())
sorted_idx = np.argsort(feature_importance)
pos = np.arange(sorted_idx.shape[0]) + .5
plt.subplot(1, 2, 2)
plt.barh(pos, feature_importance[sorted_idx], align='center')
plt.yticks(pos, boston.feature_names[sorted_idx])
plt.xlabel('Relative Importance')
plt.title('Variable Importance')
plt.show()
结果 