1 from io import StringIO
2 from sklearn.datasets import load_iris
3 from sklearn.tree import DecisionTreeClassifier
4 from sklearn import tree
5 import pydot
7 for criterion in ['gini', 'entropy']:
8 clf = DecisionTreeClassifier(criterion=criterion, random_state=0, max_depth=3)
9 iris = load_iris()
11 dot_data = StringIO()
13 clf.fit(iris.data, iris.target)
14 print(clf.feature_importances_)
15 tree.export_graphviz(clf, out_file=dot_data)
16 graph = pydot.graph_from_dot_data(dot_data.getvalue())
17 graph[0].write_png('iris_%s.png' % criterion)
19 # [ 0. 0. 0.05393633 0.94606367] gini
20 # [ 0. 0. 0.07060267 0.92939733] entropy
entropy
计算 importance，比较和模型生成权重的一致性
import numpy as np
def split_gain(gini, n, gini1, n1, gini2, n2, t):
return (n*gini - n1*gini1 - n2*gini2)*1.0/t
# gini
x3_gain = \
split_gain(0.6667, 150, 0, 50, 0.5, 100, 150) + \
split_gain(0.5, 100, 0.168, 54, 0.0425, 46, 150)
x2_gain = \
split_gain(0.168, 54, 0.0408, 48, 0.4444, 6, 150) + \
split_gain(0.0425, 46, 0.4444, 3, 0, 43, 150)
x = np.array([x2_gain, x3_gain])
x = x / np.sum(x)
print('gini:', x)
# [ 0.05389858 0.94610142] computed
# [ 0.05393633 0.94606367] sklearn
x3_gain = \
split_gain(1.585, 150, 0, 50, 1, 100, 150) + \
split_gain(1, 100, 0.4451, 54, 0.1511, 46, 150)
x2_gain = \
split_gain(0.4451, 54, 0.1461, 48, 0.9183, 6, 150) + \
split_gain(0.1511, 46, 0.9183, 3, 0, 43, 150)
x = np.array([x2_gain, x3_gain])
x = x / np.sum(x)
print('entropy:', x)
# [ 0.07060873 0.92939127] computed
# [ 0.07060267 0.92939733] sklearn
计算特征 对不存度减少的贡献，同时考虑 节点的样本量
对于某节点计算（**criterion可为gini或entropy**）
父节点 有样本量$n_0$，criterion为${c}_0$
子节点1有样本量$n_1$，criterion为${c}_1$
子节点2有样本量$n_2$，criterion为${c}_2$
总样本个数为$T$
$gain = \left(n_0*{c}_0 -n_1*{c}_1-n_2*{c}_2 \right)/T$
