我经历了以下问题：
how to extract decision rules of GradientBosstingClassifier
How to extract the decision rules from scikit-learn decision-tree?
但是以上两种方法不能解决我的目的。以下是我的查询：
我需要在Python中使用gradientboostingclassifer建立一个模型，并在SAS平台中实现该模型。为此，我需要从gradientboostingclassifer中提取决策规则。
以下是我到目前为止尝试过的内容：
基于IRIS数据构建模型：
# import the most common dataset
from sklearn.datasets import load_iris
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.tree import export_graphviz
from sklearn.externals.six import StringIO
from IPython.display import Image
X, y = load_iris(return_X_y=True)
# there are 150 observations and 4 features
print(X.shape) # (150, 4)
# let's build a small model = 5 trees with depth no more than 2
model = GradientBoostingClassifier(n_estimators=5, max_depth=3, learning_rate=1.0)
model.fit(X, y==2) # predict 2nd class vs rest, for simplicity
# we can access individual trees
trees = model.estimators_.ravel()
def plot_tree(clf):
dot_data = StringIO()
export_graphviz(clf, out_file=dot_data, node_ids=True,
filled=True, rounded=True,
special_characters=True)
graph = pydotplus.graph_from_dot_data([enter image description here][3]dot_data.getvalue())
return Image(graph.create_png())
# now we can plot the first tree
plot_tree(trees[0])
在绘制图形之后，我已经检查了第一棵树的图形源代码，并使用以下代码将其写入文本文件：
with open("C:\\Users\XXXX\Desktop\Python\input_tree.txt", "w") as wrt:
wrt.write(export_graphviz(trees[0], out_file=None, node_ids=True,
filled=True, rounded=True,
special_characters=True))
下面是输出文件：
digraph Tree {
node [shape=box, style="filled, rounded", color="black", fontname=helvetica] ;
edge [fontname=helvetica] ;
0 [label=<node #0<br/>X<SUB>3</SUB> ≤ 1.75<br/>friedman_mse = 0.222<br/>samples = 150<br/>value = 0.0>, fillcolor="#e5813955"] ;
1 [label=<node #1<br/>X<SUB>2</SUB> ≤ 4.95<br/>friedman_mse = 0.046<br/>samples = 104<br/>value = -0.285>, fillcolor="#e5813945"] ;
0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
2 [label=<node #2<br/>X<SUB>3</SUB> ≤ 1.65<br/>friedman_mse = 0.01<br/>samples = 98<br/>value = -0.323>, fillcolor="#e5813943"] ;
1 -> 2 ;
3 [label=<node #3<br/>friedman_mse = 0.0<br/>samples = 97<br/>value = -1.5>, fillcolor="#e5813900"] ;
2 -> 3 ;
4 [label=<node #4<br/>friedman_mse = -0.0<br/>samples = 1<br/>value = 3.0>, fillcolor="#e58139ff"] ;
2 -> 4 ;
5 [label=<node #5<br/>X<SUB>3</SUB> ≤ 1.55<br/>friedman_mse = 0.222<br/>samples = 6<br/>value = 0.333>, fillcolor="#e5813968"] ;
1 -> 5 ;
6 [label=<node #6<br/>friedman_mse = 0.0<br/>samples = 3<br/>value = 3.0>, fillcolor="#e58139ff"] ;
5 -> 6 ;
7 [label=<node #7<br/>friedman_mse = 0.222<br/>samples = 3<br/>value = 0.0>, fillcolor="#e5813955"] ;
5 -> 7 ;
8 [label=<node #8<br/>X<SUB>2</SUB> ≤ 4.85<br/>friedman_mse = 0.021<br/>samples = 46<br/>value = 0.645>, fillcolor="#e581397a"] ;
0 -> 8 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
9 [label=<node #9<br/>X<SUB>1</SUB> ≤ 3.1<br/>friedman_mse = 0.222<br/>samples = 3<br/>value = 0.333>, fillcolor="#e5813968"] ;
8 -> 9 ;
10 [label=<node #10<br/>friedman_mse = 0.0<br/>samples = 2<br/>value = 3.0>, fillcolor="#e58139ff"] ;
9 -> 10 ;
11 [label=<node #11<br/>friedman_mse = -0.0<br/>samples = 1<br/>value = -1.5>, fillcolor="#e5813900"] ;
9 -> 11 ;
12 [label=<node #12<br/>friedman_mse = -0.0<br/>samples = 43<br/>value = 3.0>, fillcolor="#e58139ff"] ;
8 -> 12 ;
}
要从输出文件中提取决策规则，我尝试了以下python RegEX代码转换为SAS代码：
import re
with open("C:\\Users\XXXX\Desktop\Python\input_tree.txt") as f:
with open("C:\\Users\XXXX\Desktop\Python\output.txt", "w") as f1:
result0 = 'value = 0;'
f1.write(result0)
for line in f:
result1 = re.sub(r'^(\d+)\s+.*<br\/>([A-Z]+)<SUB>(\d+)<\/SUB>\s+(.+?)([-\d.]+)<br\/>friedman_mse.*;$',r"if \2\3 \4 \5 then do;",line)
result2 = re.sub(r'^(\d+).*(?!SUB).*(value\s+=)\s([-\d.]+).*;$',r"\2 value + \3; end;",result1)
result3 = re.sub(r'^(\d+\s+->\s+\d+\s+);$',r'\1',result2)
result4 = re.sub(r'^digraph.+|^node.+|^edge.+','',result3)
result5 = re.sub(r'&(\w{2});',r'\1',result4)
result6 = re.sub(r'}','end;',result5)
f1.write(result6)
下面是上面代码的输出SAS：
value = 0;
if X3 le 1.75 then do;
if X2 le 4.95 then do;
0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
if X3 le 1.65 then do;
1 -> 2
value = value + -1.5; end;
2 -> 3
value = value + 3.0; end;
2 -> 4
if X3 le 1.55 then do;
1 -> 5
value = value + 3.0; end;
5 -> 6
value = value + 0.0; end;
5 -> 7
if X2 le 4.85 then do;
0 -> 8 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
if X1 le 3.1 then do;
8 -> 9
value = value + 3.0; end;
9 -> 10
value = value + -1.5; end;
9 -> 11
value = value + 3.0; end;
8 -> 12
end;
如您所见，输出文件中缺少一块，即我无法正确打开/关闭do-end块。为此，我需要利用节点号，但是由于无法在此处找到任何模式而无法使用。
任何人都可以帮助我进行此查询。
除此之外，像决策树分类器一样，我不能像上面第二条链接中所述提取children_left，children_right，阈值。我已经成功提取了GBM的每棵树
trees = model.estimators_.ravel()
但是我没有找到任何有用的函数来提取每棵树的值和规则。如果可以以类似DecisionTreeclassifier的方式使用grapviz对象，请提供帮助。
OR
以其他任何可以解决我的目的的方法来帮助我。
答案 0 :(得分：1)
无需使用graphviz导出来访问决策树数据。 model.estimators_包含模型组成的所有单个分类器。对于GradientBoostingClassifier，这是一个二维形状的numpy数组（n_estimators，n_classes），每个项目都是DecisionTreeRegressor。
每个决策树都有一个属性_tree，Understanding the decision tree structure显示了如何从该对象中取出节点，阈值和子节点。
import numpy
import pandas
from sklearn.ensemble import GradientBoostingClassifier
est = GradientBoostingClassifier(n_estimators=4)
numpy.random.seed(1)
est.fit(numpy.random.random((100, 3)), numpy.random.choice([0, 1, 2], size=(100,)))
print('s', est.estimators_.shape)
n_classes, n_estimators = est.estimators_.shape
for c in range(n_classes):
for t in range(n_estimators):
dtree = est.estimators_[c, t]
print("class={}, tree={}: {}".format(c, t, dtree.tree_))
rules = pandas.DataFrame({
'child_left': dtree.tree_.children_left,
'child_right': dtree.tree_.children_right,
'feature': dtree.tree_.feature,
'threshold': dtree.tree_.threshold,
})
print(rules)
为每棵树输出如下内容：
class=0, tree=0: <sklearn.tree._tree.Tree object at 0x7f18a697f370>
child_left child_right feature threshold
0 1 2 0 0.020702
1 -1 -1 -2 -2.000000
2 3 6 1 0.879058
3 4 5 1 0.543716
4 -1 -1 -2 -2.000000
5 -1 -1 -2 -2.000000
6 7 8 0 0.292586
7 -1 -1 -2 -2.000000
8 -1 -1 -2 -2.000000