Python 是否可以在 scikit-learn 中打印决策树？

Is it possible to print the decision tree in scikit-learn?

提问by Hyman Twain

Is there a way to print a trained decision tree in scikit-learn? I want to train a decision tree for my thesis and I want to put the picture of the tree in the thesis. Is that possible?

有没有办法在 scikit-learn 中打印训练有素的决策树？我想为我的论文训练一个决策树，我想把树的图片放在论文中。那可能吗？

采纳答案by EdChum

There is a method to export to graph_viz format: http://scikit-learn.org/stable/modules/generated/sklearn.tree.export_graphviz.html

有一种导出为graph_viz格式的方法：http://scikit-learn.org/stable/modules/generated/sklearn.tree.export_graphviz.html

So from the online docs:

所以从在线文档：

>>> from sklearn.datasets import load_iris
>>> from sklearn import tree
>>>
>>> clf = tree.DecisionTreeClassifier()
>>> iris = load_iris()
>>>
>>> clf = clf.fit(iris.data, iris.target)
>>> tree.export_graphviz(clf,
...     out_file='tree.dot')    

Then you can load this using graph viz, or if you have pydot installed then you can do this more directly: http://scikit-learn.org/stable/modules/tree.html

然后您可以使用图形即加载它，或者如果您安装了 pydot，那么您可以更直接地执行此操作：http://scikit-learn.org/stable/modules/tree.html

>>> from sklearn.externals.six import StringIO  
>>> import pydot 
>>> dot_data = StringIO() 
>>> tree.export_graphviz(clf, out_file=dot_data) 
>>> graph = pydot.graph_from_dot_data(dot_data.getvalue()) 
>>> graph.write_pdf("iris.pdf") 

Will produce an svg, can't display it here so you'll have to follow the link: http://scikit-learn.org/stable/_images/iris.svg

将生成一个 svg，无法在此处显示，因此您必须点击链接：http: //scikit-learn.org/stable/_images/iris.svg

Update

更新

It seems that there has been a change in the behaviour since I first answered this question and it now returns a listand hence you get this error:

自从我第一次回答这个问题以来，行为似乎发生了变化，现在它返回 a list，因此您会收到此错误：

AttributeError: 'list' object has no attribute 'write_pdf'

Firstly when you see this it's worth just printing the object and inspecting the object, and most likely what you want is the first object:

首先，当您看到此内容时，只需打印对象并检查对象即可，很可能您想要的是第一个对象：

graph[0].write_pdf("iris.pdf")

Thanks to @NickBraunagel for the comment

感谢@NickBraunagel 的评论

回答by NickBraunagel

Although I'm late to the game, the below comprehensive instructions could be useful for others who want to display decision tree output:

虽然我迟到了，但以下综合说明对于想要显示决策树输出的其他人可能有用：

Install necessary modules:

安装必要的模块：

1. install graphviz. I used conda's install package here(recommended over pip install graphvizas pipinstall doesn't include the actual GraphViz executables)
2. install pydotvia pip (pip install pydot)
3. Add the graphviz folder directory containing the .exe files (e.g. dot.exe) to your environment variable PATH
4. run EdChum's above (NOTE: graphis a listcontaining the pydot.Dotobject):

1. 安装graphviz。我在这里使用了 conda 的安装包 （推荐使用，pip install graphviz因为pip安装不包括实际的 GraphViz可执行文件）
2. pydot通过 pip ( pip install pydot)安装
3. 将包含 .exe 文件（例如 dot.exe）的 graphviz 文件夹目录添加到您的环境变量 PATH
4. 运行上面的 EdChum（注意：graph是一个list包含pydot.Dot对象）：

---

---

from sklearn.datasets import load_iris
from sklearn import tree
from sklearn.externals.six import StringIO  
import pydot 

clf = tree.DecisionTreeClassifier()
iris = load_iris()
clf = clf.fit(iris.data, iris.target)

dot_data = StringIO() 
tree.export_graphviz(clf, out_file=dot_data) 
graph = pydot.graph_from_dot_data(dot_data.getvalue()) 

graph[0].write_pdf("iris.pdf")  # must access graph's first element

Now you'll find the "iris.pdf" within your environment's default directory

现在您将在环境的默认目录中找到“iris.pdf”