决策树python sklearn 示例

本文主要是使用python sklearn，完成决策树的demo,以及可视化，最终生成的决策树结果。

from sklearn.datasets import load_iris
from sklearn import tree
from sklearn.tree import export_graphviz
import subprocess


def visualize_tree(tree, feature_name, dot_file):
    """Create tree png using graphviz.
    tree -- scikit-learn DecsisionTree.
    feature_names -- list of feature names.
    dot_file -- dot file name and path
    """
    with open("tree.dot", 'w') as f:
        export_graphviz(tree, out_file=f,
                        feature_names=feature_name)

    dt_png = "dt.png"
    command = ["dot", "-Tpng", dot_file, "-o", dt_png]
    try:
        subprocess.check_call(command)
    except Exception as e:
        print e
        exit("Could not run dot, ie graphviz, to "
             "produce visualization")


def iris_demo():
    clf = tree.DecisionTreeClassifier()
    iris = load_iris()
    # iris.data属性150*4,iris.target 类别归一化为了0,1,2(150*1)
    clf = clf.fit(iris.data, iris.target)
    dot_file = 'tree.dot'
    tree.export_graphviz(clf, out_file=dot_file)
    visualize_tree(clf, iris.feature_names, dot_file)

    # (graph,) = pydot.graph_from_dot_file('tree.dot')
    # graph.write_png('somefile.png')


if __name__ == '__main__':
    iris_demo()
    pass

数据集

---

1. 花的分类的四种属性，150个示例

2. 花的分类，一共三类对应于0,1,2

3. 花的四个属性的描述

最终生成的结果：

pydot的安装见另一篇bolg

http://blog.csdn.net/haluoluo211/article/details/78200078

转载注明出处，并在下面留言！！！

参考

http://chrisstrelioff.ws/sandbox/2015/06/08/decision_trees_in_python_with_scikit_learn_and_pandas.html

http://www.kdnuggets.com/2017/05/simplifying-decision-tree-interpretation-decision-rules-python.html