这是您需要的代码

我已经修改了顶部喜欢的代码缩进在一个jupyter笔记本python 3正确

import numpy as np
from sklearn.tree import _tree

def tree_to_code(tree, feature_names):
    tree_ = tree.tree_
    feature_name = [feature_names[i] 
                    if i != _tree.TREE_UNDEFINED else "undefined!" 
                    for i in tree_.feature]
    print("def tree({}):".format(", ".join(feature_names)))

    def recurse(node, depth):
        indent = "    " * depth
        if tree_.feature[node] != _tree.TREE_UNDEFINED:
            name = feature_name[node]
            threshold = tree_.threshold[node]
            print("{}if {} <= {}:".format(indent, name, threshold))
            recurse(tree_.children_left[node], depth + 1)
            print("{}else:  # if {} > {}".format(indent, name, threshold))
            recurse(tree_.children_right[node], depth + 1)
        else:
            print("{}return {}".format(indent, np.argmax(tree_.value[node])))

    recurse(0, 1)

下面的代码是我在anaconda python 2.7下的方法，加上一个包名“pydot-ng”，以制作具有决策规则的PDF文件。希望对大家有所帮助。

from sklearn import tree

clf = tree.DecisionTreeClassifier(max_leaf_nodes=n)
clf_ = clf.fit(X, data_y)

feature_names = X.columns
class_name = clf_.classes_.astype(int).astype(str)

def output_pdf(clf_, name):
    from sklearn import tree
    from sklearn.externals.six import StringIO
    import pydot_ng as pydot
    dot_data = StringIO()
    tree.export_graphviz(clf_, out_file=dot_data,
                         feature_names=feature_names,
                         class_names=class_name,
                         filled=True, rounded=True,
                         special_characters=True,
                          node_ids=1,)
    graph = pydot.graph_from_dot_data(dot_data.getvalue())
    graph.write_pdf("%s.pdf"%name)

output_pdf(clf_, name='filename%s'%n)

这是一个树形图

我修改了Zelazny7提交的代码来打印一些伪代码:

def get_code(tree, feature_names):
        left      = tree.tree_.children_left
        right     = tree.tree_.children_right
        threshold = tree.tree_.threshold
        features  = [feature_names[i] for i in tree.tree_.feature]
        value = tree.tree_.value

        def recurse(left, right, threshold, features, node):
                if (threshold[node] != -2):
                        print "if ( " + features[node] + " <= " + str(threshold[node]) + " ) {"
                        if left[node] != -1:
                                recurse (left, right, threshold, features,left[node])
                        print "} else {"
                        if right[node] != -1:
                                recurse (left, right, threshold, features,right[node])
                        print "}"
                else:
                        print "return " + str(value[node])

        recurse(left, right, threshold, features, 0)

如果你在同一个例子中调用get_code(dt, df.columns)，你会得到:

if ( col1 <= 0.5 ) {
return [[ 1.  0.]]
} else {
if ( col2 <= 4.5 ) {
return [[ 0.  1.]]
} else {
if ( col1 <= 2.5 ) {
return [[ 1.  0.]]
} else {
return [[ 0.  1.]]
}
}
}

只需使用sklearn中的函数。像这样的树

from sklearn.tree import export_graphviz
    export_graphviz(tree,
                out_file = "tree.dot",
                feature_names = tree.columns) //or just ["petal length", "petal width"]

然后在项目文件夹中查找文件树。点，复制所有的内容，并粘贴到这里http://www.webgraphviz.com/，并生成您的图形:)

Scikit learn在0.21版(2019年5月)中引入了一个名为export_text的有趣的新方法，用于从树中提取规则。这里的文档。不再需要创建自定义函数。

一旦你适应了你的模型，你只需要两行代码。首先，导入export_text:

from sklearn.tree import export_text

其次，创建一个包含规则的对象。为了使规则看起来更具可读性，使用feature_names参数并传递一个特性名称列表。例如，如果你的模型是model，你的特征是在一个名为X_train的数据框架中命名的，你可以创建一个名为tree_rules的对象:

tree_rules = export_text(model, feature_names=list(X_train.columns))

然后打印或保存tree_rules。输出如下所示:

|--- Age <= 0.63
|   |--- EstimatedSalary <= 0.61
|   |   |--- Age <= -0.16
|   |   |   |--- class: 0
|   |   |--- Age >  -0.16
|   |   |   |--- EstimatedSalary <= -0.06
|   |   |   |   |--- class: 0
|   |   |   |--- EstimatedSalary >  -0.06
|   |   |   |   |--- EstimatedSalary <= 0.40
|   |   |   |   |   |--- EstimatedSalary <= 0.03
|   |   |   |   |   |   |--- class: 1

下面是一个通过转换export_text的输出从决策树生成Python代码的函数:

import string
from sklearn.tree import export_text

def export_py_code(tree, feature_names, max_depth=100, spacing=4):
    if spacing < 2:
        raise ValueError('spacing must be > 1')

    # Clean up feature names (for correctness)
    nums = string.digits
    alnums = string.ascii_letters + nums
    clean = lambda s: ''.join(c if c in alnums else '_' for c in s)
    features = [clean(x) for x in feature_names]
    features = ['_'+x if x[0] in nums else x for x in features if x]
    if len(set(features)) != len(feature_names):
        raise ValueError('invalid feature names')

    # First: export tree to text
    res = export_text(tree, feature_names=features, 
                        max_depth=max_depth,
                        decimals=6,
                        spacing=spacing-1)

    # Second: generate Python code from the text
    skip, dash = ' '*spacing, '-'*(spacing-1)
    code = 'def decision_tree({}):\n'.format(', '.join(features))
    for line in repr(tree).split('\n'):
        code += skip + "# " + line + '\n'
    for line in res.split('\n'):
        line = line.rstrip().replace('|',' ')
        if '<' in line or '>' in line:
            line, val = line.rsplit(maxsplit=1)
            line = line.replace(' ' + dash, 'if')
            line = '{} {:g}:'.format(line, float(val))
        else:
            line = line.replace(' {} class:'.format(dash), 'return')
        code += skip + line + '\n'

    return code

示例用法:

res = export_py_code(tree, feature_names=names, spacing=4)
print (res)

样例输出:

def decision_tree(f1, f2, f3):
    # DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=3,
    #                        max_features=None, max_leaf_nodes=None,
    #                        min_impurity_decrease=0.0, min_impurity_split=None,
    #                        min_samples_leaf=1, min_samples_split=2,
    #                        min_weight_fraction_leaf=0.0, presort=False,
    #                        random_state=42, splitter='best')
    if f1 <= 12.5:
        if f2 <= 17.5:
            if f1 <= 10.5:
                return 2
            if f1 > 10.5:
                return 3
        if f2 > 17.5:
            if f2 <= 22.5:
                return 1
            if f2 > 22.5:
                return 1
    if f1 > 12.5:
        if f1 <= 17.5:
            if f3 <= 23.5:
                return 2
            if f3 > 23.5:
                return 3
        if f1 > 17.5:
            if f1 <= 25:
                return 1
            if f1 > 25:
                return 2

上面的示例生成了names = ['f'+str(j+1) for j in range(NUM_FEATURES)]。

一个方便的功能是，它可以生成更小的文件大小与减少间距。只需要设置spacing=2。