我相信这个答案比这里的其他答案更正确:

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, tree_.value[node])

    recurse(0, 1)

这将打印出一个有效的Python函数。下面是一个树的输出示例，它试图返回它的输入，一个0到10之间的数字。

def tree(f0):
  if f0 <= 6.0:
    if f0 <= 1.5:
      return [[ 0.]]
    else:  # if f0 > 1.5
      if f0 <= 4.5:
        if f0 <= 3.5:
          return [[ 3.]]
        else:  # if f0 > 3.5
          return [[ 4.]]
      else:  # if f0 > 4.5
        return [[ 5.]]
  else:  # if f0 > 6.0
    if f0 <= 8.5:
      if f0 <= 7.5:
        return [[ 7.]]
      else:  # if f0 > 7.5
        return [[ 8.]]
    else:  # if f0 > 8.5
      return [[ 9.]]

以下是我在其他答案中看到的一些绊脚石:

使用tree_。用阈值== -2来判断节点是否是叶节点不是一个好主意。如果它是一个阈值为-2的真实决策节点呢?相反，你应该看看树。Feature or tree.children_*。 对于tree_中的i，行features = [feature_names[i]。我的sklearn版本崩溃了，因为树。树_。特征为-2(特别是叶节点)。 递归函数中不需要有多个if语句，一个就可以了。

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

我需要一种更人性化的决策树规则格式。我正在构建开源AutoML Python包，很多时候MLJAR用户希望从树中看到确切的规则。

这就是为什么我实现了一个基于paulkernfeld答案的函数。

def get_rules(tree, feature_names, class_names):
    tree_ = tree.tree_
    feature_name = [
        feature_names[i] if i != _tree.TREE_UNDEFINED else "undefined!"
        for i in tree_.feature
    ]

    paths = []
    path = []
    
    def recurse(node, path, paths):
        
        if tree_.feature[node] != _tree.TREE_UNDEFINED:
            name = feature_name[node]
            threshold = tree_.threshold[node]
            p1, p2 = list(path), list(path)
            p1 += [f"({name} <= {np.round(threshold, 3)})"]
            recurse(tree_.children_left[node], p1, paths)
            p2 += [f"({name} > {np.round(threshold, 3)})"]
            recurse(tree_.children_right[node], p2, paths)
        else:
            path += [(tree_.value[node], tree_.n_node_samples[node])]
            paths += [path]
            
    recurse(0, path, paths)

    # sort by samples count
    samples_count = [p[-1][1] for p in paths]
    ii = list(np.argsort(samples_count))
    paths = [paths[i] for i in reversed(ii)]
    
    rules = []
    for path in paths:
        rule = "if "
        
        for p in path[:-1]:
            if rule != "if ":
                rule += " and "
            rule += str(p)
        rule += " then "
        if class_names is None:
            rule += "response: "+str(np.round(path[-1][0][0][0],3))
        else:
            classes = path[-1][0][0]
            l = np.argmax(classes)
            rule += f"class: {class_names[l]} (proba: {np.round(100.0*classes[l]/np.sum(classes),2)}%)"
        rule += f" | based on {path[-1][1]:,} samples"
        rules += [rule]
        
    return rules

规则按照分配给每个规则的训练样本的数量进行排序。对于每条规则，都有关于预测的类名和分类任务预测概率的信息。对于回归任务，只打印关于预测值的信息。

例子

from sklearn import datasets
from sklearn.tree import DecisionTreeRegressor
from sklearn import tree

# Prepare the data data
boston = datasets.load_boston()
X = boston.data
y = boston.target

# Fit the regressor, set max_depth = 3
regr = DecisionTreeRegressor(max_depth=3, random_state=1234)
model = regr.fit(X, y)

# Print rules
rules = get_rules(regr, boston.feature_names, None)
for r in rules:
    print(r)

印刷规则:

if (RM <= 6.941) and (LSTAT <= 14.4) and (DIS > 1.385) then response: 22.905 | based on 250 samples
if (RM <= 6.941) and (LSTAT > 14.4) and (CRIM <= 6.992) then response: 17.138 | based on 101 samples
if (RM <= 6.941) and (LSTAT > 14.4) and (CRIM > 6.992) then response: 11.978 | based on 74 samples
if (RM > 6.941) and (RM <= 7.437) and (NOX <= 0.659) then response: 33.349 | based on 43 samples
if (RM > 6.941) and (RM > 7.437) and (PTRATIO <= 19.65) then response: 45.897 | based on 29 samples
if (RM <= 6.941) and (LSTAT <= 14.4) and (DIS <= 1.385) then response: 45.58 | based on 5 samples
if (RM > 6.941) and (RM <= 7.437) and (NOX > 0.659) then response: 14.4 | based on 3 samples
if (RM > 6.941) and (RM > 7.437) and (PTRATIO > 19.65) then response: 21.9 | based on 1 samples

我在我的文章中总结了从决策树中提取规则的方法:用Scikit-Learn和Python以3种方式从决策树中提取规则。

这是基于@paulkernfeld的回答。如果你有一个包含特征的数据框架X和一个包含共振的目标数据框架y，你想知道哪个y值结束于哪个节点(并相应地绘制它)，你可以做以下工作:

    def tree_to_code(tree, feature_names):
        from sklearn.tree import _tree
        codelines = []
        codelines.append('def get_cat(X_tmp):\n')
        codelines.append('   catout = []\n')
        codelines.append('   for codelines in range(0,X_tmp.shape[0]):\n')
        codelines.append('      Xin = X_tmp.iloc[codelines]\n')
        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]
                codelines.append ('{}if Xin["{}"] <= {}:\n'.format(indent, name, threshold))
                recurse(tree_.children_left[node], depth + 1)
                codelines.append( '{}else:  # if Xin["{}"] > {}\n'.format(indent, name, threshold))
                recurse(tree_.children_right[node], depth + 1)
            else:
                codelines.append( '{}mycat = {}\n'.format(indent, node))

        recurse(0, 1)
        codelines.append('      catout.append(mycat)\n')
        codelines.append('   return pd.DataFrame(catout,index=X_tmp.index,columns=["category"])\n')
        codelines.append('node_ids = get_cat(X)\n')
        return codelines
    mycode = tree_to_code(clf,X.columns.values)

    # now execute the function and obtain the dataframe with all nodes
    exec(''.join(mycode))
    node_ids = [int(x[0]) for x in node_ids.values]
    node_ids2 = pd.DataFrame(node_ids)

    print('make plot')
    import matplotlib.cm as cm
    colors = cm.rainbow(np.linspace(0, 1, 1+max( list(set(node_ids)))))
    #plt.figure(figsize=cm2inch(24, 21))
    for i in list(set(node_ids)):
        plt.plot(y[node_ids2.values==i],'o',color=colors[i], label=str(i))  
    mytitle = ['y colored by node']
    plt.title(mytitle ,fontsize=14)
    plt.xlabel('my xlabel')
    plt.ylabel(tagname)
    plt.xticks(rotation=70)       
    plt.legend(loc='upper center', bbox_to_anchor=(0.5, 1.00), shadow=True, ncol=9)
    plt.tight_layout()
    plt.show()
    plt.close 

不是最优雅的版本，但它做到了…

显然，很久以前就有人决定尝试将以下函数添加到官方scikit的树导出函数中(基本上只支持export_graphviz)

def export_dict(tree, feature_names=None, max_depth=None) :
    """Export a decision tree in dict format.

以下是他的全部承诺:

https://github.com/scikit-learn/scikit-learn/blob/79bdc8f711d0af225ed6be9fdb708cea9f98a910/sklearn/tree/export.py

不太确定这条评论发生了什么。但是你也可以尝试使用这个函数。

我认为这为scikit-learn的优秀人员提供了一个严肃的文档需求，以正确地记录sklearn.tree.Tree API，这是一个底层的树结构，DecisionTreeClassifier将其作为属性tree_公开。

我创建了自己的函数，从sklearn创建的决策树中提取规则:

import pandas as pd
import numpy as np
from sklearn.tree import DecisionTreeClassifier

# dummy data:
df = pd.DataFrame({'col1':[0,1,2,3],'col2':[3,4,5,6],'dv':[0,1,0,1]})

# create decision tree
dt = DecisionTreeClassifier(max_depth=5, min_samples_leaf=1)
dt.fit(df.ix[:,:2], df.dv)

这个函数首先从节点(在子数组中由-1标识)开始，然后递归地查找父节点。我称之为节点的“沿袭”。在此过程中，我获取了我需要创建if/then/else SAS逻辑的值:

def get_lineage(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]

     # get ids of child nodes
     idx = np.argwhere(left == -1)[:,0]     

     def recurse(left, right, child, lineage=None):          
          if lineage is None:
               lineage = [child]
          if child in left:
               parent = np.where(left == child)[0].item()
               split = 'l'
          else:
               parent = np.where(right == child)[0].item()
               split = 'r'

          lineage.append((parent, split, threshold[parent], features[parent]))

          if parent == 0:
               lineage.reverse()
               return lineage
          else:
               return recurse(left, right, parent, lineage)

     for child in idx:
          for node in recurse(left, right, child):
               print node

下面的元组集包含了创建SAS if/then/else语句所需的所有内容。我不喜欢在SAS中使用do块，这就是为什么我创建逻辑来描述节点的整个路径。元组后的单个整数为路径中终端节点的ID。所有前面的元组组合起来创建该节点。

In [1]: get_lineage(dt, df.columns)
(0, 'l', 0.5, 'col1')
1
(0, 'r', 0.5, 'col1')
(2, 'l', 4.5, 'col2')
3
(0, 'r', 0.5, 'col1')
(2, 'r', 4.5, 'col2')
(4, 'l', 2.5, 'col1')
5
(0, 'r', 0.5, 'col1')
(2, 'r', 4.5, 'col2')
(4, 'r', 2.5, 'col1')
6