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。

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

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。

现在可以使用export_text了。

from sklearn.tree import export_text

r = export_text(loan_tree, feature_names=(list(X_train.columns)))
print(r)

来自[sklearn][1]的完整示例

from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import export_text
iris = load_iris()
X = iris['data']
y = iris['target']
decision_tree = DecisionTreeClassifier(random_state=0, max_depth=2)
decision_tree = decision_tree.fit(X, y)
r = export_text(decision_tree, feature_names=iris['feature_names'])
print(r)

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:)

您还可以通过区分它属于哪个类，甚至通过提到它的输出值，使它具有更丰富的信息。

def print_decision_tree(tree, feature_names, offset_unit='    '):    
left      = tree.tree_.children_left
right     = tree.tree_.children_right
threshold = tree.tree_.threshold
value = tree.tree_.value
if feature_names is None:
    features  = ['f%d'%i for i in tree.tree_.feature]
else:
    features  = [feature_names[i] for i in tree.tree_.feature]        

def recurse(left, right, threshold, features, node, depth=0):
        offset = offset_unit*depth
        if (threshold[node] != -2):
                print(offset+"if ( " + features[node] + " <= " + str(threshold[node]) + " ) {")
                if left[node] != -1:
                        recurse (left, right, threshold, features,left[node],depth+1)
                print(offset+"} else {")
                if right[node] != -1:
                        recurse (left, right, threshold, features,right[node],depth+1)
                print(offset+"}")
        else:
                #print(offset,value[node]) 

                #To remove values from node
                temp=str(value[node])
                mid=len(temp)//2
                tempx=[]
                tempy=[]
                cnt=0
                for i in temp:
                    if cnt<=mid:
                        tempx.append(i)
                        cnt+=1
                    else:
                        tempy.append(i)
                        cnt+=1
                val_yes=[]
                val_no=[]
                res=[]
                for j in tempx:
                    if j=="[" or j=="]" or j=="." or j==" ":
                        res.append(j)
                    else:
                        val_no.append(j)
                for j in tempy:
                    if j=="[" or j=="]" or j=="." or j==" ":
                        res.append(j)
                    else:
                        val_yes.append(j)
                val_yes = int("".join(map(str, val_yes)))
                val_no = int("".join(map(str, val_no)))

                if val_yes>val_no:
                    print(offset,'\033[1m',"YES")
                    print('\033[0m')
                elif val_no>val_yes:
                    print(offset,'\033[1m',"NO")
                    print('\033[0m')
                else:
                    print(offset,'\033[1m',"Tie")
                    print('\033[0m')

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