如何从scikit-learn决策树中提取决策规则?

from StringIO import StringIO
out = StringIO()
out = tree.export_graphviz(clf, out_file=out)
print out.getvalue()

你可以看到一个有向图树。然后，clf.tree_.feature和clf.tree_.value分别是节点数组拆分特征和节点数组值。你可以从这个github源中参考更多细节。

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上调用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.]]
}
}
}

下面是一个函数，在python3下打印scikit-learn决策树的规则，并对条件块进行偏移，使结构更具可读性:

def print_decision_tree(tree, feature_names=None, offset_unit='    '):
'''Plots textual representation of rules of a decision tree
tree: scikit-learn representation of tree
feature_names: list of feature names. They are set to f1,f2,f3,... if not specified
offset_unit: a string of offset of the conditional block'''


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+"return " + str(value[node]))


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

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)

一个树形图显示在这里

因为每个人都很乐于助人，所以我将对Zelazny7和Daniele的漂亮解决方案进行修改。这是针对python 2.7的，使用tab使其更具可读性:

def get_code(tree, feature_names, tabdepth=0):
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, tabdepth=0):
if (threshold[node] != -2):
print '\t' * tabdepth,
print "if ( " + features[node] + " <= " + str(threshold[node]) + " ) {"
if left[node] != -1:
recurse (left, right, threshold, features,left[node], tabdepth+1)
print '\t' * tabdepth,
print "} else {"
if right[node] != -1:
recurse (left, right, threshold, features,right[node], tabdepth+1)
print '\t' * tabdepth,
print "}"
else:
print '\t' * tabdepth,
print "return " + str(value[node])


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

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:

1. 使用tree_.threshold == -2来确定一个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tree.feature或tree.children_*。
2. features = [feature_names[i] for i in tree_.feature]行在我的sklearn版本中崩溃了，因为tree.tree_.feature的一些值是-2(特别是对于叶节点)。
3. 递归函数中不需要有多个if语句，一个就可以了。

在0.18.0版本中有一个新的DecisionTreeClassifier方法decision_path。开发人员提供了一个广泛的(文档良好的)预排。

演练中打印树结构的第一部分代码似乎没有问题。但是，我修改了第二节中的代码来检查一个示例。我的更改用# <--表示

在拉取请求# 8653和# 10951中指出错误后，下面代码中由# <--标记的更改已在演练链接中更新。现在就容易多了。

sample_id = 0
node_index = node_indicator.indices[node_indicator.indptr[sample_id]:
node_indicator.indptr[sample_id + 1]]


print('Rules used to predict sample %s: ' % sample_id)
for node_id in node_index:


if leave_id[sample_id] == node_id:  # <-- changed != to ==
#continue # <-- comment out
print("leaf node {} reached, no decision here".format(leave_id[sample_id])) # <--


else: # < -- added else to iterate through decision nodes
if (X_test[sample_id, feature[node_id]] <= threshold[node_id]):
threshold_sign = "<="
else:
threshold_sign = ">"


print("decision id node %s : (X[%s, %s] (= %s) %s %s)"
% (node_id,
sample_id,
feature[node_id],
X_test[sample_id, feature[node_id]], # <-- changed i to sample_id
threshold_sign,
threshold[node_id]))


Rules used to predict sample 0:
decision id node 0 : (X[0, 3] (= 2.4) > 0.800000011921)
decision id node 2 : (X[0, 2] (= 5.1) > 4.94999980927)
leaf node 4 reached, no decision here

更改sample_id以查看其他示例的决策路径。我没有向开发人员询问这些更改，只是在示例中看起来更直观。

修改了Zelazny7的代码以从决策树中获取SQL。

# SQL from decision tree


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]
le='<='
g ='>'
# 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)
print 'case '
for j,child in enumerate(idx):
clause=' when '
for node in recurse(left, right, child):
if len(str(node))<3:
continue
i=node
if i[1]=='l':  sign=le
else: sign=g
clause=clause+i[3]+sign+str(i[2])+' and '
clause=clause[:-4]+' then '+str(j)
print clause
print 'else 99 end as clusters'

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…

我已经经历过这些了，但我需要把规则写成这种形式

if A>0.4 then if B<0.2 then if C>0.8 then class='X'

所以我改编了@paulkernfeld的答案(谢谢)，你可以根据自己的需要定制

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


global k
k = 0
def recurse(node, depth, parent):
global k
indent = "  " * depth


if tree_.feature[node] != _tree.TREE_UNDEFINED:
name = feature_name[node]
threshold = tree_.threshold[node]
s= "{} <= {} ".format( name, threshold, node )
if node == 0:
pathto[node]=s
else:
pathto[node]=pathto[parent]+' & ' +s


recurse(tree_.children_left[node], depth + 1, node)
s="{} > {}".format( name, threshold)
if node == 0:
pathto[node]=s
else:
pathto[node]=pathto[parent]+' & ' +s
recurse(tree_.children_right[node], depth + 1, node)
else:
k=k+1
print(k,')',pathto[parent], tree_.value[node])
recurse(0, 1, 0)

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的优秀人员提供了一个严肃的文档要求——学会正确地记录sklearn.tree.Tree API，这是DecisionTreeClassifier作为其属性tree_公开的底层树结构。

下面是一种使用SKompiler库将整个树转换为单个(不一定太容易读懂)python表达式的方法:

from skompiler import skompile
skompile(dtree.predict).to('python/code')

只需要像这样使用sklearn.tree中的函数

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

然后在你的项目文件夹中寻找文件tree.dot，复制所有的内容并将其粘贴到http://www.webgraphviz.com/并生成你的图形:)

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)

在版本0.21(2019年5月)中，Scikit learn引入了一个名为export_text的有趣的新方法来从树中提取规则。文件在这里。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可读，使用feature_names参数并传递一个特性名称列表。例如，如果你的模型名为model，而你的特征在一个名为X_train的数据框架中命名，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

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)

下面是我以一种可以直接在sql中使用的形式提取决策规则的方法，这样数据就可以按节点分组。(根据之前海报的做法)

结果将是后续的CASE子句，可以复制到sql语句，例如。

SELECT COALESCE(*CASE WHEN <condition >然后在;& lt; NodeA> *,比;*当 & lt; conditions>THEN <NodeB>*， >…)节点名,*比;FROM <表或视图>

import numpy as np


import pickle
feature_names=.............
features  = [feature_names[i] for i in range(len(feature_names))]
clf= pickle.loads(trained_model)
impurity=clf.tree_.impurity
importances = clf.feature_importances_
SqlOut=""


#global Conts
global ContsNode
global Path
#Conts=[]#
ContsNode=[]
Path=[]
global Results
Results=[]


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,ParentNode=0,IsElse=0):
global Conts
global ContsNode
global Path
global Results
global LeftParents
LeftParents=[]
global RightParents
RightParents=[]
for i in range(len(left)): # This is just to tell you how to create a list.
LeftParents.append(-1)
RightParents.append(-1)
ContsNode.append("")
Path.append("")




for i in range(len(left)): # i is node
if (left[i]==-1 and right[i]==-1):
if LeftParents[i]>=0:
if Path[LeftParents[i]]>" ":
Path[i]=Path[LeftParents[i]]+" AND " +ContsNode[LeftParents[i]]
else:
Path[i]=ContsNode[LeftParents[i]]
if RightParents[i]>=0:
if Path[RightParents[i]]>" ":
Path[i]=Path[RightParents[i]]+" AND not " +ContsNode[RightParents[i]]
else:
Path[i]=" not " +ContsNode[RightParents[i]]
Results.append(" case when  " +Path[i]+"  then ''" +"{:4d}".format(i)+ " "+"{:2.2f}".format(impurity[i])+" "+Path[i][0:180]+"''")


else:
if LeftParents[i]>=0:
if Path[LeftParents[i]]>" ":
Path[i]=Path[LeftParents[i]]+" AND " +ContsNode[LeftParents[i]]
else:
Path[i]=ContsNode[LeftParents[i]]
if RightParents[i]>=0:
if Path[RightParents[i]]>" ":
Path[i]=Path[RightParents[i]]+" AND not " +ContsNode[RightParents[i]]
else:
Path[i]=" not "+ContsNode[RightParents[i]]
if (left[i]!=-1):
LeftParents[left[i]]=i
if (right[i]!=-1):
RightParents[right[i]]=i
ContsNode[i]=   "( "+ features[i] + " <= " + str(threshold[i])   + " ) "


recurse(left, right, threshold, features, 0,0,0,0)
print_decision_tree(clf,features)
SqlOut=""
for i in range(len(Results)):
SqlOut=SqlOut+Results[i]+ " end,"+chr(13)+chr(10)