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。

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_。值分别为节点数组拆分特征和节点数组值。你可以参考这个github来源的更多细节。

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)

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)

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'

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 <conditions> THEN > <NodeA>*， >* CASE WHEN <条件> THEN <NodeB>*， > ....)* > 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)