我能从决策树中的训练树中提取基本的决策规则(或“决策路径”)作为文本列表吗?

喜欢的东西:

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

当前回答

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。

其他回答

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)
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。

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