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)
其他回答
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)
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。
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)演练。
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。
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)
推荐文章
- 证书验证失败:无法获得本地颁发者证书
- 当使用pip3安装包时，“Python中的ssl模块不可用”
- 无法切换Python与pyenv
- Python if not == vs if !=
- 如何从scikit-learn决策树中提取决策规则?
- 为什么在Mac OS X v10.9 (Mavericks)的终端中apt-get功能不起作用?
- 将旋转的xtick标签与各自的xtick对齐
- 为什么元组可以包含可变项?
- 如何合并字典的字典?
- 如何创建类属性?
- 数据挖掘中分类和聚类的区别?
- 不区分大小写的“in”
- 在Python中获取迭代器中的元素个数
- 解析日期字符串并更改格式
- 使用try和。Python中的if
