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
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')
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)
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。
Scikit learn在0.21版(2019年5月)中引入了一个名为export_text的有趣的新方法，用于从树中提取规则。这里的文档。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具可读性，使用feature_names参数并传递一个特性名称列表。例如，如果你的模型是model，你的特征是在一个名为X_train的数据框架中命名的，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
从这个答案中，您可以得到一个可读且高效的表示:https://stackoverflow.com/a/65939892/3746632
输出如下所示。X为一维向量，表示单个实例的特征。
from numba import jit,njit
@njit
def predict(X):
ret = 0
if X[0] <= 0.5: # if w_pizza <= 0.5
if X[1] <= 0.5: # if w_mexico <= 0.5
if X[2] <= 0.5: # if w_reusable <= 0.5
ret += 1
else: # if w_reusable > 0.5
pass
else: # if w_mexico > 0.5
ret += 1
else: # if w_pizza > 0.5
pass
if X[0] <= 0.5: # if w_pizza <= 0.5
if X[1] <= 0.5: # if w_mexico <= 0.5
if X[2] <= 0.5: # if w_reusable <= 0.5
ret += 1
else: # if w_reusable > 0.5
pass
else: # if w_mexico > 0.5
pass
else: # if w_pizza > 0.5
ret += 1
if X[0] <= 0.5: # if w_pizza <= 0.5
if X[1] <= 0.5: # if w_mexico <= 0.5
if X[2] <= 0.5: # if w_reusable <= 0.5
ret += 1
else: # if w_reusable > 0.5
ret += 1
else: # if w_mexico > 0.5
ret += 1
else: # if w_pizza > 0.5
pass
if X[0] <= 0.5: # if w_pizza <= 0.5
if X[1] <= 0.5: # if w_mexico <= 0.5
if X[2] <= 0.5: # if w_reusable <= 0.5
ret += 1
else: # if w_reusable > 0.5
ret += 1
else: # if w_mexico > 0.5
pass
else: # if w_pizza > 0.5
ret += 1
if X[0] <= 0.5: # if w_pizza <= 0.5
if X[1] <= 0.5: # if w_mexico <= 0.5
if X[2] <= 0.5: # if w_reusable <= 0.5
ret += 1
else: # if w_reusable > 0.5
pass
else: # if w_mexico > 0.5
pass
else: # if w_pizza > 0.5
pass
if X[0] <= 0.5: # if w_pizza <= 0.5
if X[1] <= 0.5: # if w_mexico <= 0.5
if X[2] <= 0.5: # if w_reusable <= 0.5
ret += 1
else: # if w_reusable > 0.5
pass
else: # if w_mexico > 0.5
ret += 1
else: # if w_pizza > 0.5
ret += 1
if X[0] <= 0.5: # if w_pizza <= 0.5
if X[1] <= 0.5: # if w_mexico <= 0.5
if X[2] <= 0.5: # if w_reusable <= 0.5
ret += 1
else: # if w_reusable > 0.5
pass
else: # if w_mexico > 0.5
pass
else: # if w_pizza > 0.5
ret += 1
if X[0] <= 0.5: # if w_pizza <= 0.5
if X[1] <= 0.5: # if w_mexico <= 0.5
if X[2] <= 0.5: # if w_reusable <= 0.5
ret += 1
else: # if w_reusable > 0.5
pass
else: # if w_mexico > 0.5
pass
else: # if w_pizza > 0.5
pass
if X[0] <= 0.5: # if w_pizza <= 0.5
if X[1] <= 0.5: # if w_mexico <= 0.5
if X[2] <= 0.5: # if w_reusable <= 0.5
ret += 1
else: # if w_reusable > 0.5
pass
else: # if w_mexico > 0.5
pass
else: # if w_pizza > 0.5
pass
if X[0] <= 0.5: # if w_pizza <= 0.5
if X[1] <= 0.5: # if w_mexico <= 0.5
if X[2] <= 0.5: # if w_reusable <= 0.5
ret += 1
else: # if w_reusable > 0.5
pass
else: # if w_mexico > 0.5
pass
else: # if w_pizza > 0.5
pass
return ret/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
