def PostPruning_PEP(Tree, labels, dataSet):
"""
:param Tree:预处理的决策树
:param labels:特征类别属性
:param dataSet:数据集
:return:剪枝后的决策树
"""
classList = [example[-1] for example in dataSet]
majorClass = majorityCnt(classList) # 找到数量最多的类别
et = nodeError(dataSet) + 1 / 2 # 计算非叶节点t误差
Nt = getNumLeaf(Tree) # 子树Tt叶节点数目
eTt = leafError(Tree, labels, dataSet) + Nt / 2 # 子树Tt所有叶节点误差
nt = len(dataSet) # 节点t训练实例数目
if nt > eTt:
SeTt = np.sqrt(eTt * (nt - eTt) / nt) # 子树Tt总误差
else:
SeTt = 0
# print('================================')
# print('Tree=', Tree)
# print('et=', et)
# print('eTt=', eTt)
# print('Nt=', Nt)
# print('nt=', nt)
#print('SeTt=', SeTt)
# print('eTt + SeTt=', eTt + SeTt)
if et < eTt + SeTt: # 若节点t误差小于子树Tt误差
return majorClass # 则进行剪枝，直接返回最大类
firstFeat = list(Tree.keys())[0] # 取出tree的第一个键名
secondDict = Tree[firstFeat] # 取出tree第一个键值
labelIndex = labels.index(firstFeat) # 找到键名在特征属性的索引值
# print('firstFeat=', firstFeat)
# print('secondDict=', secondDict)
subLabels = labels[:labelIndex] # 剔除预处理的键名
subLabels.extend(labels[labelIndex + 1:])
for keys in secondDict.keys(): # 遍历第二个字典的键
if type(secondDict[keys]).__name__ == 'dict':
items = keys.split(',') # 如果该键包含多个特征值，那么进行分离
# print('items=', items)
subDataSet = splitDataSet(dataSet, labelIndex, items) # 划分数据集
secondDict[keys] = PostPruning_PEP(secondDict[keys], subLabels,
subDataSet)
return Tree
def calErrorRatio(Tree, labels, dataSet, NT, infoSet):
"""
:param Tree:决策树
:param labels:特征类别属性
:param dataSet:数据集
:param NT:数据集总样本数目
:param infoSet:所有节点的信息总集合
:return:各个节点的信息集：
包括：子树，节点数目，误差增加率和子树分类前特征
"""
firstFeat = list(Tree.keys())[0] # 取出tree的第一个键名
secondDict = Tree[firstFeat] # 取出tree第一个键值
labelIndex = labels.index(firstFeat) # 找到键名在特征属性的索引值
subLabels = labels[:labelIndex] # 剔除预处理的键名
subLabels.extend(labels[labelIndex + 1:])
for keys in secondDict.keys(): # 遍历第二个字典的键
if type(secondDict[keys]).__name__ == 'dict':
items = keys.split(',') # 如果该键包含多个特征值，那么进行分离
subDataSet = splitDataSet(dataSet, labelIndex, items) # 划分数据集
info, infoSet = calErrorRatio(secondDict[keys], subLabels,
subDataSet, NT, infoSet)
info.setdefault('keys', keys) # 在节点信息集中，增加分类前特征
infoSet.append(info)
# print('=============================')
# print('Tree=', Tree)
# print('firstFeat=', firstFeat)
# print('secondDict=', secondDict)
Rt = nodeError(dataSet) / NT # 计算节点误差率
RTt = leafError(Tree, labels, dataSet) / NT # 计算子树误差率
Nt = getNumLeaf(Tree) # 计算叶节点数目
if Nt == 1:
a = 2.0
else:
a = (Rt - RTt) / (Nt - 1) # 计算误差增加率
info = {'Tree': Tree, 'NumLeaf': Nt, 'a': a} # 构建节点信息集
# print('info=', info)
return info, infoSet
print('trainSet=\n', labels, '\n')
for data in trainSet:
print(data)
print('-------------------------')
print('testSet=\n', labels, '\n')
for data in testSet:
print(data)
print('-------------------------')
'''
"""对ID3算法生成的决策树，进行剪枝"""
''''''
print('===========================================')
# 先用ID3算法，将训练集生成决策树
ID3TrainTree = createID3Tree(list(trainSet), list(labels))
print('The ID3 Decision Tree:', 'Depth:', getTreeDepth(ID3TrainTree), ';Leaf:', getNumLeaf(ID3TrainTree))
print('The Node with largest number is', findKeyNode(ID3TrainTree))
# 根据测试集，进行预剪枝
PreID3Tree = PrePruning(list(trainSet), testSet, list(labels))
print('The Pre_Pruning_ID3 Decision Tree:', 'Depth:', getTreeDepth(PreID3Tree), ';Leaf:', getNumLeaf(PreID3Tree))
print('The Node with largest number is', findKeyNode(PreID3Tree))
# 根据测试集，使用REP方法进行后剪枝
REPID3Tree = PostPruning_REP(list(trainSet), testSet, list(labels))
print('The REP_Pruning_ID3 Decision Tree:', 'Depth:', getTreeDepth(REPID3Tree), ';Leaf:', getNumLeaf(REPID3Tree))
print('The Node with largest number is', findKeyNode(REPID3Tree))
# 根据测试集，使用REP方法进行后剪枝
PEPID3Tree = PostPruning_PEP(ID3TrainTree, list(labels), list(dataSet))
print('The PEP_Pruning_ID3 Decision Tree:', 'Depth:', getTreeDepth(PEPID3Tree), ';Leaf:', getNumLeaf(PEPID3Tree))