firstLabelIndex = labels.index(firstLabel) # 属性对应的index
secondDict = tree[firstLabel]
value = testData[firstLabelIndex] # 属性值
if type(secondDict[value]).__name__ == "dict": # 假如还是一棵树则递归
classLabel = classifyDecisionTree(secondDict[value], labels, testData)
else:
classLabel = secondDict[value]
return classLabel
if __name__ == '__main__':
# 读取数据
lensesData, lensesLable = loadDataSet("lenses.txt")
# 复制属性标签，
# createTree()操作会影响传入的类别标签
lensesLableCopy = lensesLable[:]
# 创建树
decisionTree = createTree(lensesData, lensesLableCopy)
print(decisionTree)
# 对树进行绘图
TreePlot.createPlot(decisionTree)
# 进行预测
classLabel = classifyDecisionTree(decisionTree, lensesLable,
["young", "hyper", "yes", "normal"])
print(classLabel)
'''
读取序列化对象
'''
def grabTree(filename):
fr = open(filename, "rb")
return pickle.load(fr)
if __name__ == '__main__':
# 创建示例数据集
dataSet, labels = createDataSet()
lebelsCopy = labels[:]
# 学习构建决策树
tree = createTree(dataSet, labels)
print(tree)
# 画决策树
TreePlot.createPlot(tree)
# 序列化存储树结构
storeTree(tree, "object.txt")
# 文件中读取数结构
myTree = grabTree("object.txt")
print(myTree)
print(classifyDecisionTree(myTree, lebelsCopy, [1, 1]))
classCount[vote]=0
classCount[vote]+=1
sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
return sortedClassCount[0][0]
def createTree(dataSet,labels):
classList=[example[-1] for example in dataSet] # 类别：男或女
if classList.count(classList[0])==len(classList):
return classList[0]
if len(dataSet[0])==1:
return majorityCnt(classList)
bestFeat=chooseBestFeatureToSplit(dataSet) #选择最优特征
bestFeatLabel=labels[bestFeat]
myTree={bestFeatLabel:{}} #分类结果以字典形式保存
del(labels[bestFeat])
featValues=[example[bestFeat] for example in dataSet]
uniqueVals=set(featValues)
for value in uniqueVals:
subLabels=labels[:]
myTree[bestFeatLabel][value]=createTree(splitDataSet\
(dataSet,bestFeat,value),subLabels)
return myTree
if __name__=='__main__':
dataSet, labels=createDataSet1() # 创造示列数据
mytree=createTree(dataSet, labels) # 输出决策树模型结果
print mytree
TreePlot.createPlot(mytree)
__author__ = 'wanghao'
"""
the glasses examples
"""
import ID3Tree
import TreePlot
fr = open('./lenses.txt')
DataList = fr.readlines()
DataSet = []
for data in DataList:
DataSet.append(data.strip().split('\t'))
print "The dateSet is ", DataSet
Labels = ['age', 'prescript', 'astigmatic', 'tearRate']
LenseTree = ID3Tree.createTree(DataSet, Labels)
print "the result ID3 Tree is ", LenseTree
TreePlot.createPlot(LenseTree)
print "---------------------------------------\n" # Get the leaf Node LeafNodeNum = ID3Tree.getNumLeafs(myTree) print "This ID3 Tree leaf node num is ", LeafNodeNum print "---------------------------------------\n" # Get the depth of the ID3 MaxDepth = ID3Tree.getTreeDepth(myTree) print "This ID3 tree max depth is ", MaxDepth print "---------------------------------------\n" # Plot the tree TreePlot.createPlot(myTree) print "---------------------------------------\n"
from TestTrees import calcShannonEnt
from TestTrees import chooseBestFeatureToSplit
from TestTrees import createTree
import TestTrees
import TreePlot
def createDataSet():
dataSet = [[1, 1, 'yes'], [1, 1, 'yes'], [1, 0, 'no'], [0, 1, 'no'],
[0, 1, 'no']]
labels = ['no surfacing', 'flippers']
return dataSet, labels
fr = open('matpilb\lenses.txt')
lenses = [inst.strip().split('\t') for inst in fr.readlines()]
lensesLabels = ['ages', 'prescript', 'astigmatic', 'tearRate']
print(lenses)
lensesTree = TestTrees.createTree(lenses, lensesLabels)
TreePlot.createPlot(lensesTree)
'>=' + str(splite))] = CreateTree(
son_data, label_lisan, label_lianxu)
elif j[feature] < splite and i == 1:
son_data.append(j)
if len(son_data) == 0:
return leaf(data)
else:
Tree[labels_word[feature]][str(
'<' + str(splite))] = CreateTree(
son_data, label_lisan, label_lianxu)
else:
for j in data:
if j[feature] == label_value[feature][i]: son_data.append(j)
if len(son_data) == 0:
return leaf(data)
else:
Tree[labels_word[feature]][
label_value[feature][i]] = CreateTree(
son_data, label_lisan, labels_lianxu)
return Tree
if __name__ == '__main__':
Tree = CreateTree(dataSet, labels_lisan, labels_lianxu)
TreePlot.createPlot(Tree)
