机器学习实战-使用决策树预测隐形眼镜类型-python3

from math import log

数据集链接

计算给定数据集的香农熵

def calcShannonEnt(dataSet):
    numEntries=len(dataSet)
    labelCounts={}
    for featVec in dataSet:
        currentLabel=featVec[-1]
        #print('calcShannonEnt函数输出featVec：')
        #print(featVec)
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel]=0
        labelCounts[currentLabel]+=1
    shannonEnt=0.0
    for key in labelCounts:
        prob=float(labelCounts[key])/numEntries
        shannonEnt-=prob*log(prob,2)
    return shannonEnt

按照给定特征划分数据集

def splitDataSet(dataSet,axis,value):
    retDataSet=[]
    for featVec in dataSet:
        if featVec[axis]==value:
            reducedFeatVec=featVec[:axis]
            reducedFeatVec.extend(featVec[axis+1:])
            retDataSet.append(reducedFeatVec)
    return retDataSet

选择最好的数据集划分方式

def chooseBestFeatureToSplit(dataSet):
    numFeatures=len(dataSet[0])-1#特征的数量（因每一行有一列类别，故减一）
    baseEntropy=calcShannonEnt(dataSet)
    bestInfoGain=0.0
    bestFeature=-1
    for i in range(numFeatures):
        featList=[example[i] for example in dataSet]
        #print('chooseBestFeatureToSplit函数输出featList:')
        #print(featList)
        uniqueVals=set(featList)
        newEntropy=0.0
        for value in uniqueVals:
            subDataSet=splitDataSet(dataSet,i,value)
            prob=len(subDataSet)/float(len(dataSet))
            newEntropy+=prob*calcShannonEnt(subDataSet)
        infoGain=baseEntropy-newEntropy
        if(infoGain>bestInfoGain):
            bestInfoGain=infoGain
            bestFeature=i
    return bestFeature

选取频率最高的类

import operator
def majorityCnt(classList):
    classCount={}
    for vote in classList:
        if vote not in classCount.keys():
            classCount[vote]=0
        classCount[vote]+=1
    sortedClassCount=sorted(classCount.iteritems(),key=operator.itemgetter(1),reverse=Ture)
    return sortedClassCount[0][0]

创建决策树

def createTree(dataSet,labels):
    classList=[example[-1] for example in dataSet]
    if classList.count(classList[0])==len(classList):
        return classList[0]
    if len(dataSet[0])==1:
        return majorityCnt(classList)
    bestFeat=chooseBestFeatureToSplit(dataSet)
    bestFeatLabel=labels[bestFeat]
    myTree={bestFeatLabel:{}}
    #print(labels[bestFeat])
    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

使用决策树分类

def classify(inputTree,featLabels,testVec):
    firstStr=list(inputTree.keys())[0]#源代码没有list，会产生错误：TypeError: 'dict_keys' object does not support indexing，这是由于python3改变了dict.keys,返回的是dict_keys对象,支持iterable 但不支持indexable，我们可以将其明确的转化成list：
    #print(firstStr)
    #print(featLabels)
    secondDict=inputTree[firstStr]
    featIndex=featLabels.index(firstStr)
    for key in secondDict.keys():
        if testVec[featIndex]==key:
            if type(secondDict[key]).__name__=='dict':
                classLabel=classify(secondDict[key],featLabels,testVec)
            else:
                classLabel=secondDict[key]
    return classLabel

调用函数

fr=open('lenses.txt')
lenses=[inst.strip().split('\t') for inst in fr.readlines()]
#print(lenses)
lensesLabels=['age','prescript','astigmatic','tearRate']
lensesTree=createTree(lenses,lensesLabels)
lensesTree

lensesLabels=['age','prescript','astigmatic','tearRate']#直接用上边的lenseslabels会缺少属性，个人感觉是createtree函数中的del（）的问题
#print(lensesLabels)
classify(lensesTree,lensesLabels,['presbyopic','hyper','no','normal'])

运行结果