使用python對決策樹算法進行學習

#-*-coding:utf-8-*-
from math import log
import operator

def calcShanonEnt(dataSet):
    '''
    計算給定數據集的香農熵
    :param dataSet:
    :return:shanonEnt
    '''
    numEntries = len(dataSet)
    labelCounts={}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel]=0
        labelCounts[currentLabel] +=1
    shanonEnt = 0.0
    for key in labelCounts:
        prob= float(labelCounts[key])/numEntries
        shanonEnt -= prob*log(prob,2)
    return shanonEnt
def splitDataSet(dataSet,axis,value):
    '''
    按照給特定特徵劃分數據集
    :param dataSet:
    :param axis:
    :param value:
    :return:
    '''
    retDataSet=[]
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]
            reducedFeatVec.extend(featVec[axis+1:])
            retDataSet.append(reducedFeatVec)
    return retDataSet
def createDataSet():
    '''
    數據集
    :return:
    '''
    dataSet = [
        [1, 1, 'yes'],
        [1, 1, 'yes'],
        [1, 0, 'no'],
        [0, 1, 'no'],
        [0, 1, 'no'],
    ]
    labels =['no surfacing','filppers']
    return dataSet,labels

def chooseBestFeatureToSplit(dataSet):
    '''
    選擇最好的特徵進行分割
    :param dataSet:
    :return:
    '''
    numFeatures = len(dataSet[0])-1
    baseEntropy = calcShanonEnt(dataSet)
    bestInfoGain=0.0;bestFeature=-1
    for i in range(numFeatures):
        featList = [example[i] for example in dataSet]
        uniqueVals =set(featList)
        newEntropy = 0.0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet,i,value)
            prob = len(subDataSet)/float(len(dataSet))
            newEntropy+= prob*calcShanonEnt(subDataSet)
        infoGain =baseEntropy-newEntropy
        if infoGain>bestInfoGain:
            bestInfoGain =infoGain
            bestFeature=i
    return bestFeature

def majortyCnt(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=True)
    return sortedClassCount[0][0]

def createTree(dataSet,labels):
    '''
    創建樹的函數代碼
    :param dataSet:
    :param labels:
    :return:
    '''
    classList = [example[-1] for example in dataSet]
    if classList.count(classList[0]) == len(classList):
        return classList[0]
    if len(dataSet[0]) == 1:
        return majortyCnt(classList)
    bestFeat = chooseBestFeatureToSplit(dataSet)
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel:{}}
    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__':
    myDat,labels =createDataSet()
    #print(myDat)
    #print(calcShanonEnt(myDat))
    #print(splitDataSet(myDat,0,1))
    #print(splitDataSet(myDat, 0, 0))
    #print(chooseBestFeatureToSplit(myDat))
    #print(myDat)
    print(createTree(myDat,labels))

作者：WangB