决策树——实践

# -*- coding: utf-8 -*-"""Created on Tue Sep 08 10:10:15 2015@author: Administrator"""import operator   #为了能够处理叶子节点的类标签仍然不唯一的情况。from math import log#计算训练数据集的香农熵def calcShannonEnt(dataSet):    numEntries = len(dataSet)    labelCounts = {}    for featVec in dataSet:        currentLabel = featVec[-1]        if currentLabel not in labelCounts.keys():            labelCounts[currentLabel] = 0   #这里不能为1,因为后一语句是一定执行的。        labelCounts[currentLabel] += 1    shannonEnt = 0.0    for key in labelCounts:        prob = float(labelCounts[key])/numEntries        shannonEnt -= prob * log(prob, 2)    return shannonEnt#创建训练数据集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#按照给定特征划分数据集def splitDataSet(dataSet, axis, value):   #第二个参数为划分数据集的特征，第三个参数为需要返回的特征的值。    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    baseEntropy = calcShannonEnt(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 * calcShannonEnt(subDataSet)        infoGain = baseEntropy - newEntropy        if (infoGain > bestInfoGain):            bestInfoGain = infoGain            bestFeature = i    return bestFeature#处理叶子节点的类标签仍然不唯一的情况。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 = True)    return sortedClassCount[0][0]    #创建树的函数代码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:{}}    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    #使用决策树的分类函数def classify(inputTree, featLabels, testVec):    firstStr = inputTree.keys()[0]    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    #使用pickle模块存储决策树def storeTree(inputTree, filename):    import pickle    fw = open(filename, 'w')    pickle.dump(inputTree, fw)    fw.close()def grabTree(filename):    import pickle    fr = open(filename)    return pickle.load(fr)