决策树，decision的pyton代码和注释（机器学习实战）

Decison Tree的注释：画图部分不给注释了

from math import log
import numpy
def calcShannonEnt(dataSet):
numEntries = len(dataSet)
labelCounts = {}

#这个是字典，｛a:1,b:2｝其中a，b是key，1，2是对应的value
for featVec in dataSet:
currentLabel = featVec[-1]

#-1代表最后一行，也就是类标
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
def createDataSet():
dataSet=[[1,1,'yes'],
[1,1,'yes'],
[1,0,'no'],
[0,1,'yes'],
[0,1,'no']]
labels=['no surfacing','flippers']
return dataSet,labels
#依据特征划分数据集  axis代表第几个特征  value代表该特征所对应的值  返回的是划分后的数据集
def splitDataSet(dataSet, axis, value):
retDataSet = []
for featVec in dataSet:
if featVec[axis] == value:
reducedFeatVec = featVec[:axis]

#这里的featVec[:axis]，是指从第1（就是下标0）个数到第axis个，不包含
reducedFeatVec.extend(featVec[axis+1:])

#同上，这里的[axis+1,:]就是从最后到axis+1
retDataSet.append(reducedFeatVec)

#extend,append都是扩展用的，a=[1,2],b=[3,4],a.append(b)=[1,2,[3,4]],a.extend(b)=[1,2,3,4]
return retDataSet

#选择最好的数据集(特征)划分方式  返回最佳特征下标def chooseBestFeatureToSplit(dataSet):    numFeatures = len(dataSet[0]) - 1   #特征个数    baseEntropy = calcShannonEnt(dataSet)    bestInfoGain = 0.0; bestFeature = -1    for i in range(numFeatures):   #遍历特征 第i个        featureSet = set([example[i] for example in dataSet])   #第i个特征取值集合

#这一部分代码没啥难度，跟matalb差不多，唯一就是这个set        newEntropy= 0.0        for value in featureSet:            subDataSet = splitDataSet(dataSet, i, value)            prob = len(subDataSet)/float(len(dataSet))            newEntropy += prob * calcShannonEnt(subDataSet)   #该特征划分所对应的entropy        infoGain = baseEntropy - newEntropy        if infoGain > bestInfoGain:            bestInfoGain = infoGain            bestFeature = i    return bestFeature

#创建树的函数代码   python中用字典类型来存储树的结构 返回的结果是myTree-字典def createTree(dataSet, labels):    classList = [example[-1] for example in dataSet]    if classList.count(classList[0]) == len(classList):    #类别完全相同则停止继续划分  返回类标签-叶子节点        return classList[0]    if len(dataSet[0]) == 1:        return majorityCnt(classList)       #遍历完所有的特征时返回出现次数最多的    bestFeat = chooseBestFeatureToSplit(dataSet)    bestFeatLabel = labels[bestFeat]    myTree = {bestFeatLabel:{}}    del(labels[bestFeat])    featValues = [example[bestFeat] for example in dataSet]    #得到的列表包含所有的属性值    uniqueVals = set(featValues)    for value in uniqueVals:        subLabels = labels[:]        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value), subLabels)    return myTree

#多数表决的方法决定叶子节点的分类 ----  当所有的特征全部用完时仍属于多类def majorityCnt(classList):    classCount = {}    for vote in classList:        if vote not in classCount.key():            classCount[vote] = 0;        classCount[vote] += 1    sortedClassCount = sorted(classCount.iteritems(), key = operator.itemgetter(1), reverse = True)

#排序函数，至于怎么用，help就好，里面参数设置有详细例子    return sortedClassCount[0][0]

创建树的函数代码   其实这一步应该放在上一步前面def createTree(dataSet, labels):classList = [example[-1] for example in dataSet]if classList.count(classList[0]) == len(classList):    #类别完全相同则停止继续划分  返回类标签-叶子节点return classList[0]

#count是数数目的函数，a=[1,1,2] a.count[1]=2 len相当于matalb里的lengthif len(dataSet[0]) == 1:return majorityCnt(classList)       #遍历完所有的特征时返回出现次数最多的bestFeat = chooseBestFeatureToSplit(dataSet)bestFeatLabel = labels[bestFeat]myTree = {bestFeatLabel:{}}del(labels[bestFeat])featValues = [example[bestFeat] for example in dataSet]    #得到的列表包含所有的属性值uniqueVals = set(featValues)for value in uniqueVals:subLabels = labels[:]myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value), subLabels)

#这一步creteTree里面又用了creatTree，递归调用，直到len(dataSet[0]) == 1:return myTree