机器学习基础决策树分类

决策树就是通过一系列条件判断分类的方法

#encoding:  utf-8
from math import log
import operator
#两个文件相互import会出错，具体参考http://blog.csdn.net/sinat_16790541/article/details/43376741
#import TreePlotter
import pickle  #用于序列化对象并且在磁盘上存储


def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}
    #为所有可能分类创造字典
    for featVec in dataSet:
        currentLabel = featVec[-1]  #键值是最后一列的数值
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel] = 0
        labelCounts[currentLabel] += 1
    #计算香农熵
    shannonEnt = 0.0
    for key in labelCounts:
        prob = float(labelCounts[key]) / numEntries  #所有类出现的频率
        shannonEnt -= prob * log(prob, 2)  # H=∑ p[i]*log(p[i],2)
    return shannonEnt


#自定义数据
def createDataSet():
    dataSet = [[1, 1, 'yes'], [1, 1, 'yes'], [0, 1, 'no'], [1, 0, 'no'],
               [0, 1, 'no']]
    labels = ['no surfacing', 'flippers']
    return dataSet, labels


#按照给定特征划分数据集，参数：待划分数据集，划分数据集的特征的位置，需要返回的特征的值
def splitDataSet(dataSet, axis, value):
    retDateSet = []  #新的list对象，避免修改dataSet
    for featVec in dataSet:
        if featVec[axis] == value:
            #抽取符合的元素,去掉用作特征的元素
            reducedFeatVec = featVec[:axis]
            #extend()函數合併添加列表元素
            reducedFeatVec.extend(featVec[axis + 1:])
            #append()函數添加第四個元素，列表
            retDateSet.append(reducedFeatVec)
    return retDateSet


#选择最好的数据集划分方式
def chooseBestFeatureToSplit(dataSet):
    #在第一行计算特征的数量
    numFeatures = len(dataSet[0]) - 1
    #计算初始信息熵
    baseEntropy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0
    bestFeature = -1
    for i in range(numFeatures):
        #创建唯一的分类标签
        featList = [example[i] for example in dataSet]
        #set集合中元素互不相同
        uniqueVals = set(featList)
        newEntropy = 0.0
        #计算每种划分方式的信息熵
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet, i, value)
            prob = len(subDataSet) / float(len(dataSet))
            newEntropy += prob * calcShannonEnt(subDataSet)
        infoGain = baseEntropy - newEntropy
        #计算最好的信息增益
        if (infoGain > bestInfoGain):
            bestInfoGain = infoGain
            bestFeature = i
    return bestFeature


#返回出现次数最多的分类名称
def majorityCnt(classList):
    classCount = {}
    for vote in classList:
        if vote not in classCount.keys():
            classCount[vote] = 0
        classCount[vote] += 1
    sortedClassCount = sorted(
        classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


#递归建树，参数为数据集和标签列表
def createTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]
    #类别完全相同时停止划分
    if classList.count(classList[0]) == len(classList):
        return classList[0]
    #便利完所有特征时返回出现次数最多的类别
    if len(dataSet[0]) == 1:
        return majorityCnt(classList)
    #当前数据集选取的最好特征
    bestFeat = chooseBestFeatureToSplit(dataSet)
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel: {}}
    del (labels[bestFeat])
    #得到列表包含的所有属性值
    featValues = [example[bestFeat] for example in dataSet]
    uniqueVals = set(featValues)
    #递归建树
    for value in uniqueVals:
        #函数参数是列表类型时，参数按引用方式传递，所以采用新变量代替原始列表
        subLabels = labels[:]
        myTree[bestFeatLabel][value] = createTree(
            splitDataSet(dataSet, bestFeat, value), subLabels)
    return myTree


def classify(inputTree, featLabels, testVec):
    firstStr = list(inputTree.keys())[0]
    secondDict = inputTree[firstStr]
    #将标签字符串转换为索引
    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

#利用pickle包存储树，减少后续计算时间
def storeTree(inputTree, filename):
    ##读写模式:r只读,r+读写,w新建(会覆盖原有文件),a追加,b二进制文件.常用模式
    #pickle存储方式默认是二进制方式，所以读写方式要加b
    fw = open(filename, 'wb+')
    pickle.dump(inputTree, fw)
    fw.close


def grabTree(filename):
    fr = open(filename, 'rb+')
    return pickle.load(fr)

'''
mydat, labels = createDataSet()
print(mydat)
print(labels)

print(calcShannonEnt(mydat))
print(splitDataSet(mydat, 0, 1))
print(chooseBestFeatureToSplit(mydat))
myTree = createTree(mydat, labels)

myTree = TreePlotter.retrieveTree(0)
print(myTree)
storeTree(myTree, 'classifierStorage.txt')
print(grabTree('classifierStorage.txt'))
print(classify(myTree, labels, [1, 1]))
'''

采用matplotlib来绘制属树形图

#encoding:  utf-8
import matplotlib.pyplot as plt
import Trees

#定义文本框和箭头格式
decisionNode = dict(boxstyle='sawtooth', fc='0.8')
leafNode = dict(boxstyle='round4', fc='0.8')
arrow_args = dict(arrowstyle='<-')


#绘制带箭头的注解
def plotNode(nodeTxt, centerPt, parentPt, nodeType):
    createPlot.ax1.annotate(
        nodeTxt,
        xy=parentPt,
        xycoords='axes fraction',
        xytext=centerPt,
        textcoords='axes fraction',
        va='center',
        ha='center',
        bbox=nodeType,
        arrowprops=arrow_args)


def createPlot(inTree):
    fig = plt.figure(1, facecolor='white')
    fig.clf()
    #定义绘图区,绘制图形的X轴和Y轴的有效范围都是0.0~1.0
    axprops = dict(xticks=[], yticks=[])
    createPlot.ax1 = plt.subplot(111, frameon=False, **axprops)
    #记录树的宽度和深度
    plotTree.totalW = float(getNumLeafs(inTree))
    plotTree.totalD = float(getTreeDepth(inTree))
    #分号使用在把多个简单语句（比如赋值语句，print，函数调用）放在同一行的时候，使用分号把它们隔开
    plotTree.xOff = -0.5 / plotTree.totalW
    plotTree.yOff = 1.0
    plotTree(inTree, (0.5, 1.0), '')
    plt.show()
    '''
    plotNode('judge', (0.5, 0.1), (0.1, 0.5), decisionNode)
    plotNode('leaf', (0.8, 0.1), (0.3, 0.8), leafNode)
    '''


#求叶节点数目
def getNumLeafs(myTree):
    numLeafs = 0
    firstStr = list(myTree.keys())[0]
    secondDict = myTree[firstStr]
    for key in secondDict.keys():
        #测试节点的数据类型是否还是字典
        if type(secondDict[key]).__name__ == 'dict':
            numLeafs += getNumLeafs(secondDict[key])
        else:
            numLeafs += 1
    return numLeafs


#求树的深度
def getTreeDepth(myTree):
    maxDepth = 0
    firstStr = list(myTree.keys())[0]
    secondDict = myTree[firstStr]
    for key in secondDict.keys():
        if type(secondDict[key]).__name__ == 'dict':
            thisDepth = 1 + getTreeDepth(secondDict[key])
        else:
            thisDepth = 1
        if thisDepth > maxDepth:
            maxDepth = thisDepth
    return maxDepth


#在父子节点之间填充文本信息
def plotMidText(cntrPt, parentPt, txtString):
    xMid = (parentPt[0] - cntrPt[0]) / 2.0 + cntrPt[0]
    yMid = (parentPt[1] - cntrPt[1]) / 2.0 + cntrPt[1]
    createPlot.ax1.text(xMid, yMid, txtString)


def plotTree(myTree, parentPt, nodeText):
    #计算宽和高
    numLeafs = getNumLeafs(myTree)
    depth = getTreeDepth(myTree)
    firstStr = list(myTree.keys())[0]
    cntrPt = (plotTree.xOff + (1.0 + float(numLeafs)) / 2.0 / plotTree.totalW,
              plotTree.yOff)
    #标记子节点属性值
    plotMidText(cntrPt, parentPt, nodeText)
    plotNode(firstStr, cntrPt, parentPt, decisionNode)
    secondDict = myTree[firstStr]
    #减少y的偏移量
    plotTree.yOff = plotTree.yOff - 1.0 / plotTree.totalD
    for key in secondDict.keys():
        if (type(secondDict[key]).__name__ == 'dict'):
            plotTree(secondDict[key], cntrPt, str(key))
        else:
            plotTree.xOff = plotTree.xOff + 1.0 / plotTree.totalW
            plotNode(secondDict[key], (plotTree.xOff, plotTree.yOff), cntrPt,
                     leafNode)
            plotMidText((plotTree.xOff, plotTree.yOff), cntrPt, str(key))
    plotTree.yOff = plotTree.yOff + 1.0 / plotTree.totalD


#预先存储树的信息避免每次测试的时候都要建树
def retrieveTree(i):
    listOfTree = [{
        'no surfacing': {
            0: 'no',
            1: {
                'flippers': {
                    0: 'no',
                    1: 'yes'
                }
            }
        }
    }, {
        'no surfacing': {
            0: 'no',
            1: {
                'flippers': {
                    0: {
                        'head': {
                            0: 'no',
                            1: 'yes'
                        }
                    },
                    1: 'no'
                }
            }
        }
    }]
    return listOfTree[i]

'''
#createPlot()
myTree = retrieveTree(0)
myTree['no surfacing'][3]='maybe'
print(myTree)
createPlot(myTree)
'''
fr = open('lenses.txt','r+')
#readlines()读取整个文件所有行，保存在一个列表(list)变量中，每行作为一个元素
lenses=[inst.strip().split('\t') for inst in fr.readlines()]
lensesLabels=['age','prescript','astigmatic','tearRate']
lensesTree=Trees.createTree(lenses,lensesLabels)
createPlot(lensesTree)