机器学习实战 第3章 决策树

机器学习实战 第3章 决策树 python 3.6

from math import log
import operator

#创建数据集
def createDataSet():
    dataSet = [[1,1,'yes'],
              [1,1,'yes'],
              [1,0,'no'],
              [0,1,'no'],
              [0,1,'no']]
    labels = ['noSurfacing','flippers','fish']
    return dataSet, labels
    
#3-1计算给懂数据集的香农熵
def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}
    for featVec in dataSet:
        currentLabel = featVec[-1]
        if currentLabel not in labelCounts.keys():
            labelCounts[currentLabel] = 0
        labelCounts[currentLabel] += 1
    shannonEnt = 0.0
    for key in labelCounts:
        prob = float(labelCounts[key]) / numEntries
        shannonEnt -= prob*log(prob,2)
    return shannonEnt

dataSet, labels = createDataSet()
#3-2按照给定特征划分数据集
#选出dataset中第axis个特征值为value的数据集，数据集不包含第axis个特征的值
def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reduceFeatVec = featVec[:axis]
            reduceFeatVec.extend(featVec[axis+1:])
            retDataSet.append(reduceFeatVec)
    return retDataSet

#3-3选择最好的数据集划分方式
# 针对每一个特征的计算信息增益，返回信息增益最大的特征
def chooseBestFeatureToSplit(dataSet):
    numFeatures = len(dataSet[0]) - 1
    baseEntropy = calcShannonEnt(dataSet)
    baseInfoGain = 0.0; bestFeature = -1
    for i in range(numFeatures):
        featList = [example[i] for example in dataSet]
#         print(featList)
        uniqueVals = set(featList)
#         print(uniqueVals)
        newEntropy = 0.0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet, i, value)
#             print(i,value,subDataSet)
            prob = len(subDataSet) / float(len(dataSet))
            newEntropy += prob * calcShannonEnt(subDataSet)
        infoGain = baseEntropy - newEntropy
        if infoGain > baseInfoGain:
            baseInfoGain = infoGain
            bestFeature = i
    return bestFeature  

def majorrityCnt(classLsit):
    classCount = {}
    for vote in classLsit:
        if vote not in classCount.keys():
            classCount[vote] = 0
        classCount[vote] += 1
    sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)  #items python3的对应iteritems的函数
    return sortedClassCount[0][0]

#递归构建决策树 
# 3-4创建数的函数代码
def createTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]   # 获取类别
#     print(classList)
    if classList.count(classList[0]) == len(classList):     #只剩一个类别，返回该类别
        return classList[0]
    if len(dataSet[0]) == 1:                           #遍历完所有特征，若仍然无法将数据集划分成仅包含唯一类别的分组，则返回出现次数最多的类别
        return majorrityCnt(classList)
    bestFeat = chooseBestFeatureToSplit(dataSet)   # 获取信息增益最大的特征
    bestFeatLabel = labels[bestFeat]              # 最优特征标签
    myTree = {bestFeatLabel:{}}                     # 最优特征对应的树
    print('myTree:',myTree)
    del(labels[bestFeat])                         # 删除已经使用过的特征
    featValues = [example[bestFeat] for example in dataSet]   # 取出分类特征的值
    print('bestFeat:',bestFeat,'bestFeatLabel:',bestFeatLabel,'featValues:',featValues)
    uniqueVals = set(featValues)
    for value in uniqueVals:               # 对于该特征的不同值分别得到分类结果
        subLabels = labels[:]
        # 对于最优分类变量，分别计算该类别不同的值对应的最优分类结果；若该值对应同一分类，则返回该类别；
        #若无法分成一类，则对应不同的类别继续选择后续的类别进行分类，递归进行，直到分成同一类或者无法分成同一类而返回次数最多的累呗为止（终止条件）
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet,bestFeat,value),subLabels)  
        print('myTree:',myTree)
    return myTree

myData, labels = createDataSet()
myTree = createTree(myData, labels)
myTree

# 决策树可视化
# matplotlab 绘制决策树
# 3-5使用文本注解绘制树节点
import matplotlib.pyplot as plt

# 以下2行为为了显示中文设置
plt.rcParams['font.family'] = ['sans-serif']
plt.rcParams['font.sans-serif'] = ['SimHei']

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

def plotNode(nodeTxt, centerPt, parentPt, nodeType):   # 绘制带箭头的注释
    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():
    fig = plt.figure(1, facecolor="white")
    fig.clf()
    createPlot.ax1 = plt.subplot(111, frameon=False)
    plotNode("决策节点", (0.5,0.1), (0.1,0.5), decisionNode)
    plotNode("叶子结点", (0.8,0.1), (0.3,0.3), leafNode)
    plt.show()
    
createPlot()

# 3-6获取叶子节点数目和数的层级
def getNumleafs(myTree):
    numLeafs = 0
    firstStr = list(myTree.keys())[0]     #需要先转化为list
    secondDict = myTree[firstStr]
    for key in secondDict.keys():
        if type(secondDict[key]).__name__=='dict':   #测试节点的数据类型是是否为字典
            numLeafs += getNumleafs(secondDict[key])
        else:
            numLeafs += 1
    return numLeafs

def getTreeDepth(myTree):
    maxDepth = 0
    firstStr = list(myTree.keys())[0]   #需要先转化为list
    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

# 3-7 plottre函数
# 在父子节点间填充文本信息
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, nodeTxt):
    numLeafs = getNumleafs(myTree)
    depth = getTreeDepth(myTree)   #计算宽与高
    firstStr = list(myTree.keys())[0]
    cntrPt = (plotTree.xOff + (1.0 + float(numLeafs))/2.0/plotTree.totalW, plotTree.yOff)
    plotMidText(cntrPt, parentPt, nodeTxt)
    plotNode(firstStr, cntrPt, parentPt, decisionNode)
    secondDict = myTree[firstStr]
    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
    
def createPlot(inTree):
    fig = plt.figure(1, facecolor='white')
    fig.clf()
    axprops = dict(xticks=[], yticks=[])
    createPlot.ax1 = plt.subplot(111, frameon=False, **axprops)
    plotTree.totalW = float(getNumleafs(inTree))
    plotTree.totalD = float(getNumleafs(inTree))
    plotTree.xOff = -0.5/plotTree.totalW; plotTree.yOff = 1.0;
    plotTree(inTree, (0.5,1.0), '')
    plt.show()
      
# 使用决策树进行分类
# 3-8
def classify(inputTree, featLabels, testVec):
    firstStr = list(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