【读书笔记】机器学习实战-第三章 决策树

机器学习实战

决策树-隐形眼镜类型

• trees.py

#!/usr/bin/python
# -*- coding: utf-8 -*-
from math import log
import operator
import treePlotter

def calcShannonEnt(dataSet):  # 计算集合熵
    numEntires = len(dataSet)
    labelCounts = {}
    for featVec in dataSet:  # 统计频率
        currentLabel = featVec[-1]
        labelCounts[currentLabel] = labelCounts.get(currentLabel,0)+1  # dic.get()函数，访问不存在的键时，自动插入并设为默认值
    shannonEnt = 0.0
    for key in labelCounts.keys():  # 遍历字典，计算熵
        prob = float(labelCounts[key])/numEntires
        shannonEnt -= prob * log(prob, 2)  # log函数
    return shannonEnt

def createDataSet():  # 测试数据
    dataSet = [[1,1,'yes'],
               [1,1,'yes'],
               [1,0,'no'],
               [0,1,'no'],
               [0,1,'no']]
    labels = ['no surfacing','flippers']  # flippers: 脚蹼
    return dataSet, labels

def splitDataSet(dataSet, axis, value):    # 返回第axis特征值为value的列表
    retDataSet = []                         # 新对象，防止传入参数被修改
    for featVec in dataSet:                 # 寻找符合要求的值，添加到新列表中
        if featVec[axis] == value:
            reduceFeatVec = featVec[:axis]  # 除去第axis特征
            reduceFeatVec.extend(featVec[axis+1:])  # extend ：在列表末尾一次性添加另一个序列的多个值
            retDataSet.append(reduceFeatVec)        # 列表末尾添加源元素
    return retDataSet

def chooseBestFeatureToSplit(dataSet):
    numFeatures = len(dataSet[0])-1         # 特征个数
    baseEntropy = calcShannonEnt(dataSet)   # 计算原始集合熵
    bestInfoGain = 0.0 ;bestFeature = -1;   # 最优解记录
    for i in range(numFeatures):
        featList = [example[i] for example in dataSet]  # 列表推导式
        uniqueVals = set(featList)                       # 获取特征值取值范围
        newEntropy = 0.0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet, i, value)   # 获取被划分集合
            prob = len(subDataSet)/float(len(dataSet))     # 计算划分集合所占比例
            newEntropy += prob*calcShannonEnt(subDataSet)  # 计算熵
        infoGain = baseEntropy - newEntropy                # 计算信息增益
        if ( infoGain>bestInfoGain ):
            bestInfoGain = infoGain
            bestFeature = i
    return bestFeature

def majoryCnt(classList):  # 终止块的分类：多数表决 输入：类列表
    classCount = {}
    for vote in classList:
        classCount[vote] =classCount.get(vote, 0) + 1
    sortedClassCount = sorted(classCount.iteritems(), key = operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]

def createTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]         # 列表推导式：获取包含的所有类别
    if classList.count(classList[0]) == len(classList):      # [].count()：统计函数
        return classList[0]                                 # 叶子节点
    if len(dataSet[0]) == 1:
        return majoryCnt(classList)                         # 终止块
    bestFeat = chooseBestFeatureToSplit(dataSet)    # 确定分类特征
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel:{}}                     # 字典记录分类特征
    del(labels[bestFeat])                           # 从特征列表删除已分类特征
    featValues = [example[bestFeat] for example in dataSet]
    uniqueVals = set(featValues)                    # 获取特征所有取值范围
    for value in uniqueVals:
        subLabels = labels[:]
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet,bestFeat,value),subLabels)  # 递归子树
    return myTree

def classify(inputTree,featLabels,testVec):  # 使用决策树决策
    firstStr = inputTree.keys()[0]
    secondDict = inputTree[firstStr]
    featIndex = featLabels.index(firstStr)  # index: 获取当前特征的编号
    key = testVec[featIndex]
    valueOfFeat = secondDict[key]
    if isinstance(valueOfFeat, dict):
        classLabel = classify(valueOfFeat, featLabels, testVec)  # 递归
    else: classLabel = valueOfFeat
    return classLabel


def storeTree(inputTree, filename):  # 序列化对象
    import pickle
    fw = open(filename, 'w')
    pickle.dump(inputTree, fw)
    fw.close()


def grabTree(filename):
    import pickle
    fr = open(filename)
    return pickle.load(fr)

fr = open('lenses.txt')
lenses = [sample.strip().split('\t') for sample in fr.readlines()]  # 列表推导式
lensesLabels = ['age','prescript','astigmatic','tearRate']           # 特征
lensesTree = createTree(lenses,lensesLabels)                         # 建树
treePlotter.createPlot(lensesTree)                                   # 作图

#myDat, labels = createDataSet()
#tmp = createTree(myDat,labels)

#tmp = chooseBestFeatureToSplit(myDat)
#splitDataSet(myDat,0,0)

#tmp = calcShannonEnt(myDat)
#pass

• treePlotter.py

#!/usr/bin/python
# -*- coding: utf-8 -*-
import matplotlib.pyplot as plt

# 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="<-")

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():
    fig = plt.figure(1, facecolor= 'white')
    fig.clf()
    createPlot.ax1 = plt.subplot(111,frameon=False)  # 函数属性 可以在函数里面定义也可以在函数定义后加入也可以
    plotNode('decision node',(0.5,0.1),(0.1,0.5),decisionNode)
    plotNode('leaf node',(0.8,0.1),(0.3,0.8),leafNode)
    plt.show()

def getNumLeafs(myTree):
    numLeafs = 0
    firstStr = myTree.keys()[0]
    secondDict = myTree[firstStr]
    for key in secondDict.keys():
        if type(secondDict[key]).__name__=='dict':#test to see if the nodes are dictonaires, if not they are leaf nodes
            numLeafs += getNumLeafs(secondDict[key])
        else:   numLeafs +=1
    return numLeafs

def getTreeDepth(myTree):
    maxDepth = 0
    firstStr = myTree.keys()[0]
    secondDict = myTree[firstStr]
    for key in secondDict.keys():
        if type(secondDict[key]).__name__=='dict':#test to see if the nodes are dictonaires, if not they are leaf nodes
            thisDepth = 1 + getTreeDepth(secondDict[key])
        else:   thisDepth = 1
        if thisDepth > maxDepth: maxDepth = thisDepth
    return maxDepth

def retrieveTree(i):
    listOfTrees =[{'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 listOfTrees[i]

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, va="center", ha="center", rotation=30)

def plotTree(myTree, parentPt, nodeTxt):#if the first key tells you what feat was split on
    numLeafs = getNumLeafs(myTree)  #this determines the x width of this tree
    depth = getTreeDepth(myTree)
    firstStr = myTree.keys()[0]     #the text label for this node should be this
    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':#test to see if the nodes are dictonaires, if not they are leaf nodes
            plotTree(secondDict[key],cntrPt,str(key))        #recursion
        else:   #it's a leaf node print the leaf node
            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)    #no ticks
    #createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses
    plotTree.totalW = float(getNumLeafs(inTree))
    plotTree.totalD = float(getTreeDepth(inTree))
    plotTree.xOff = -0.5/plotTree.totalW; plotTree.yOff = 1.0;
    plotTree(inTree, (0.5,1.0), '')
    plt.show()

#createPlot()