python机器学习实战2：实现决策树

1.决策树的相关知识

在之前的接触中决策树直观印象应该就是if-else的循环，if会怎么样，else之后再继续if-else直至最终的结果。在上节讲的kNN它其实已经可以完成很多任务，但是它最大的缺点就是无法给数据集的内在含义，决策树的主要优势在于数据形式非常容易理解。

我们来对决策树进行一个总的概括，然后对程序进行解释。优点：计算复杂度不高，输出结果易于理解，对中间值的缺失不敏感，可以处理不相关特征数据。缺点：可能会产生过度匹配的问题。适用数据类型：数值型和标称型。

标称型：标称型目标变量的结果只在有限目标集中取值，如真与假(标称型目标变量主要用于分类)

数值型：数值型目标变量则可以从无限的数值集合中取值，如0.100，42.001等 (数值型目标变量主要用于回归)

2.信息增益

讲到信息增益，或者信息论也总会提到一个名人克劳德 · 香农，集合信息度量方式称为香农熵或者简称为熵，这个名字就是来源于信息之父香农。（其实，我这里会有一个经验的分享啦，就是在学习过程中，经常会遇到一些之前从来没有听过的名词或者专业术语，文人之间的咬文嚼字真的我是很无感的，但是理工科是以严谨和细致著称的，所以看论文或书籍的时候经常看到没听过的词，这时候可千万不要放弃或者烦操，看一下公式或者解释，也许会豁然开朗，不过是名字罢了，追根究底有可能只是一行公式）

熵定义为信息的期望值，在明晰这个概念之前，我们必须明白信息的定义。如果待分类的事物可能划分在多个分类之中，则符号$x_i$的信息定义为如下所示：

$l(x_i) = -log_2 p(x_i)$

其中$p(x_i)$是选择该分类的概率。

为了计算熵，我们需要计算所有类别可能值包含的信息期望值，通过下面的公式得到:

$H=-\sum_{i=1}^n p(x_i)log_2 p(x_i)$

是不是看到熵，心里就一颤，莫名的烦躁呢。。。也有可能只有LZ是这样的，但是如果静下心来，会发现只是个代号，内容还是比较平易近人的哈。

3.决策树的代码实现
这里主要有两个.py文件。
第一个是trees.py，代码如下：

#coding:utf-8
#导入一些操作符

from math import log
import operator

#创建一个简单的数据集
def createDataSet():
    dataSet = [[1, 1, 'yes'],
               [1, 1, 'yes'],
               [1, 0, 'no'],
               [0, 1, 'no'],
               [0, 1, 'no']]
    labels = ['no surfacing','flippers']
    #change to discrete values
    return dataSet, labels

#计算给定数据集的香农熵
def calcShannonEnt(dataSet):
    numEntries = len(dataSet)
    labelCounts = {}
    for featVec in dataSet: #the the number of unique elements and their occurance
        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) #log base 2
    return shannonEnt

#按照给定特征划分数据集    
def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]     #chop out axis used for splitting
            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      #the last column is used for the labels
    baseEntropy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0; bestFeature = -1
    for i in range(numFeatures):        #iterate over all the features
        featList = [example[i] for example in dataSet]#create a list of all the examples of this feature
        uniqueVals = set(featList)       #get a set of unique values
        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     #calculate the info gain; ie reduction in entropy
        if (infoGain > bestInfoGain):       #compare this to the best gain so far
            bestInfoGain = infoGain         #if better than current best, set to best
            bestFeature = i
    return bestFeature                      #returns an integer

#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.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]#stop splitting when all of the classes are equal
    if len(dataSet[0]) == 1: #stop splitting when there are no more features in dataSet
        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[:]       #copy all of labels, so trees don't mess up existing labels
        myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet, bestFeat, value),subLabels)
    return myTree                            

#使用决策树执行分类    
def classify(inputTree,featLabels,testVec):
    #python2
    # firstStr = inputTree.keys()[0]
    #python3.5
    firstSides = list(inputTree.keys())
    firstStr = firstSides[0]

    secondDict = inputTree[firstStr]
    featIndex = featLabels.index(firstStr)
    key = testVec[featIndex]
    valueOfFeat = secondDict[key]
    if isinstance(valueOfFeat, dict): 
        classLabel = classify(valueOfFeat, featLabels, testVec)
    else: classLabel = valueOfFeat
    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)

第二个主要是绘制决策树图treePlotter.py

#coding:utf-8

#导入matplotlib.pyplot,如果显示mo module,请自行安装
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="<-")

#获取叶节点数
def getNumLeafs(myTree):
    numLeafs = 0
    #如果使用的是python2，用注释掉的一行
    # firstStr = myTree.keys()[0]


    #LZ使用的是python3
    firstSides = list(myTree.keys())
    firstStr = firstSides[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

#获取树的层数
def getTreeDepth(myTree):
    maxDepth = 0
    #python2的用法
    # firstStr = myTree.keys()[0]

    #python3使用下面两行
    firstSides = list(myTree.keys())
    firstStr = firstSides[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

#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 )

#在父子节点填充文本信息    
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, va="center", ha="center", rotation=30)

#plotTree函数
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)
    #python2
    # firstStr = myTree.keys()[0]     #the text label for this node should be this
    #python3
    firstSides = list(myTree.keys())
    firstStr = firstSides[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':#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
#if you do get a dictonary you know it's a tree, and the first element will be another dict

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()

#def createPlot():
#    fig = plt.figure(1, facecolor='white')
#    fig.clf()
#    createPlot.ax1 = plt.subplot(111, frameon=False) #ticks for demo puropses 
#    plotNode('a decision node', (0.5, 0.1), (0.1, 0.5), decisionNode)
#    plotNode('a leaf node', (0.8, 0.1), (0.3, 0.8), leafNode)
#    plt.show()

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]

#createPlot(thisTree)

这里贴出代码和代码配套的数据集，有兴趣的小伙伴可以自行下载。链接: https://pan.baidu.com/s/1gf664dP 密码: 32r5
需要注意的是因为LZ笔记本上装的是python3.5，为了确保代码编译成功，把原本的python2版本的代码改了一部分，注释里都有，小伙伴可以根据自己的需求进行选择O(∩_∩)O