机器学习实践（III）决策树

决策树的构造

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( overfitting)问题。

试用数据范围

数值型和标称型。

---

信息增益：在划分数据集之前之后信息发生的变化。

符号 xi 的信息定义为

l(xi)=−log2p(xi)

其中 p(xi) 是选择该分类的概率

集合信息的度量方式称为 香农熵或者简称为 熵

H=−∑i=1np(xi)log2p(xi)

---

计算给定数据集的香农熵

from math import log
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

熵越高，则混合的数据越多

---

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

---

递归构建决策树

ID3算法

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

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]

---

用Matplotlib注解绘制树形图

import matplotlib.pyplot as plt

decisionNode = dict(boxstyle="sawtooth", fc="0.8")
leafNode = dict(boxstyle="round4", fc="0.8")
arrow_args = dict(arrowstyle="<-")


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 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 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
# 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 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]

---

使用决策树的分类算法

def classify(inputTree, featLabels, testVec):
    firstStr = inputTree.keys()[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

---

决策树的存储

在python中，一般可以使用pickle类来进行python对象的序列化，而cPickle提供了一个更快速简单的接口，如python文档所说的：“cPickle – A faster pickle”。
cPickle可以对任意一种类型的python对象进行序列化操作，比如list，dict，甚至是一个类的对象等。而所谓的序列化，我的粗浅的理解就是为了能够完整的保存并能够完全可逆的恢复。在cPickle中，主要有四个函数可以做这一工作，下面使用例子来介绍。
1 dump： 将python对象序列化保存到本地的文件。

 import cPickle
 data = range(1000)
cPickle.dump(data,open("test\\data.pkl","wb")) 

dump函数需要指定两个参数，第一个是需要序列化的python对象名称，第二个是本地的文件，需要注意的是，在这里需要使用open函数打开一个文件，并指定“写”操作。

2 load：载入本地文件，恢复python对象
data = cPickle.load(open("test\\data.pkl","rb"))
同dump一样，这里需要使用open函数打开本地的一个文件，并指定“读”操作

3 dumps：将python对象序列化保存到一个字符串变量中。
data_string = cPickle.dumps(data)

4 loads：从字符串变量中载入python对象
代码如下:
data = cPickle.loads(data_string)