《机器学习实战》--决策树

机器学习实战第三章python3的实现及注释
trees.py

from math import log
import operator

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 keys in labelCounts:
        prob = float(labelCounts[keys]) / numEntries
        shannonEnt -= prob * log(prob, 2)
    return shannonEnt


def createDataSet():
    dataSet = [[1, 1, 'yes'],
               [1, 1, 'yes'],
               [1, 0, 'no'],
               [0, 1, 'no'],
               [0, 1, 'no']]
    labels = ['no surfacing', 'flippers']
    return dataSet, labels


def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:
        if featVec[axis] == value:
            reduceFeatVec = featVec[:axis]
            reduceFeatVec.extend(featVec[axis + 1:])  # 去除包含axis数据集中中的axis值
            retDataSet.append(reduceFeatVec)
    return retDataSet


def chooseBestFeatureToSplit(dataSet):# 返回最佳类别的序号
    numFeature = len(dataSet[0]) - 1
    baseEntropy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0
    bestFeature = -1
    for i in range(numFeature):
        featList = [example[i] for example in dataSet]# 去example中的i列元素
        uniqueVals = set(featList)  # 重复的删除
        newEntroy = 0.0
        for value in uniqueVals:
            subDataSet = splitDataSet(dataSet, i, value)
            prob = len(subDataSet) / float(len(dataSet))
            newEntroy += prob * calcShannonEnt(subDataSet)
        infoGain = baseEntropy - newEntroy
        if infoGain > bestInfoGain:
            bestInfoGain = infoGain
            bestFeature = i
    return bestFeature

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

def CreateTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]# 取其最后一列
    if classList.count(classList[0]) == len(classList):# 类列表中第一个元素的个数等于类列表数，则返回第一个元素
        return classList[0]
    if len(dataSet[0]) == 1:# 若每个元素长度为零，则返回出现最多的元素
        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[:]
        myTree[bestFeatLabel][value] = CreateTree(splitDataSet(dataSet, bestFeat, value), subLabels)
    return myTree

def classify(inputTree, featLabels, testVec):
    firstStr = list(inputTree.keys())[0]# 取字典中的第一个key值
    secondDist = inputTree[firstStr]
    featIndex = featLabels.index(firstStr)# 取label的下标
    key = testVec[featIndex]# 获得label下标的对应值
    valueOfFeat = secondDist[key]# 求属于那个子树
    if isinstance(valueOfFeat, dict):
        classLabel = classify(valueOfFeat, featLabels, testVec)
    else:
        classLabel = valueOfFeat
    return classLabel

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)

treesPlot.py

import matplotlib.pyplot as plt

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)
#     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 getNumLeafs(myTree):
    numLeafs = 0
    firstStr = list(myTree.keys())[0]# 需要将字典转换为列表
    secondDict = myTree[firstStr]
    for key in secondDict.keys():
        if type(secondDict[key]).__name__ == 'dict':
            numLeafs += getNumLeafs(secondDict[key])
        else:
            numLeafs += 1
    return numLeafs

def getTreeDepth(myTree):
    maxDepth = 0
    firstStr = list(myTree.keys())[0]# 需要将字典转换为列表
    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

# def retriveTree(i):
#     listOfTree = {'no surfacing': {0: 'no', 1: {'flippers': {0: 'no', 1: 'yes'}}}}
#     return listOfTree(i)

def plotMidText(cntrPt, parentPr, txtString):
    xMid = (parentPr[0] - cntrPt[0]) / 2.0 + cntrPt[0]
    yMid = (parentPr[1] - cntrPt[1]) / 2.0 + cntrPt[1]
    createPlot.ax1.text(xMid, yMid, txtString, va="center", ha="center", rotation=30)

def plotTree(myTree, parentPr, nodeTxt):
    numleafs = getTreeDepth(myTree)
    depth = getTreeDepth(myTree)
    firstStr = list(myTree.keys())[0]
    cntrPt = (plotTree.xOff + (1.0 + float(numleafs))/2.0/plotTree.totalW, plotTree.yOff)
    plotMidText(cntrPt, parentPr, nodeTxt)
    plotNode(firstStr, cntrPt, parentPr, 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(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]

treesPlot.py代码理解参考：
https://www.cnblogs.com/fantasy01/p/4595902.html