《机器学习实战》

决策树预测隐形眼镜类型

# -*- coding: utf-8 -*-
# @Time    : 2021/6/21 12:59
# @Author  : weiwei
# @File    : LensType.py
from math import log
import operator
import matplotlib.pyplot as plt


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


def splitDataSet(dataSet, axis, value):
    retDataSet = []
    for featVec in dataSet:

        if featVec[axis] == value:
            reducedFeatVec = featVec[:axis]

            reducedFeatVec.extend(featVec[axis + 1:])

            retDataSet.append(reducedFeatVec)

    return retDataSet


def chooseBestFeatureToSplit(dataSet):
    numFeatures = len(dataSet[0]) - 1
    baseEntropy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0
    bestFeature = -1
    for i in range(numFeatures):
        featList = [example[i] for example in dataSet]

        uniqueVals = set(featList)
        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
        if (infoGain > bestInfoGain):
            bestInfoGain = infoGain
            bestFeature = i
    return bestFeature


def majorityCnt(classList):
    classCount = {}
    for vote in classList:
        if vote not in classCount.keys():
            classCount[vote] = 0
        classCount[vote] += 1
    sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True)
    return sortedClassCount[0][0]


def createTree(dataSet, labels):
    classList = [example[-1] for example in dataSet]
    if classList.count(classList[0]) == len(classList):
        return classList[0]
    if len(dataSet[0]) == 1:
        return majorityCnt(classList)
    bestFeat = chooseBestFeatureToSplit(dataSet)
    bestFeatLabel = labels[bestFeat]
    myTree = {bestFeatLabel: {}}
    # print("0tree", myTree)
    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 getNumLeafs(myTree):
    numLeafs = 0

    temp_keys = list(myTree.keys())
    firstStr = temp_keys[0]
    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 = next(iter(myTree))
    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 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]


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 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):
    numLeafs = getNumLeafs(myTree)
    depth = getTreeDepth(myTree)
    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(getTreeDepth(inTree))
    plotTree.xOff = -0.5 / plotTree.totalW
    plotTree.yOff = 1.0

    plotTree(inTree, (0.5, 1.0), '')
    plt.show()


def prodict():
    with open("lenses.txt", "rb") as fr:
        lenses = [inst.decode().strip().split('\t') for inst in fr.readlines()]
    lensesLabels = ['age', 'prescript', 'astigmatic', "tearRate"]
    lensesTree = createTree(lenses, lensesLabels)
    createPlot(lensesTree)
    return lensesTree


def classify(inputTree, featLabels, testVec):
    firstStr = list(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


if __name__ == "__main__":
    mytree = prodict()
    labels = ['age', 'prescript', 'astigmatic', "tearRate"]
    result = classify(mytree, labels, ["presbyopic", "hyper", "yes", "normal"])
    if result == 'no lenses':
        print("视力良好")
    if result == 'soft':
        print("轻微近视")
    if result == 'hard':
        print("重度近视")

lenses.txt

young	myope	no	reduced	no lenses
young	myope	no	normal	soft
young	myope	yes	reduced	no lenses
young	myope	yes	normal	hard
young	hyper	no	reduced	no lenses
young	hyper	no	normal	soft
young	hyper	yes	reduced	no lenses
young	hyper	yes	normal	hard
pre	myope	no	reduced	no lenses
pre	myope	no	normal	soft
pre	myope	yes	reduced	no lenses
pre	myope	yes	normal	hard
pre	hyper	no	reduced	no lenses
pre	hyper	no	normal	soft
pre	hyper	yes	reduced	no lenses
pre	hyper	yes	normal	no lenses
presbyopic	myope	no	reduced	no lenses
presbyopic	myope	no	normal	no lenses
presbyopic	myope	yes	reduced	no lenses
presbyopic	myope	yes	normal	hard
presbyopic	hyper	no	reduced	no lenses
presbyopic	hyper	no	normal	soft
presbyopic	hyper	yes	reduced	no lenses
presbyopic	hyper	yes	normal	no lenses

书上内容相关文件也可访问machine-learning