【人工智能】机器学习之使用Python生成ID3决策树

❤❤❤ID3算法

:white_check_mark::white_check_mark:决策树的思想：

给定一个集合，其中的每个样本由若干属性表示，决策树通过贪心的策略不断挑选最优的属性。 常见的决策树算法有ID3,C4.5,CART算法等。

:zzz::zzz::zzz:ID3算法：

baseEntropy = self.calcShannonEnt(dataset) # 基础熵 num = len(dataset) # 样本总数 #子集中的概率 subDataSet = self.splitDataSet(dataset, i, val) prob = len(subDataSet) / float(num) # 条件熵 newEntropy += prob * self.calcShannonEnt(subDataSet) # 信息增益 infoGain = baseEntropy - newEntropy

:100:1.先写绘图树方法，函数。

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 getNumLeafs(myTree):
    numLeafs = 0
    firstStr = list(myTree.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 = list(myTree.keys())[0]
    secondDict = myTree[firstStr]
    for key in secondDict.keys():
        if type(secondDict[key]).__name__ == 'dict':
            thisDepth = getTreeDepth(secondDict[key]) + 1
        else:
            thisDepth = 1
        if thisDepth > maxDepth:
            maxDepth = thisDepth
    return maxDepth

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)

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__ =