第1关：创建数据集
def createDataSet():dataSet = [[1, 1, 'yes'],[1, 1, 'yes'],[1, 0, 'no'],[0, 1, 'no'],[0, 1, 'no']]labels = ['no surfacing','flippers']return dataSet, labels
####请在此处输入代码####
myDat, t = createDataSet()
#######################
print(myDat)
第2关：计算数据集的信息熵
from math import log
import operator
def calcShannonEnt(dataSet):numEntries = len(dataSet) #声明数据集中样本总数labelCounts = {} #创建字典for featVec in dataSet: #所有可能分类的数量和发生频率currentLabel = featVec[-1]if currentLabel not in labelCounts.keys(): labelCounts[currentLabel] = 0labelCounts[currentLabel] += 1shannonEnt = 0.0for key in labelCounts:prob = float(labelCounts[key])/numEntriesshannonEnt -= prob * log(prob,2) #log base 2return shannonEnt
第3关：数据集的划分
def splitDataSet(dataSet, axis, value):retDataSet = [] #创建列表对象引用数据集，防止由于多次调用而改变元数据集。####请在此处输入代码####for i in dataSet:if i[axis] == value:t = i[:axis]t.extend(i[axis + 1:])retDataSet.append(t)#######################return retDataSet
第4关：计算信息增益
from ex03_lib import calcShannonEnt,splitDataSetdef chooseBestFeatureToSplit(dataSet):numFeatures = len(dataSet[0]) - 1 #最后一个元素是当前实例的类别标签。baseEntropy = calcShannonEnt(dataSet) #计算原始信息熵。bestInfoGain = 0.0; bestFeature = -1for i in range(numFeatures): #遍历数据集中所有特征。featList = [example[i] for example in dataSet]#create a list of all the examples of this featureuniqueVals = set(featList) #创建唯一的分类标签列表。newEntropy = 0.0####请在此处输入代码####for value in uniqueVals: #遍历当前特征中所有唯一的特征值。subDataSet = splitDataSet(dataSet, i, value)prob = len(subDataSet)/float(len(dataSet))newEntropy += prob * calcShannonEnt(subDataSet) #计算每种划分方式的信息熵。 infoGain = baseEntropy - newEntropy #计算信息增益。#######################if (infoGain > bestInfoGain): #将结果与目前所得到的最优划分进行比较。bestInfoGain = infoGain #如果结果优于当前最优化分特征，则更新划分特征。bestFeature = ireturn bestFeature #返回最优划分的索引值。
