数据挖掘习题之决策树算法

根据processed.cleveland.data数据进行数据挖掘操作
UCI公开数据集-heartdisease，属性信息如下：
1.#3(age)
2.#4(sex)
3.#9(cp)
4.#10(trestbps)
5.#12(chol)
6.#16(fbs)
7.#19(restecg)
8.#32(thalach)
9.#38(exang)
10.#40(oldpeak)
11.#41(slope)
12.#44(ca)
13.#51(thal)
14.#58(num)(thepredictedattribute)
数据集参考网址：https://archive.ics.uci.edu/ml/datasets/Heart+Disease

import math 
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 key in labelCounts:
        prob = float(labelCounts[key])/numEntries
        shannonEnt -= prob*math.log(prob, 2)
    return shannonEnt
     
def CreateDataSet():
    #字符串转化浮点数
    def safe_float(number):
        try:
            return float(number)
        except:
            return None
    #读取数据
    dataset=[]
    with open('processed.cleveland.data') as read_file:
        for line in read_file:
            line=line.replace('\n','').split(',')
            line=list(map(safe_float,line))
            dataset.append(line)
    labels = ['age','sex','cp','trestbps','chol','fbs','restecg','thalach','thalach','exang','oldpeak','slope','ca','thal','num']
    return dataset, labels
 
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 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]
  
def chooseBestFeatureToSplit(dataSet):
    numberFeatures = len(dataSet[0])-1
    baseEntropy = calcShannonEnt(dataSet)
    bestInfoGain = 0.0;
    bestFeature = -1;
    for i in range(numberFeatures):
        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 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:{}}
    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
 
         
         
MyData,label = CreateDataSet()

#决策树ID3
createTree(MyData,label)

运行结果：