def createC1(dataset):
    C1=[]
    for transaction in dataset:
        for item in transaction:
            if not [item] in C1:#如果不在項(xiàng)集中
                C1.append([item])
    C1.sort()
    #可以作為key值
    return map(frozenset,C1)#每個(gè)元素是一個(gè)frozenset
#滿足要求的構(gòu)成L1,然后L1組合成為C2。進(jìn)一步過濾成為L2
#frozenset可以作為key值
def scanD(D,Ck,minSupport):
    #先在記錄中查看所有候選集的次數(shù)
    ssCnt = {}
    for td in D:
        for can in Ck:
            if can.issubset(td):#如果是那個(gè)集合的子集
                if not ssCnt.has_key(can):ssCnt[can]=1
                else:ssCnt[can]+=1
    numCount = len(D)#記錄的總數(shù)
    #記錄每個(gè)項(xiàng)集的支持度
    supportData={}
    retList=[]
    for key in ssCnt.iterkeys():
        support = float(ssCnt[key]*1.0/numCount)
        if support>=minSupport:
            retList.insert(0,key)#加入滿足條件的項(xiàng)集合的序列
        supportData[key] = support
    return retList,supportData
 

x = apriori.loadDataSet()
C1 = apriori.createC1(x)#frozenset每個(gè)元素
print C1
#構(gòu)建事物集
D = map(set,x)#每個(gè)元素是集合
L1,supportData0 = apriori.scanD(D,C1,0.5)
print L1

#前面K-1x項(xiàng)目相同的時(shí)候可以生成Lk
def aprioriGen(Lk,k):
    #前面k-1項(xiàng)目相同就可以合成
    retList = []
    lenLk = len(Lk)
    for i in range(lenLk):
        for j in range(i+1,lenLk):
            L1 = list(Lk[i])[:k-2]#可以考慮1個(gè)元素的時(shí)候是0直接合并
            L2 = list(Lk[j])[:k-2]
            L1.sort()
            L2.sort()
            if L1==L2:
                retList.append(Lk[i]|Lk[j])
    return retList
def apriori(dataset,minSupport=0.5):
    C1 = createC1(dataset)
    D = map(set,dataset)
    L1,supportData = scanD(D,C1,minSupport)
    L = [L1]
    k = 2#項(xiàng)集為2
    #頻繁n-1項(xiàng)目總數(shù)為
    while(len(L[k-2])>0):#因?yàn)轫?xiàng)集存的位置是0
        Ck = aprioriGen(L[k-2],k)
        Lk,supK = scanD(D,Ck,minSupport)
        supportData.update(supK)#加入字典更新
        L.append(Lk)#L+1
        k+=1#當(dāng)空集的時(shí)候退出
    return L,supportData

dataSet = apriori.loadDataSet()
L,supportData = apriori.apriori(dataSet,minSupport=0.7)
print L

#規(guī)則生成函數(shù)
def generateRules(L,supportData,minConf=0.7):
    bigRuleList=[]
    for i in range(1,len(L)):#只獲取兩個(gè)或者更多的頻繁項(xiàng)集合
        for freqSet in L[i]:
            H1 = [frozenset([item]) for item in freqSet]#將每個(gè)元素拆出來這個(gè)是右邊被推出的項(xiàng)集
            if (i>1):
                rulesFromConseq()
            else:
                calcConf(freqSet,H1,supportData,bigRuleList,minConf)
    return bigRuleList
#計(jì)算可信度
def calcConf(freqSet,H,supportData,brl,minConf=0.7):
    prunedH = []
    for conseq in H:
        conf = supportData[freqSet]/supportData[freqSet-conseq]#獲得條件概率（freq-conseq) -> conseq
        if conf>=minConf:
            print freqSet-conseq,'--->',conseq,'conf:',conf
            brl.append((freqSet-conseq,conseq,conf))#加入這個(gè)元祖
            prunedH.append(conseq)#為后面準(zhǔn)備。因?yàn)槿舨粷M足規(guī)則右邊該元素基礎(chǔ)下添加也不會滿足
    return prunedH
#最初的規(guī)則生成更多的規(guī)則
def rulesFromConseq(freqSet,H,supportData,brl,minConf=0.7):
    m = len(H[0])
    if (len(freqSet)>(m+1)):#一直到該頻繁項(xiàng)集能包含的右邊推出等于項(xiàng)的個(gè)數(shù)-1為止例如{1，2，3，4}當(dāng){1}-{2,3,4}以后此時(shí)H[0]長度為3
        Hmp1 = aprioriGen(H,m+1)#右邊推出過程類似生成過程
        Hmp1 = calcConf(freqSet,Hmp1,supportData,brl,minConf)#過濾過程返回被推出的右邊的項(xiàng)集的集合
        if (len(Hmp1)>1):#若有新規(guī)則生成繼續(xù)遞歸處理
            rulesFromConseq(freqSet,Hmp1,supportData,brl,minConf)

#生成所有頻繁項(xiàng)集合
dataSet = apriori.loadDataSet()
L,supportData =  apriori.apriori(dataSet,minSupport=0.5)
#生成規(guī)則
rules = apriori.generateRules(L,supportData,minConf=0.5)

frozenset([3]) ---> frozenset([1]) conf: 0.666666666667
frozenset([1]) ---> frozenset([3]) conf: 1.0
frozenset([5]) ---> frozenset([2]) conf: 1.0
frozenset([2]) ---> frozenset([5]) conf: 1.0
frozenset([3]) ---> frozenset([2]) conf: 0.666666666667
frozenset([2]) ---> frozenset([3]) conf: 0.666666666667
frozenset([5]) ---> frozenset([3]) conf: 0.666666666667
frozenset([3]) ---> frozenset([5]) conf: 0.666666666667
frozenset([5]) ---> frozenset([2, 3]) conf: 0.666666666667
frozenset([3]) ---> frozenset([2, 5]) conf: 0.666666666667
frozenset([2]) ---> frozenset([3, 5]) conf: 0.666666666667

#只保留包含投票數(shù)據(jù)的actionId
def getActionIds():
    fr = open('recent20bills.txt')
    actionIdList=[];billTitleList=[]
    for line in fr.readlines():
        billNum = int(line.split('\t')[0])
        try:
            billDetail = votesmart.votes.getBill(billNum)#獲取議案對象
            for action in billDetail.actions:
                if action.level=='House' and \
                        (action.stage=='Passage' or \
                         action.stage=='Amendment Vote'):
                    actionId = int(action.actionId)
                    actionIdList.append(actionId)
                    billTitleList.append(line.strip().split('\t')[1])
        except:
            print "problem gettin bill %d"%billNum
        sleep(1)
    return actionIdList,billTitleList

#基于投票數(shù)據(jù)的事物列表填充函數(shù)
def getTransList(actionIdList,billTitleList):
    itemMeaning = ['Republican','Democratic']
    for billTitle in billTitleList:
        itemMeaning.append('%s -- Nay'%billTitle)
        itemMeaning.append('%s -- Yea' % billTitle)
    #創(chuàng)建事務(wù)字典
    transDict = {}
    voteCount = 2# 0,1是所屬黨派。2開始是被第幾次投票
    for actionId in actionIdList:
        sleep(3)
        print 'getting votes for actionId: %d' %actionId
        try:
            voteList = votesmart.votes.getBillActionVotes(actionId)
            for vote in voteList:
                if not transDict.has_key(vote.candidateName):
                    transDict[vote.candidateName] = []
                    if vote.officeParties =='Democratic':
                        transDict[vote.candidateName].append(1)
                    elif vote.officeParties=='Republican':
                        transDict[vote.candidateName].append(0)
                    if vote.action=='Nay':
                        transDict[vote.candidateName].append(voteCount)
                    elif vote.action=='Yea':
                        transDict[vote.candidateName].append(voteCount+1)
        except:
            print "problem getting actionId:%d" %actionId
        voteCount+=2
    return transDict,itemMeaning

Prohibiting Federal Funding of National Public Radio -- Yea
           -------->
Republican
Repealing the Health Care Bill -- Yea
confidence: 0.995614

mushDatSet = [line.split() for line in  open('mushroom.dat').readlines()]
L,suppData = apriori.apriori(mushDatSet,minSupport=0.3)
#尋找毒的公共特征
for item in L[1]:
    if item.intersection('2'):print item

frozenset(['2', '59'])
frozenset(['39', '2'])
frozenset(['2', '67'])
frozenset(['2', '34'])
frozenset(['2', '23'])
frozenset(['2', '86'])
frozenset(['76', '2'])
frozenset(['90', '2'])
frozenset(['2', '53'])
frozenset(['93', '2'])
frozenset(['63', '2'])
frozenset(['2', '28'])
frozenset(['2', '85'])
frozenset(['2', '36'])