Apriori代码

from numpy import *def loadDataSet():#简单的测试数据集

return [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]def createC1(dataSet):

C1 = [] for transaction in dataSet:

for item in transaction:

if not [item] in C1:

C1.append([item])

C1.sort()

return list(map(frozenset, C1))#frozenset一经创建不可修改。所以C1为每个项构建了一个不变的集合。而且这个集合可以当键值使用，而set是做不到的。def scanD(D, Ck, minSupport):#包含候选集合的列表，数据集CK，最小支持度（包含该项集） ssCnt = {} for tid in D:#遍历候选集 for can in Ck:#遍历数据集的所有交易记录 if can.issubset(tid): if can not in ssCnt: ssCnt[can]=1 else: ssCnt[can] += 1 numItems = float(len(D)) retList = [] supportData = {} for key in ssCnt:#计算所有项集支持度 support = ssCnt[key]/numItems if support >= minSupport: retList.insert(0,key) supportData[key] = support return retList, supportDatadef aprioriGen(Lk, k): #输入频繁集列表和项集元素，输出CK retList = [] lenLk = len(Lk) for i in range(lenLk): for j in range(i+1, lenLk): L1 = list(Lk[i])[:k-2]; L2 = list(Lk[j])[:k-2] L1.sort(); L2.sort() if L1==L2: #前k-2相同时合并集合。用k-2使遍历次数最少 retList.append(Lk[i] | Lk[j]) return retListdef apriori(dataSet, minSupport = 0.5): C1 = createC1(dataSet) D = list(map(set, dataSet))#将set（）映射到dataSet列表中的每一项

L1, supportData = scanD(D, C1, minSupport)

L = [L1] k = 2 while (len(L[k-2]) > 0):

Ck = aprioriGen(L[k-2], k)

Lk, supK = scanD(D, Ck, minSupport)

supportData.update(supK)

L.append(Lk)

k += 1 return L, supportDatadef generateRules(L, supportData, minConf=0.7):#从频繁项中挖掘关联规则。频繁项集列表，包含哪些频繁项集支持数据的字典，最小可信度阈值 bigRuleList = []#规则 for i in range(1, len(L)):#只获取有两个或者更多元素的集合（单个无法建立规则） for freqSet in L[i]:

H1 = [frozenset([item]) for item in freqSet]#只含单个元素的列表H1

if (i > 1):

rulesFromConseq(freqSet, H1, supportData, bigRuleList, minConf)

else: calcConf(freqSet, H1, supportData, bigRuleList, minConf)

return bigRuleList

def calcConf(freqSet, H, supportData, brl, minConf=0.7):#评估规则

prunedH = [] for conseq in H:

conf = supportData[freqSet]/supportData[freqSet-conseq]

if conf >= minConf:

print (freqSet-conseq,'-->',conseq,'conf:',conf)

brl.append((freqSet-conseq, conseq, conf))

prunedH.append(conseq)

return prunedHdef rulesFromConseq(freqSet, H, supportData, brl, minConf=0.7):#生成候选规则集合

m = len(H[0]) if (len(freqSet) > (m + 1)): #尝试进一步合并

Hmp1 = aprioriGen(H, m+1)#创造Hm+1条新候选规则

Hmp1 = calcConf(freqSet, Hmp1, supportData, brl, minConf)

if (len(Hmp1) > 1):

rulesFromConseq(freqSet, Hmp1, supportData, brl, minConf)def pntRules(ruleList, itemMeaning):

for ruleTup in ruleList:

for item in ruleTup[0]:

print (itemMeaning[item])

print (" -------->")

for item in ruleTup[1]:

print (itemMeaning[item])

print ("confidence: %f" % ruleTup[2])

print()dataSet=loadDataSet()L,suppData=apriori(dataSet,minSupport=0.5)print(L)print(suppData)rules=generateRules(L,suppData,minConf=0.7)print(rules)