关联分析（二）：Apriori算法的python实现

'''
@author: Peter
'''
from numpy import *
def loadDataSet():
    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))#use frozen set so we
                            #can use it as a key in a dict   
def scanD(D, Ck, minSupport):
    ssCnt = {}
    for tid in D:
        for can in Ck:
            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:
        support = ssCnt[key]/numItems
        if support >= minSupport:
            retList.insert(0,key)
        supportData[key] = support
    return retList, supportData
    
def aprioriGen(Lk, k): #creates 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: #if first k-2 elements are equal
                retList.append(Lk[i] | Lk[j]) #set union
    return retList
    
def apriori(dataSet, minSupport = 0.5):
    C1 = createC1(dataSet)
    D = list(map(set, dataSet))
    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)#scan DB to get Lk
        supportData.update(supK)
        L.append(Lk)
        k += 1
    return L, supportData
 

def generateRules(L, supportData, minConf=0.7):  #supportData is a dict coming from scanD
    bigRuleList = []
    for i in range(1, len(L)):#only get the sets with two or more items
        for freqSet in L[i]:
            H1 = [frozenset([item]) for item in freqSet]
            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):
    prunedH = [] #create new list to return
    for conseq in H:
        conf = supportData[freqSet]/supportData[freqSet-conseq] #calc confidence
        if conf >= minConf:
            print (freqSet-conseq,'-->',conseq,', conf:',conf)
            brl.append((freqSet-conseq, conseq, conf))
            prunedH.append(conseq)
    return prunedH
    
def rulesFromConseq(freqSet, H, supportData, brl, minConf=0.7):
    m = len(H[0])
    if (len(freqSet) > (m + 1)): #try further merging
        Hmp1 = aprioriGen(H, m+1)#create Hm+1 new candidates
        Hmp1 = calcConf(freqSet, Hmp1, supportData, brl, minConf)
        if (len(Hmp1) > 1):    #need at least two sets to merge
            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()       #print a blank line


dataset = loadDataSet()
print("dataset:", dataset,"\n")
#C1 = createC1(dataset)
#D = list(map(set, dataset))
#L1, suppData0 = scanD(D, C1, 0.75)
#print(L1)
#发现频繁项
ms = 0.5
L, suppData = apriori(dataset, minSupport =ms)
#查看所有项集的支持度
print("查看所有项集的支持度:")
#因为要做字典的键，所以使用frozenset，而不能使用普通的集合（因不可哈希）
for key, value in suppData.items():
    print(key,":", value)
print()
print("满足最小支持度%.2f的频繁项集："%ms)
for i,l in enumerate(L):
    print("%d -项集: "%(i+1))
    if len(l):
        for x in l:
            print(x)
    else: print(None)
print()

#发现关联规则
conf = 0.7
print("支持度不小于%.2f的频繁项集中,满足最小置信度%.2f的关联规则："%(ms,conf))
rules = generateRules(L, suppData, minConf = conf)