关联规则Apriori

                              首先介绍的是啤酒和尿布的故事（上网自查），这是学习关联规则必须知道的一个故事。

                              频繁项集，关联规则，支持度，置信度这四个概念贯穿Apriori算法的始终。

                              如果一个集合不是频繁相集，那它的超集比然也不是频繁相集。

机器学习实战例子：

#coding:utf-8
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 map(frozenset,c1)

>>> D=apriori.loadDataSet()
>>> C=apriori.createC1(D)
>>> print C
[frozenset([1]), frozenset([2]), frozenset([3]), frozenset([4]), frozenset([5])]

                         获得集合中组成元素

def scanD(D, Ck, minSupport):
    ssCnt = {}
    for tid in D:
        for can in Ck:
            if can.issubset(tid):
                if not ssCnt.has_key(can): 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 求两个集合的合并
    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 = 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)      #每次循环合并成两项集，三项集....
        Lk, supK = scanD(D, Ck, minSupport)#scan DB to get Lk
        supportData.update(supK)
        L.append(Lk)
        k += 1
    return L, supportData

>>> L,suppData=apriori.apriori(D)     
>>> print L
[[frozenset([1]), frozenset([3]), frozenset([2]), frozenset([5])], [frozenset([1, 3]), frozenset([2, 5]), frozenset([2, 3]), frozenset([3, 5])], [frozenset([2, 3, 5])], []]
>>> print suppData
{frozenset([5]): 0.75, frozenset([3]): 0.75, frozenset([2, 3, 5]): 0.5, frozenset([1, 2]): 0.25, frozenset([1, 5]): 0.25, frozenset([3, 5]): 0.5, frozenset([4]): 0.25, frozenset([2, 3]): 0.5, frozenset([2, 5]): 0.75, frozenset([1]): 0.5, frozenset([1, 3]): 0.5, frozenset([2]): 0.75}

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):
    print "#H#",H
    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)

>>> rules=apriori.generateRules(L,suppData,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
#H# [frozenset([2]), frozenset([3]), frozenset([5])]
frozenset([5]) --> frozenset([2, 3]) conf: 0.666666666667
frozenset([3]) --> frozenset([2, 5]) conf: 0.666666666667
frozenset([2]) --> frozenset([3, 5]) conf: 0.666666666667
#H# [frozenset([2, 3]), frozenset([2, 5]), frozenset([3, 5])]