Apriori关联算法

1.算法核心思想：Apriori算法实际上是关联规则的学习过程

2.首先要弄清楚两个指标：支持度、置信度

事件A发生的概率P(A)即为A的支持度

事件A、B同时发生的概率P(A,B)为AB的支持度

事件A发生导致事件B发生的概率P(A,B)/P(A)为A——>B这条规则的置信度，置信度是针对规则而言的

3.Apriori原理：如果某个项集是频繁的，那么它的所有子集也是频繁的；反过来看，也就是说如果一个项集是非频繁集，那么它的所有超集也是非频繁的，那么我们就可以在筛选过程中逐步去掉非频繁集，从而大大减少计算量。

4.算法伪代码：

（1）生成频繁项集列表

生成单元素项集

while 集合中项的个数大于0

构建一个k个项组成的候选项集的列表

从候选项集中筛选出频繁项集

k<——k+1

（2）生成关联规则

python代码实现：

# -*- coding:utf8 -*-

# 创建数据集
def createDataSet():
    return [[1,3,4], [2,3,5], [1,2,3,5], [2,5]]

# 生成单元素项集
def createC1(dataSet):
    C1 = []
    for data in dataSet:
        for item in data:
            if not [item] in C1:
                C1.append([item])
    C1.sort()
    return map(frozenset, C1) 

# 从候选集中筛选频繁集
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.append(key)
            supportData[key] = support
    return retList, supportData

# 生成候选集
def aprioriGen(Lk, k):
    retList = []
    lenLk = len(Lk)
    for i in range(lenLk):
        for j in range(i+1, lenLk):
            # 前k-2项相同时，将两个集合合并
            L1 = list(Lk[i])[:k-2]; L2 = list(Lk[j])[:k-2]
            L1.sort(); L2.sort()
            if L1==L2:
                retList.append(Lk[i] | Lk[j])
    return retList

# 生成频繁项集列表
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)
        Lk, supK = scanD(D, Ck, minSupport)
        supportData.update(supK)
        L.append(Lk)
        k += 1
    return L, supportData

# 生成关联规则
def generateRules(L, supportData, minConf=0.7):
    bigRuleList = []
    for i in range(1, len(L)):
        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

# 计算置信度
def calcConf(freqSet, H, supportData, brl, minConf=0.7):
    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 prunedH

# 生成候选规则集合
def rulesFromConseq(freqSet, H, supportData, brl, minConf=0.7):
    m = len(H[0])
    if (len(freqSet) > (m+1)):
        Hmpl = aprioriGen(H, m+1)
        Hmpl = calcConf(freqSet, Hmpl, supportData, brl, minConf)
        if (len(Hmpl)>1):
            rulesFromConseq(freqSet, Hmpl, supportData, brl, minConf)



if __name__ == '__main__':
    dataSet = createDataSet()
    L,supportData = apriori(dataSet, minSupport=0.5)
    # print L
    rules = generateRules(L, supportData, minConf=0.7)
    print rules