Python3.4 Apriori算法

'''思路：      1、生成L1;      2、Ck生成Lk;      3、Lk生成Ck+1;      4、得到频繁项集；（前面只用到支持度）;      5、通过频繁项集生成关联规则。（用到置信度）.'''import collectionsdatasets = [    ["I1","I2","I5"],    ["I2","I4"],    ["I2","I3"],    ["I1","I2","I4"],    ["I1","I3"],    ["I2","I3"],    ["I1","I3"],    ["I1","I2","I3","I5"],    ["I1","I2","I3"]    ]#使用绝对最小支持度，即为频数，相对支持度表示概率，用前面的频数除以记录条数nmin_support = 2min_confidence = 0.5Lk_all = {}#将每条记录内容进行连接，最终以字符串形式连接每条记录里的各个元素，它们之间使用逗号隔开def getdatasetsString():    result = []    for transation in datasets:        tmp = ""        for item in transation:            tmp+=item            if item != transation[-1]:                tmp += ","        result.append(tmp)    return result#print(getdatasetsString())#得到L1def getL1():    tmp = []    L1 = {}    for transaction in datasets:        for item in transaction:            tmp.append(item)      rs = collections.Counter(tmp)      #使用库函数直接统计出现的次数，避免手动计数。    for key in sorted(rs):        if(rs[key] >= min_support):      #通过最小支持度进行剪枝操作，得到L1            L1[key] = rs[key]    return L1#L1 = getL1()#print("L1:",L1)#Ck生成Lkdef getLk(Ck):    Lk = {}    result = getdatasetsString()    #print(result)    for items in Ck:        tmpitems = items.split(",")        count = 0        for r in result:            flag = True            for item in tmpitems:                if item in r:                    continue                else:                    flag = False                    break            if flag:                count = count + 1        if (count >= min_support):            Lk[items] = count    return Lk#由Lk生成Ck+1def getCk1(Lk):     Ck= []    keys = list(Lk.keys())    keys1 = list(Lk.keys())    for key in keys:        keys1.remove(key)       #自连接时去掉前面出现过的元素        for key1 in keys1:            key_last = key.split(",")[-1]        #获取最后一个元素            key1_last = key1.split(",")[-1]            key_pre = key.replace(key_last,"")            key1_pre = key1.replace(key1_last,"")            if( key_pre == key1_pre):                if (key_last>key1_last):                    s = key_pre+key1_last+","+key_last      #还需要进一步判断s所有少一个元素的子串是否是频繁项集                else:                    s = key_pre+key_last+","+key1_last      #还需要进一步判断s所有少一个元素的子串是否是频繁项集                subc = getSubString(s)                  #获取所有少一个元素的子串，以list形式存起来，与候选项集相同形式存储                subl = getLk(subc)                      #通过Ck生成Lk                if(len(subc) == len(subl)):             #如果Ck与Lk元素个数相同，则说明ck里所有元素都是频繁的                    Ck.append(s)    return Ck;    #得到最终频繁项集def getFiallyLk(L1):    Lk = L1    while(True):        Ck1 = getCk1(Lk)        Lk1 = getLk(Ck1)        #print("Lk:",Lk)        for key in Lk:            Lk_all[key] = Lk[key]        if (len(Lk1) == 0):            break        Lk = Lk1    return Lk#获取所有少一个元素的子串，以list形式存起来，与候选项集相同形式存储,比如'abc',则得到'ab'、'ac'和'bc'def getSubString(s):    substring = []    items = s.split(",")    for item in items:        if item == items[-1]:            substring.append(s.replace(","+item,""))        else:            substring.append(s.replace(item+",",""))    return substring#Lk = getFiallyLk(L1)#print("最终频繁项集:",Lk)#下面将根据频繁项集获取强关联规则from itertools import combinationstry:    from functools import reduceexcept ImportError:    pass#通过函数f就可以获取列表的所有非空子集(不包括本身)f = lambda s: reduce(list.__add__, (    list(map(list, combinations(s, l)))        for l in range(1, len(s))),    [])#获取强关联规则def getRule(Lk):    rules = {}    for Lk_item in Lk:        items = Lk_item.split(",")        #n = len(datasets)      #由于概率过程中都除以n，所以可以约掉而不用计算        N = Lk[Lk_item]           #P(X->Y) = p(XY)/P(X) = N(XY)/N(X),这里的N就是计算出了N(XY)        pre_item_list = f(items)        for pre_item in pre_item_list:            back_item = sorted(list(set(items)^set(pre_item)) )         #得到2个list的差集            #print(pre_item,"=>",back_item)            pre_s = ""            for item in pre_item:                if len(pre_item) == 1:                    pre_s += item                else:                    if item == pre_item[-1]:                        pre_s += item                    else:                        pre_s += item + ","            back_s = ""            for item in back_item:                if len(back_item) == 1:                    back_s += item                else:                    if item == back_item[-1]:                        back_s += item                    else:                        back_s += item + ","            #下面计算N(X)            N1 = Lk_all[pre_s]            p = N/N1            if(p >= min_confidence):                rule = pre_s+" => "+back_s                #print(rule)                rules[rule] = p    return rules        #print(Lk_all)  #存放所有频繁项集里的元素出现的次数if __name__ == "__main__":    L1 = getL1()    Lk = getFiallyLk(L1)    print("最终频繁项集:",Lk)    rules = getRule(Lk)    for rule in rules:        print(rule,":",rules[rule])    '''    C2 = getCk1(L1)    print("C2:",C2)    L2 = getLk(C2)    print("L2:",L2)    C3 = getCk1(L2)    print("C3:",C3)    L3 = getLk(C3)    print("L3:",L3)    '''

最终输出结果截图：