Laurel

导航

Python两步实现关联规则Apriori算法,参考机器学习实战,包括频繁项集的构建以及关联规则的挖掘

 

 

 

 

 

这是我学习了关联规则Apriori算法原理后参照《机器学习实战》实现的算法代码,首先分为两个部分,第一部分是频繁项集的构建,第二部分是关联规则的挖掘。特别的是我的测试数据也就是loadDataSet()函数中的数据进行了改变,这是为了能帮助理解第二部分。然后代码中我加了很多为了让自己理解的输出测试,保留在里面,应该也能帮助大家理解^.^

一、构建频繁项集(注释都在代码中了~。~)

In [122]:
from numpy import *

def loadDataSet():
    return [[1, 3, 4,6,7], [2, 3, 4,5,6,7], [1, 2, 3, 5,7], [2,4, 5,6],[3,4,5,6,7]]

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)#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 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
    print'Lk:',Lk
    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]#见《数据挖掘概念与技术》p161的连接步讲解
            L1.sort(); L2.sort()
            print'L1,L2',L1,L2
            if L1==L2: #if first k-2 elements are equal,另外在由一项频繁集L1构造C2时,以上[:k-2]=[:0]=[],所以会有L1==L2,构造出2项候选集C2
                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)
        Lk, supK = scanD(D, Ck, minSupport)#scan DB to get Lk
        supportData.update(supK)
        L.append(Lk)
        k += 1
    return L, supportData
 

测试以上代码

In [130]:
data=loadDataSet()
D=map(set,data)
C1=createC1(D)
L,suppData=apriori(data,0.5)
print 'C1:',C1
print 'L:',L
print 'suppData:',suppData
 
Lk: [frozenset([2]), frozenset([4]), frozenset([6]), frozenset([3]), frozenset([5]), frozenset([7])]
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
Lk: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
L1,L2 [2] [4]
L1,L2 [2] [4]
L1,L2 [2] [4]
L1,L2 [2] [3]
L1,L2 [2] [3]
L1,L2 [2] [6]
L1,L2 [2] [5]
L1,L2 [2] [3]
L1,L2 [2] [3]
L1,L2 [2] [5]
L1,L2 [4] [4]
L1,L2 [4] [4]
L1,L2 [4] [3]
L1,L2 [4] [3]
L1,L2 [4] [6]
L1,L2 [4] [5]
L1,L2 [4] [3]
L1,L2 [4] [3]
L1,L2 [4] [5]
L1,L2 [4] [4]
L1,L2 [4] [3]
L1,L2 [4] [3]
L1,L2 [4] [6]
L1,L2 [4] [5]
L1,L2 [4] [3]
L1,L2 [4] [3]
L1,L2 [4] [5]
L1,L2 [4] [3]
L1,L2 [4] [3]
L1,L2 [4] [6]
L1,L2 [4] [5]
L1,L2 [4] [3]
L1,L2 [4] [3]
L1,L2 [4] [5]
L1,L2 [3] [3]
L1,L2 [3] [6]
L1,L2 [3] [5]
L1,L2 [3] [3]
L1,L2 [3] [3]
L1,L2 [3] [5]
L1,L2 [3] [6]
L1,L2 [3] [5]
L1,L2 [3] [3]
L1,L2 [3] [3]
L1,L2 [3] [5]
L1,L2 [6] [5]
L1,L2 [6] [3]
L1,L2 [6] [3]
L1,L2 [6] [5]
L1,L2 [5] [3]
L1,L2 [5] [3]
L1,L2 [5] [5]
L1,L2 [3] [3]
L1,L2 [3] [5]
L1,L2 [3] [5]
Lk: [frozenset([3, 6, 7]), frozenset([4, 5, 6]), frozenset([3, 5, 7]), frozenset([3, 4, 7]), frozenset([4, 6, 7]), frozenset([3, 4, 6])]
L1,L2 [3, 6] [4, 5]
L1,L2 [3, 6] [3, 5]
L1,L2 [3, 6] [3, 4]
L1,L2 [3, 6] [4, 6]
L1,L2 [3, 6] [3, 4]
L1,L2 [4, 5] [3, 5]
L1,L2 [4, 5] [3, 4]
L1,L2 [4, 5] [4, 6]
L1,L2 [4, 5] [3, 4]
L1,L2 [3, 5] [3, 4]
L1,L2 [3, 5] [4, 6]
L1,L2 [3, 5] [3, 4]
L1,L2 [3, 4] [4, 6]
L1,L2 [3, 4] [3, 4]
L1,L2 [4, 6] [3, 4]
Lk: [frozenset([3, 4, 6, 7])]
C1: [frozenset([1]), frozenset([2]), frozenset([3]), frozenset([4]), frozenset([5]), frozenset([6]), frozenset([7])]
L: [[frozenset([2]), frozenset([4]), frozenset([6]), frozenset([3]), frozenset([5]), frozenset([7])], [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])], [frozenset([3, 6, 7]), frozenset([4, 5, 6]), frozenset([3, 5, 7]), frozenset([3, 4, 7]), frozenset([4, 6, 7]), frozenset([3, 4, 6])], [frozenset([3, 4, 6, 7])], []]
suppData: {frozenset([5, 7]): 0.6, frozenset([3, 4, 6]): 0.6, frozenset([3, 7]): 0.8, frozenset([4, 6, 7]): 0.6, frozenset([3, 6]): 0.6, frozenset([3, 4, 7]): 0.6, frozenset([5, 6]): 0.6, frozenset([2, 6]): 0.4, frozenset([6, 7]): 0.6, frozenset([3, 5, 7]): 0.6, frozenset([4, 5, 6]): 0.6, frozenset([4]): 0.8, frozenset([4, 7]): 0.6, frozenset([2, 7]): 0.4, frozenset([2, 4]): 0.4, frozenset([7]): 0.8, frozenset([5]): 0.8, frozenset([3]): 0.8, frozenset([3, 4, 5]): 0.4, frozenset([6]): 0.8, frozenset([3, 5, 6]): 0.4, frozenset([3, 5]): 0.6, frozenset([5, 6, 7]): 0.4, frozenset([3, 4]): 0.6, frozenset([3, 6, 7]): 0.6, frozenset([2, 3]): 0.4, frozenset([4, 6]): 0.8, frozenset([2, 5]): 0.6, frozenset([1]): 0.4, frozenset([4, 5, 7]): 0.4, frozenset([2]): 0.6, frozenset([3, 4, 6, 7]): 0.6, frozenset([4, 5]): 0.6}
二、基于构造出的频繁项集挖掘关联规则(注释都在代码中了~。~) 需要注意的就是对rulesFromConseq()函数的理解,可以参照我代码中添加的用于测试的输出函数的输出理解
In [123]:
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
        print 'i:',i
        for freqSet in L[i]:
            print'L[i]:',L[i]
            print'freqSet:',freqSet
            H1 = [frozenset([item]) for item in freqSet]
            print 'H1:',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):
    prunedH = [] #create new list to return
    for conseq in H:
        print'conseq:',conseq
        print'freqSet-conseq:',freqSet-conseq
        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)
#     print 'prunedH:',prunedH
    return prunedH

#rulesFromConseq目的就是对每一个频繁项集生成右边的规则,一个频繁项集可以生成很多右边的规则
#if (len(freqSet) > (m + 1))这是迭代停止的条件,也就是当右边的规则的元素数+1=该频繁项长度时停止迭代
#if (len(Hmp1) > 1)当Hmp1的长度大于1时才能合并,合并需要至少两个frozenset
def rulesFromConseq(freqSet, H, supportData, brl, minConf=0.7):
    m = len(H[0])
    print'm:',m
    print'len(freqSet):',len(freqSet)
    if (len(freqSet) > (m + 1)): #try further merging
        Hmp1 = aprioriGen(H, m+1)#create Hm+1 new candidates
        print'Hmp1:',Hmp1
        Hmp1 = calcConf(freqSet, Hmp1, supportData, brl, minConf)
        print 'Hmp2:',Hmp1
        if (len(Hmp1) > 1):    #need at least two sets to merge
            print'---------'
            rulesFromConseq(freqSet, Hmp1, supportData, brl, minConf)
            print'*********'
 

测试以上代码

In [131]:
generateRules(L,suppData,0.5)
 
i: 1
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([2, 5])
H1: [frozenset([2]), frozenset([5])]
conseq: frozenset([2])
freqSet-conseq: frozenset([5])
frozenset([5]) --> frozenset([2]) conf: 0.75
conseq: frozenset([5])
freqSet-conseq: frozenset([2])
frozenset([2]) --> frozenset([5]) conf: 1.0
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([4, 5])
H1: [frozenset([4]), frozenset([5])]
conseq: frozenset([4])
freqSet-conseq: frozenset([5])
frozenset([5]) --> frozenset([4]) conf: 0.75
conseq: frozenset([5])
freqSet-conseq: frozenset([4])
frozenset([4]) --> frozenset([5]) conf: 0.75
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([4, 7])
H1: [frozenset([4]), frozenset([7])]
conseq: frozenset([4])
freqSet-conseq: frozenset([7])
frozenset([7]) --> frozenset([4]) conf: 0.75
conseq: frozenset([7])
freqSet-conseq: frozenset([4])
frozenset([4]) --> frozenset([7]) conf: 0.75
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([4, 6])
H1: [frozenset([4]), frozenset([6])]
conseq: frozenset([4])
freqSet-conseq: frozenset([6])
frozenset([6]) --> frozenset([4]) conf: 1.0
conseq: frozenset([6])
freqSet-conseq: frozenset([4])
frozenset([4]) --> frozenset([6]) conf: 1.0
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([3, 4])
H1: [frozenset([3]), frozenset([4])]
conseq: frozenset([3])
freqSet-conseq: frozenset([4])
frozenset([4]) --> frozenset([3]) conf: 0.75
conseq: frozenset([4])
freqSet-conseq: frozenset([3])
frozenset([3]) --> frozenset([4]) conf: 0.75
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([3, 5])
H1: [frozenset([3]), frozenset([5])]
conseq: frozenset([3])
freqSet-conseq: frozenset([5])
frozenset([5]) --> frozenset([3]) conf: 0.75
conseq: frozenset([5])
freqSet-conseq: frozenset([3])
frozenset([3]) --> frozenset([5]) conf: 0.75
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([6, 7])
H1: [frozenset([6]), frozenset([7])]
conseq: frozenset([6])
freqSet-conseq: frozenset([7])
frozenset([7]) --> frozenset([6]) conf: 0.75
conseq: frozenset([7])
freqSet-conseq: frozenset([6])
frozenset([6]) --> frozenset([7]) conf: 0.75
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([5, 6])
H1: [frozenset([5]), frozenset([6])]
conseq: frozenset([5])
freqSet-conseq: frozenset([6])
frozenset([6]) --> frozenset([5]) conf: 0.75
conseq: frozenset([6])
freqSet-conseq: frozenset([5])
frozenset([5]) --> frozenset([6]) conf: 0.75
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([3, 6])
H1: [frozenset([3]), frozenset([6])]
conseq: frozenset([3])
freqSet-conseq: frozenset([6])
frozenset([6]) --> frozenset([3]) conf: 0.75
conseq: frozenset([6])
freqSet-conseq: frozenset([3])
frozenset([3]) --> frozenset([6]) conf: 0.75
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([3, 7])
H1: [frozenset([3]), frozenset([7])]
conseq: frozenset([3])
freqSet-conseq: frozenset([7])
frozenset([7]) --> frozenset([3]) conf: 1.0
conseq: frozenset([7])
freqSet-conseq: frozenset([3])
frozenset([3]) --> frozenset([7]) conf: 1.0
L[i]: [frozenset([2, 5]), frozenset([4, 5]), frozenset([4, 7]), frozenset([4, 6]), frozenset([3, 4]), frozenset([3, 5]), frozenset([6, 7]), frozenset([5, 6]), frozenset([3, 6]), frozenset([3, 7]), frozenset([5, 7])]
freqSet: frozenset([5, 7])
H1: [frozenset([5]), frozenset([7])]
conseq: frozenset([5])
freqSet-conseq: frozenset([7])
frozenset([7]) --> frozenset([5]) conf: 0.75
conseq: frozenset([7])
freqSet-conseq: frozenset([5])
frozenset([5]) --> frozenset([7]) conf: 0.75
i: 2
L[i]: [frozenset([3, 6, 7]), frozenset([4, 5, 6]), frozenset([3, 5, 7]), frozenset([3, 4, 7]), frozenset([4, 6, 7]), frozenset([3, 4, 6])]
freqSet: frozenset([3, 6, 7])
H1: [frozenset([3]), frozenset([6]), frozenset([7])]
m: 1
len(freqSet): 3
Lk: [frozenset([3]), frozenset([6]), frozenset([7])]
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
Hmp1: [frozenset([3, 6]), frozenset([3, 7]), frozenset([6, 7])]
conseq: frozenset([3, 6])
freqSet-conseq: frozenset([7])
frozenset([7]) --> frozenset([3, 6]) conf: 0.75
conseq: frozenset([3, 7])
freqSet-conseq: frozenset([6])
frozenset([6]) --> frozenset([3, 7]) conf: 0.75
conseq: frozenset([6, 7])
freqSet-conseq: frozenset([3])
frozenset([3]) --> frozenset([6, 7]) conf: 0.75
Hmp2: [frozenset([3, 6]), frozenset([3, 7]), frozenset([6, 7])]
---------
m: 2
len(freqSet): 3
*********
L[i]: [frozenset([3, 6, 7]), frozenset([4, 5, 6]), frozenset([3, 5, 7]), frozenset([3, 4, 7]), frozenset([4, 6, 7]), frozenset([3, 4, 6])]
freqSet: frozenset([4, 5, 6])
H1: [frozenset([4]), frozenset([5]), frozenset([6])]
m: 1
len(freqSet): 3
Lk: [frozenset([4]), frozenset([5]), frozenset([6])]
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
Hmp1: [frozenset([4, 5]), frozenset([4, 6]), frozenset([5, 6])]
conseq: frozenset([4, 5])
freqSet-conseq: frozenset([6])
frozenset([6]) --> frozenset([4, 5]) conf: 0.75
conseq: frozenset([4, 6])
freqSet-conseq: frozenset([5])
frozenset([5]) --> frozenset([4, 6]) conf: 0.75
conseq: frozenset([5, 6])
freqSet-conseq: frozenset([4])
frozenset([4]) --> frozenset([5, 6]) conf: 0.75
Hmp2: [frozenset([4, 5]), frozenset([4, 6]), frozenset([5, 6])]
---------
m: 2
len(freqSet): 3
*********
L[i]: [frozenset([3, 6, 7]), frozenset([4, 5, 6]), frozenset([3, 5, 7]), frozenset([3, 4, 7]), frozenset([4, 6, 7]), frozenset([3, 4, 6])]
freqSet: frozenset([3, 5, 7])
H1: [frozenset([3]), frozenset([5]), frozenset([7])]
m: 1
len(freqSet): 3
Lk: [frozenset([3]), frozenset([5]), frozenset([7])]
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
Hmp1: [frozenset([3, 5]), frozenset([3, 7]), frozenset([5, 7])]
conseq: frozenset([3, 5])
freqSet-conseq: frozenset([7])
frozenset([7]) --> frozenset([3, 5]) conf: 0.75
conseq: frozenset([3, 7])
freqSet-conseq: frozenset([5])
frozenset([5]) --> frozenset([3, 7]) conf: 0.75
conseq: frozenset([5, 7])
freqSet-conseq: frozenset([3])
frozenset([3]) --> frozenset([5, 7]) conf: 0.75
Hmp2: [frozenset([3, 5]), frozenset([3, 7]), frozenset([5, 7])]
---------
m: 2
len(freqSet): 3
*********
L[i]: [frozenset([3, 6, 7]), frozenset([4, 5, 6]), frozenset([3, 5, 7]), frozenset([3, 4, 7]), frozenset([4, 6, 7]), frozenset([3, 4, 6])]
freqSet: frozenset([3, 4, 7])
H1: [frozenset([3]), frozenset([4]), frozenset([7])]
m: 1
len(freqSet): 3
Lk: [frozenset([3]), frozenset([4]), frozenset([7])]
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
Hmp1: [frozenset([3, 4]), frozenset([3, 7]), frozenset([4, 7])]
conseq: frozenset([3, 4])
freqSet-conseq: frozenset([7])
frozenset([7]) --> frozenset([3, 4]) conf: 0.75
conseq: frozenset([3, 7])
freqSet-conseq: frozenset([4])
frozenset([4]) --> frozenset([3, 7]) conf: 0.75
conseq: frozenset([4, 7])
freqSet-conseq: frozenset([3])
frozenset([3]) --> frozenset([4, 7]) conf: 0.75
Hmp2: [frozenset([3, 4]), frozenset([3, 7]), frozenset([4, 7])]
---------
m: 2
len(freqSet): 3
*********
L[i]: [frozenset([3, 6, 7]), frozenset([4, 5, 6]), frozenset([3, 5, 7]), frozenset([3, 4, 7]), frozenset([4, 6, 7]), frozenset([3, 4, 6])]
freqSet: frozenset([4, 6, 7])
H1: [frozenset([4]), frozenset([6]), frozenset([7])]
m: 1
len(freqSet): 3
Lk: [frozenset([4]), frozenset([6]), frozenset([7])]
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
Hmp1: [frozenset([4, 6]), frozenset([4, 7]), frozenset([6, 7])]
conseq: frozenset([4, 6])
freqSet-conseq: frozenset([7])
frozenset([7]) --> frozenset([4, 6]) conf: 0.75
conseq: frozenset([4, 7])
freqSet-conseq: frozenset([6])
frozenset([6]) --> frozenset([4, 7]) conf: 0.75
conseq: frozenset([6, 7])
freqSet-conseq: frozenset([4])
frozenset([4]) --> frozenset([6, 7]) conf: 0.75
Hmp2: [frozenset([4, 6]), frozenset([4, 7]), frozenset([6, 7])]
---------
m: 2
len(freqSet): 3
*********
L[i]: [frozenset([3, 6, 7]), frozenset([4, 5, 6]), frozenset([3, 5, 7]), frozenset([3, 4, 7]), frozenset([4, 6, 7]), frozenset([3, 4, 6])]
freqSet: frozenset([3, 4, 6])
H1: [frozenset([3]), frozenset([4]), frozenset([6])]
m: 1
len(freqSet): 3
Lk: [frozenset([3]), frozenset([4]), frozenset([6])]
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
Hmp1: [frozenset([3, 4]), frozenset([3, 6]), frozenset([4, 6])]
conseq: frozenset([3, 4])
freqSet-conseq: frozenset([6])
frozenset([6]) --> frozenset([3, 4]) conf: 0.75
conseq: frozenset([3, 6])
freqSet-conseq: frozenset([4])
frozenset([4]) --> frozenset([3, 6]) conf: 0.75
conseq: frozenset([4, 6])
freqSet-conseq: frozenset([3])
frozenset([3]) --> frozenset([4, 6]) conf: 0.75
Hmp2: [frozenset([3, 4]), frozenset([3, 6]), frozenset([4, 6])]
---------
m: 2
len(freqSet): 3
*********
i: 3
L[i]: [frozenset([3, 4, 6, 7])]
freqSet: frozenset([3, 4, 6, 7])
H1: [frozenset([3]), frozenset([4]), frozenset([6]), frozenset([7])]
m: 1
len(freqSet): 4
Lk: [frozenset([3]), frozenset([4]), frozenset([6]), frozenset([7])]
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
L1,L2 [] []
Hmp1: [frozenset([3, 4]), frozenset([3, 6]), frozenset([3, 7]), frozenset([4, 6]), frozenset([4, 7]), frozenset([6, 7])]
conseq: frozenset([3, 4])
freqSet-conseq: frozenset([6, 7])
frozenset([6, 7]) --> frozenset([3, 4]) conf: 1.0
conseq: frozenset([3, 6])
freqSet-conseq: frozenset([4, 7])
frozenset([4, 7]) --> frozenset([3, 6]) conf: 1.0
conseq: frozenset([3, 7])
freqSet-conseq: frozenset([4, 6])
frozenset([4, 6]) --> frozenset([3, 7]) conf: 0.75
conseq: frozenset([4, 6])
freqSet-conseq: frozenset([3, 7])
frozenset([3, 7]) --> frozenset([4, 6]) conf: 0.75
conseq: frozenset([4, 7])
freqSet-conseq: frozenset([3, 6])
frozenset([3, 6]) --> frozenset([4, 7]) conf: 1.0
conseq: frozenset([6, 7])
freqSet-conseq: frozenset([3, 4])
frozenset([3, 4]) --> frozenset([6, 7]) conf: 1.0
Hmp2: [frozenset([3, 4]), frozenset([3, 6]), frozenset([3, 7]), frozenset([4, 6]), frozenset([4, 7]), frozenset([6, 7])]
---------
m: 2
len(freqSet): 4
Lk: [frozenset([3, 4]), frozenset([3, 6]), frozenset([3, 7]), frozenset([4, 6]), frozenset([4, 7]), frozenset([6, 7])]
L1,L2 [3] [3]
L1,L2 [3] [3]
L1,L2 [3] [4]
L1,L2 [3] [4]
L1,L2 [3] [6]
L1,L2 [3] [3]
L1,L2 [3] [4]
L1,L2 [3] [4]
L1,L2 [3] [6]
L1,L2 [3] [4]
L1,L2 [3] [4]
L1,L2 [3] [6]
L1,L2 [4] [4]
L1,L2 [4] [6]
L1,L2 [4] [6]
Hmp1: [frozenset([3, 4, 6]), frozenset([3, 4, 7]), frozenset([3, 6, 7]), frozenset([4, 6, 7])]
conseq: frozenset([3, 4, 6])
freqSet-conseq: frozenset([7])
frozenset([7]) --> frozenset([3, 4, 6]) conf: 0.75
conseq: frozenset([3, 4, 7])
freqSet-conseq: frozenset([6])
frozenset([6]) --> frozenset([3, 4, 7]) conf: 0.75
conseq: frozenset([3, 6, 7])
freqSet-conseq: frozenset([4])
frozenset([4]) --> frozenset([3, 6, 7]) conf: 0.75
conseq: frozenset([4, 6, 7])
freqSet-conseq: frozenset([3])
frozenset([3]) --> frozenset([4, 6, 7]) conf: 0.75
Hmp2: [frozenset([3, 4, 6]), frozenset([3, 4, 7]), frozenset([3, 6, 7]), frozenset([4, 6, 7])]
---------
m: 3
len(freqSet): 4
*********
*********
i: 4
Out[131]:
[(frozenset({5}), frozenset({2}), 0.7499999999999999),
 (frozenset({2}), frozenset({5}), 1.0),
 (frozenset({5}), frozenset({4}), 0.7499999999999999),
 (frozenset({4}), frozenset({5}), 0.7499999999999999),
 (frozenset({7}), frozenset({4}), 0.7499999999999999),
 (frozenset({4}), frozenset({7}), 0.7499999999999999),
 (frozenset({6}), frozenset({4}), 1.0),
 (frozenset({4}), frozenset({6}), 1.0),
 (frozenset({4}), frozenset({3}), 0.7499999999999999),
 (frozenset({3}), frozenset({4}), 0.7499999999999999),
 (frozenset({5}), frozenset({3}), 0.7499999999999999),
 (frozenset({3}), frozenset({5}), 0.7499999999999999),
 (frozenset({7}), frozenset({6}), 0.7499999999999999),
 (frozenset({6}), frozenset({7}), 0.7499999999999999),
 (frozenset({6}), frozenset({5}), 0.7499999999999999),
 (frozenset({5}), frozenset({6}), 0.7499999999999999),
 (frozenset({6}), frozenset({3}), 0.7499999999999999),
 (frozenset({3}), frozenset({6}), 0.7499999999999999),
 (frozenset({7}), frozenset({3}), 1.0),
 (frozenset({3}), frozenset({7}), 1.0),
 (frozenset({7}), frozenset({5}), 0.7499999999999999),
 (frozenset({5}), frozenset({7}), 0.7499999999999999),
 (frozenset({7}), frozenset({3, 6}), 0.7499999999999999),
 (frozenset({6}), frozenset({3, 7}), 0.7499999999999999),
 (frozenset({3}), frozenset({6, 7}), 0.7499999999999999),
 (frozenset({6}), frozenset({4, 5}), 0.7499999999999999),
 (frozenset({5}), frozenset({4, 6}), 0.7499999999999999),
 (frozenset({4}), frozenset({5, 6}), 0.7499999999999999),
 (frozenset({7}), frozenset({3, 5}), 0.7499999999999999),
 (frozenset({5}), frozenset({3, 7}), 0.7499999999999999),
 (frozenset({3}), frozenset({5, 7}), 0.7499999999999999),
 (frozenset({7}), frozenset({3, 4}), 0.7499999999999999),
 (frozenset({4}), frozenset({3, 7}), 0.7499999999999999),
 (frozenset({3}), frozenset({4, 7}), 0.7499999999999999),
 (frozenset({7}), frozenset({4, 6}), 0.7499999999999999),
 (frozenset({6}), frozenset({4, 7}), 0.7499999999999999),
 (frozenset({4}), frozenset({6, 7}), 0.7499999999999999),
 (frozenset({6}), frozenset({3, 4}), 0.7499999999999999),
 (frozenset({4}), frozenset({3, 6}), 0.7499999999999999),
 (frozenset({3}), frozenset({4, 6}), 0.7499999999999999),
 (frozenset({6, 7}), frozenset({3, 4}), 1.0),
 (frozenset({4, 7}), frozenset({3, 6}), 1.0),
 (frozenset({4, 6}), frozenset({3, 7}), 0.7499999999999999),
 (frozenset({3, 7}), frozenset({4, 6}), 0.7499999999999999),
 (frozenset({3, 6}), frozenset({4, 7}), 1.0),
 (frozenset({3, 4}), frozenset({6, 7}), 1.0),
 (frozenset({7}), frozenset({3, 4, 6}), 0.7499999999999999),
 (frozenset({6}), frozenset({3, 4, 7}), 0.7499999999999999),
 (frozenset({4}), frozenset({3, 6, 7}), 0.7499999999999999),
 (frozenset({3}), frozenset({4, 6, 7}), 0.7499999999999999)]
 

有空会把自己对Apriori算法原理的理解补上,ennnnn……

posted on 2019-02-22 10:47  Laurel1115  阅读(852)  评论(0编辑  收藏  举报