Apriori算法解析
参考原文
参考博文的文章链接
参考代码
"""
Apriori算法测试.
@author: ZSCDumin
"""
def loadDataSet():
'''
创建简单的数据集
'''
return [[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]
def createC1(dataSet):
"""
函数说明:C1 是大小为1的所有候选项集的集合,是不重复的frozenset集合.
"""
C1 = []
for transaction in dataSet:
for item in transaction:
if not [item] in C1:
C1.append([item])
C1.sort()
return list(map(frozenset, C1))
def scanD(D, Ck, minSupport):
"""
函数说明:该函数用于从大小为1的所有候选项集的集合C1生成频繁项集列表L1,即retList。
数据集:D
候选项集列表:Ck
最小支持度:minSupport
返回值: 频繁项集列表:retList
包含支持度值的字典:supportData
"""
ssCnt = {}
for tid in D:
for can in Ck:
if can.issubset(tid):
if not can in ssCnt:
ssCnt[can] = 1
else:
ssCnt[can] += 1
numItems = float(len(D))
reList = []
supportData = {}
for key in ssCnt:
support = ssCnt[key] / numItems
if support >= minSupport:
reList.insert(0, key)
supportData[key] = support
return reList, supportData
def aprioriGen(Lk, k):
'''
由初始候选项集的集合Lk生成新的生成候选项集,
k表示生成的新项集中所含有的元素个数
'''
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:
retList.append(Lk[i] | Lk[j])
return retList
def apriori(dataSet, minSupport=0.5):
C1 = createC1(dataSet)
D = list(map(set, dataSet))
L1, suppData = 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)
suppData.update(supK)
L.append(Lk)
k += 1
return L, suppData
def calcConf(freqSet, H, supportData, brl, minConf=0.7):
'''
计算规则的可信度,返回满足最小可信度的规则。
freqSet(frozenset):频繁项集
H(frozenset):频繁项集中所有的元素
supportData(dic):频繁项集中所有元素的支持度
brl(tuple):满足可信度条件的关联规则
minConf(float):最小可信度
'''
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
def rulesFromConseq(freqSet, H, supportData, brl, minConf=0.7):
'''
对频繁项集中元素超过2的项集进行合并。
freqSet(frozenset):频繁项集
H(frozenset):频繁项集中的所有元素,即可以出现在规则右部的元素
supportData(dict):所有项集的支持度信息
brl(tuple):生成的规则
'''
m = len(H[0])
if len(freqSet) > m + 1:
Hmp1 = aprioriGen(H, m + 1)
Hmp1 = calcConf(freqSet, Hmp1, supportData, brl, minConf)
if len(Hmp1) > 1:
rulesFromConseq(freqSet, Hmp1, supportData, brl, minConf)
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
if __name__ == '__main__':
mushDataSet = [line.split() for line in open(
'./mushroom.dat').readlines()]
L, supportData = apriori(mushDataSet, minSupport=0.3)
for item in L[3]:
if '2' in item:
print(item)