Apriori算法

假如有4条记录
[[1, 3, 4], [2, 3, 5], [1, 2, 3, 5], [2, 5]]
那么集合{1}的支持度为2/4，即出现记次数/总记录数。

一条规则P-H的可信度为 support(P&&H)/support(P)
机器学习实战的算法首先枚举了所有计算出来满足支持度的记录，然后以枚举的为P&&H，然后再枚举子集，用P&&H/(P&&H-子集)计算可信度。

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)

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):
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 = 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

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]
print(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 = []
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):
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 pntRules(ruleList, itemMeaning):
for ruleTup in ruleList:
for item in ruleTup[0]:
print itemMeaning[item]
print "           -------->"
for item in ruleTup[1]:
print itemMeaning[item]
print "confidence: %f" % ruleTup[2]
print