Apriori算法--Python实现

 # -*- coding: utf-8 -*-
 """
 Created on Mon Nov 05 22:50:13 2018

 @author: ZhuChaochao
 """
 def loadDataSet():
     f = open("F:/Python CODE/zcc/1.txt",'r') #读取的数据
     source = f.readlines()
     f.close()
     dataset = []
     for line in source:
         line=line.strip().split('  ')
         curLine = list(map(int,line))
         dataset.append(curLine)
     return dataset

 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 can in ssCnt:
                     ssCnt[can] = 1
                 else:
                     ssCnt[can] += 1

     D=list(map(set,D))
     numItems = float(len(D))
     retList = []
     supportData = {}
     for key in ssCnt:
         try:
             support = ssCnt[key]/numItems
         except (ZeroDivisionError,ValueError) as e:
             print(e)
         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
     L, supportDatareturn 

source = f.readlines()
f.close()
dataset = []
for line in source:
line=line.strip().split(' ')
curLine = list(map(int,line))
dataset.append(curLine)
return dataset

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 can in ssCnt:
ssCnt[can] = 1
else:
ssCnt[can] += 1

D=list(map(set,D))
numItems = float(len(D))
retList = []
supportData = {}
for key in ssCnt:
try:
support = ssCnt[key]/numItems
except (ZeroDivisionError,ValueError) as e:
print(e)
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
L, supportDatareturn