python apriori模块_python实现Apriori算法

# coding: utf-8

# 利用python实现apriori算法

# In[1]:

#导入需要的库

from numpy import *

# In[2]:

def loadDataSet():

return [[1,3,4],[2,3,5],[1,2,3,5],[2,5]]

# In[3]:

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)

# In[4]:

#计算Ck在数据集D中的支持度，并返回支持度大于minSupport的数据集

def scanD(D,Ck,minSupport):

ssCnt={}

for tid in D:

for can in Ck:

if can.issubset(tid):

if can not in ssCnt.keys():

ssCnt[can]=1

else :

ssCnt[can]+=1

numItems=float(len(D))

retList=[]

supportData={}

for key in ssCnt:

support=ssCnt[key]/numItems

if support>= min