Python3.6-Apriori算法进行关联分析

python3.6机器学习实战第11章代码问题总结

程序清单11-1

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 list(map(frozenset,C1))
def scanD(D,Ck,minSupport):
    numItems=float(len(list(D)))#python3.6不支持len(map对象，即D)，可以看到D可以用一次
    print(list(D))#我调整了源代码的位置，这一步发现map对象D运行完这一段就变空了
    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
    print(list(D))
    #numItems=float(len(D))
    print(numItems)
    retList=[]
    supportData={}
    for key in ssCnt:
        support=ssCnt[key]/numItem