1 # -*- coding: utf-8 -*-
2 """
3 Created on Mon Nov 05 22:50:13 2018
4
5 @author: ZhuChaochao
6 """
7 def loadDataSet():
8 f = open("F:/Python CODE/zcc/1.txt",‘r‘) #读取的数据
9 source = f.readlines()
10 f.close()
11 dataset = []
12 for line in source:
13 line=line.strip().split(‘ ‘)
14 curLine = list(map(int,line))
15 dataset.append(curLine)
16 return dataset
17
18
19 def createC1(dataset):
20 C1 = []
21 for transaction in dataset:
22 for item in transaction:
23 if not [item] in C1:
24 C1.append([item])
25 C1.sort()
26 return map(frozenset,C1)
27
28 def scanD(D,CK,minSupport):
29 ssCnt = {}
30 for tid in D:
31 for can in CK:
32 if can.issubset(tid):
33 if not can in ssCnt:
34 ssCnt[can] = 1
35 else:
36 ssCnt[can] += 1
37
38 D=list(map(set,D))
39 numItems = float(len(D))
40 retList = []
41 supportData = {}
42 for key in ssCnt:
43 try:
44 support = ssCnt[key]/numItems
45 except (ZeroDivisionError,ValueError) as e:
46 print(e)
47 if support >= minSupport:
48 retList.insert(0,key)
49 supportData[key] = support
50 return retList,supportData
51
52 def aprioriGen(Lk, k):
53 retList = []
54 lenLk = len(Lk)
55 for i in range(lenLk):
56 for j in range(i+1, lenLk):
57 L1 = list(Lk[i])[:k-2]; L2 = list(Lk[j])[:k-2]
58 L1.sort(); L2.sort()
59 if L1==L2:
60 retList.append(Lk[i] | Lk[j])
61 return retList
62
63 def apriori(dataSet, minSupport = 0.5):
64 C1 = createC1(dataSet)
65 D = map(set, dataSet)
66 L1, supportData = scanD(D, C1, minSupport)
67 L = [L1]
68 k = 2
69 while (len(L[k-2]) > 0):
70 Ck = aprioriGen(L[k-2], k)
71 Lk, supK = scanD(D, Ck, minSupport)
72 supportData.update(supK)
73 L.append(Lk)
74 k += 1
75 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
原文地址：https://www.cnblogs.com/USTC-ZCC/p/9982134.html