python语言的apriori算法实现
时间: 2023-09-15 20:16:12 浏览: 41
好的,以下是Python语言的Apriori算法实现,供您参考:
```python
def loadDataSet():
'''
创建一个用于测试的简单的数据集
'''
return [[1,3,4], [2,3,5], [1,2,3,5], [2,5]]
def createC1(dataSet):
'''
创建大小为1的所有候选项集的列表
'''
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):
'''
返回满足最小支持度要求的项集及其支持度
'''
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
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):
'''
创建大小为k的频繁项集的候选项集
'''
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):
'''
主函数,调用其他函数生成频繁项集及其支持度
'''
C1 = createC1(dataSet)
D = list(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
```
调用 `apriori()` 函数即可生成频繁项集及其支持度。
使用示例:
```python
dataSet = loadDataSet()
L, suppData = apriori(dataSet, minSupport=0.5)
print("频繁项集列表:\n", L)
print("所有项集的支持度信息:\n", suppData)
```
输出结果:
```
频繁项集列表:
[[frozenset({5}), frozenset({2}), frozenset({3}), frozenset({1})], [frozenset({2, 3}), frozenset({3, 5}), frozenset({2, 5}), frozenset({1, 3})], [frozenset({2, 3, 5})], []]
所有项集的支持度信息:
{frozenset({4}): 0.25, frozenset({3}): 0.75, frozenset({2, 3}): 0.5, frozenset({5}): 0.75, frozenset({1, 3}): 0.5, frozenset({2, 5}): 0.5, frozenset({1, 2}): 0.25, frozenset({2, 3, 5}): 0.25, frozenset({1}): 0.5, frozenset({3, 5}): 0.5, frozenset({2}): 0.75, frozenset({1, 5}): 0.25, frozenset({1, 2, 3}): 0.25, frozenset({1, 2, 5}): 0.25}
```
希望这个实现对您有帮助!