apriori算法python代码

以下是apriori算法的Python代码：

# 导入必要的库
import itertools

# 设置最小支持度和最小置信度
min_support = 0.5
min_confidence = 0.5

# 定义函数，生成C1项集
def create_C1(data):
    C1 = []
    for transaction in data:
        for item in transaction:
            if not [item] in C1:
                C1.append([item])
    C1.sort()
    return list(map(frozenset, C1))

# 定义函数，生成满足最小支持度的项集
def scan_D(D, Ck, min_support):
    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 >= min_support:
            retList.insert(0, key)
            supportData[key] = support
    return retList, supportData

# 定义函数，生成所有的频繁项集
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

# 定义函数，生成满足最小置信度的关联规则
def calc_conf(freqSet, H, supportData, brl, min_confidence):
    prunedH = []
    for conseq in H:
        conf = supportData[freqSet] / supportData[freqSet - conseq]
        if conf >= min_confidence:
            print(freqSet - conseq, '-->', conseq, 'conf:', conf)
            brl.append((freqSet-conseq, conseq, conf))
            prunedH.append(conseq)
    return prunedH

# 定义函数，递归生成规则
def rulesFromConseq(freqSet, H, supportData, brl, min_confidence):
    m = len(H[0])
    if len(freqSet) > (m + 1):
        Hmp1 = aprioriGen(H, m+1)
        Hmp1 = calc_conf(freqSet, Hmp1, supportData, brl, min_confidence)
        if len(Hmp1) > 1:
            rulesFromConseq(freqSet, Hmp1, supportData, brl, min_confidence)

# 定义函数，生成关联规则
def generate_rules(L, supportData, min_confidence):
    bigRuleList = []
    for i in range(1, len(L)):
        for freqSet in L[i]:
            H1 = [frozenset([item]) for item in freqSet]
            if (i > 1):
                rulesFromConseq(freqSet, H1, supportData, bigRuleList, min_confidence)
            else:
                calc_conf(freqSet, H1, supportData, bigRuleList, min_confidence)
    return bigRuleList

注意，以上代码只是apriori算法的框架代码，具体实现需要根据具体的数据集进行相应的修改。