import csv # 获取user.csv文件里面的内容 import re class ReadCsv(): def read_csv(self): item = [] r = csv.reader(open("D:\桌面文件\作业文档\大数据分析\试验1\Groceries.csv", "r")) for csv_i in r: item.append(csv_i) item = item[1:] # 从第一行开始获取 return item r = ReadCsv() a = r.read_csv() # print(a) dataset = [] for list2 in a: string = list2[1].replace('{', '') string1 = string.replace('}', '') # 去掉{} string2 = re.sub('/' + '[a-z]*' + ' ' + '[a-z]*', '', string1) # 去掉/后面的那项商品 string3 = re.sub('/' + '[a-z]*', '', string2) dataset.append(string3.split(',')) # print(dataset) def create_C1(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)) # print(len(create_C1(dataset))) 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 num_items = float(len(D)) retList = [] support_data = {} for key in ssCnt: support = ssCnt[key] / num_items if support >= min_support: retList.insert(0, key) support_data[key] = support return retList, support_data def apriori_gen(Lk, k): retList = [] len_Lk = len(Lk) for i in range(len_Lk): for j in range(i + 1, len_Lk): 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, min_support):换个格式实现此代码

抱歉，我不太明白您的问题是什么。如果您需要更改这段代码的格式，可以尝试使用以下格式化方式：

import csv
import re

class ReadCsv():
    def read_csv(self):
        item = []
        r = csv.reader(open("D:\桌面文件\作业文档\大数据分析\试验1\Groceries.csv", "r"))
        for csv_i in r:
            item.append(csv_i)
        item = item[1:]  # 从第一行开始获取
        return item

r = ReadCsv()
a = r.read_csv()

dataset = []
for list2 in a:
    string = list2[1].replace('{', '')
    string1 = string.replace('}', '')  # 去掉{}
    string2 = re.sub('/' + '[a-z]*' + ' ' + '[a-z]*', '', string1)  # 去掉/后面的那项商品
    string3 = re.sub('/' + '[a-z]*', '', string2)
    dataset.append(string3.split(','))

def create_C1(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 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
    num_items = float(len(D))
    retList = []
    support_data = {}
    for key in ssCnt:
        support = ssCnt[key] / num_items
        if support >= min_support:
            retList.insert(0, key)
        support_data[key] = support
    return retList, support_data

def apriori_gen(Lk, k):
    retList = []
    len_Lk = len(Lk)
    for i in range(len_Lk):
        for j in range(i + 1, len_Lk):
            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, min_support):
    C1 = create_C1(dataset)
    D = list(map(set, dataset))
    L1, support_data = scan_D(D, C1, min_support)
    L = [L1]
    k = 2
    while len(L[k - 2]) > 0:
        Ck = apriori_gen(L[k - 2], k)
        Lk, supK = scan_D(D, Ck, min_support)
        support_data.update(supK)
        L.append(Lk)
        k += 1
    return L, support_data