Apriori关联规则算法实现——python（anaconda）

导入需要的包

import pandas as pd
import numpy as np

读取csv文件

path = r"D:postgraduatestudydata_miningtestguanxinbing.csv"
data_datafram = pd.read_csv(path,encoding="gbk")

由于读取到的数据是datafram，所以先将pandas读取的数据转化为array

data_array = np.array(data_datafram)

然后转化为list形式

data_list =data_array.tolist()

获取列名（表头）

name = data_datafram.columns.values

按照0,1对应为列名

medicine = []
for i in range(356):
    num = data_list[i]
    case = zip(name,num)
    temp_list = []
    for j in case:
        if j[1] == 1.0:
            temp_list.append(j[0])
    medicine.append(temp_list)

导入包，进行关联规则分析

from efficient_apriori import apriori
transactions = medicine
itemsets,rules = apriori(transactions,
                         min_support = 0.1,
                         min_confidence= 0.7)
print(itemsets,'n')
for i in rules:
    print(i)

使用 pip install pip install efficient_apriori 安装pip install efficient_apriori

输出结果为