R 语言 Apriori 关联规则算法

1、加载数据集，按照设定参数进行计算

"whole milk" 全脂牛奶

"other vegetables" 其他蔬菜

"rolls/buns" 面包卷

"yogurt" 酸奶

"soda" 汽水

"bottled water" 瓶装水

R 复制代码

# 安装并加载包
#install.packages("arules")
library(arules)

#Apriori 要求数据为事务型数据（transactions），两种常见来源：
#直接用 Groceries 内置购物篮数据集（最常用示例）
#普通数据框转换为事务格式
# 加载内置购物篮数据
data(Groceries)

# 查看所有商品列表
itemLabels(Groceries)

# 查看前 5 条交易的项集
inspect(head(Groceries, 5))

# 查看所有商品的出现频率（从高到低）
print(itemFrequencyPlot(Groceries, topN = 10))

# 运行Apriori算法
rules <- apriori(
  data = Groceries,
  parameter = list(
    supp = 0.01,    # 最小支持度1%
    conf = 0.3,     # 最小置信度30%
    target = "rules"
  )
)

# 查看结果
inspect(head(rules, 10))

2、查看结果

> inspect(head(rules, 10))

lhs rhs support confidence coverage lift count

$1$ {hard cheese} => {whole milk} 0.01006609 0.4107884 0.02450432 1.607682 99

$2$ {butter milk} => {other vegetables} 0.01037112 0.3709091 0.02796136 1.916916 102

$3$ {butter milk} => {whole milk} 0.01159126 0.4145455 0.02796136 1.622385 114

$4$ {ham} => {whole milk} 0.01148958 0.4414062 0.02602949 1.727509 113

$5$ {sliced cheese} => {whole milk} 0.01077783 0.4398340 0.02450432 1.721356 106

$6$ {oil} => {whole milk} 0.01128622 0.4021739 0.02806304 1.573968 111

$7$ {onions} => {other vegetables} 0.01423488 0.4590164 0.03101169 2.372268 140

$8$ {onions} => {whole milk} 0.01209964 0.3901639 0.03101169 1.526965 119

$9$ {berries} => {yogurt} 0.01057448 0.3180428 0.03324860 2.279848 104

$10$ {berries} => {other vegetables} 0.01026945 0.3088685 0.03324860 1.596280 101

R 复制代码

# 按提升度排序，看强关联规则
rules_sorted <- sort(rules, by = "lift", decreasing = TRUE)
inspect(head(rules_sorted, 5))

> inspect(head(rules_sorted, 5))

lhs rhs support confidence coverage lift

$1$ {citrus fruit, other vegetables} => {root vegetables} 0.01037112 0.3591549 0.02887646 3.295045

$2$ {tropical fruit, other vegetables} => {root vegetables} 0.01230300 0.3427762 0.03589222 3.144780

$3$ {beef} => {root vegetables} 0.01738688 0.3313953 0.05246568 3.040367

$4$ {citrus fruit, root vegetables} => {other vegetables} 0.01037112 0.5862069 0.01769192 3.029608

$5$ {tropical fruit, root vegetables} => {other vegetables} 0.01230300 0.5845411 0.02104728 3.020999

count

$1$ 102

$2$ 121

$3$ 171

$4$ 102

$5$ 121

3、散点图

R 复制代码

#install.packages("arulesViz")
library(arulesViz)

# 散点图：支持度/置信度/提升度（映射为颜色）
plot(rules, measure = c("support", "confidence"), shading = "lift")

4、网络图

R 复制代码

# 网络图展示规则关系，前10条规则
plot(head(rules_sorted, 10), method = "graph")

R 复制代码

# 只找结果包含"牛奶"的规则
milk_rules <- subset(rules, rhs %in% "whole milk")
inspect(milk_rules)

5、数据转事物

R 复制代码

#-------------------数据转事物--------------
# 示例原始数据框
df <- data.frame(
  T1 = c("牛奶", "面包", "鸡蛋"),
  T2 = c("面包", "可乐"),
  T3 = c("牛奶", "可乐", "薯片"),
  T4 = c("牛奶", "面包", "可乐")
)

# 转为事务格式
trans <- as(df, "transactions")

# 执行Apriori
rules2 <- apriori(trans, parameter = list(supp = 0.2, conf = 0.5))
inspect(rules2)

#查看前5条规则
inspect(head(sort(rules2,by = "lift", decreasing = TRUE),5))