R语言 - 关联规则 - R语言教程-OStack程序员社区-中国程序员成长平台

OStack程序员社区-中国程序员成长平台 › 门户 › 编程› R语言›R语言教程

R语言 - 关联规则

原作者: [db:作者] 来自: [db:来源] 收藏邀请

> library(arules)
> library(arulesViz)

#提取数据Groceries
> data(Groceries)

#观察数据Groceries全貌
> summary(Groceries)

#运行apriori算法关联规则自动收敛，起始项集数设置为1，最小支持度阈值设置为0.001，最小置信度为0.6，要挖掘关联类型的目标为"rules"
> rules <- apriori(Groceries,parameter = list(minlen = 1,support=0.001,confidence=0.6,target="rules"))

#信息writing显示了已关联规则2918条
Apriori


Parameter specification:
 confidence minval smax arem aval originalSupport maxtime
 0.6 0.1 1 none FALSE TRUE 5
 support minlen maxlen target ext
 0.001 1 10 rules FALSE


Algorithmic control:
 filter tree heap memopt load sort verbose
 0.1 TRUE TRUE FALSE TRUE 2 TRUE


Absolute minimum support count: 9 


set item appearances ...[0 item(s)] done [0.00s].

set transactions ...[169 item(s), 9835 transaction(s)] done [0.00s].

sorting and recoding items ... [157 item(s)] done [0.00s].

creating transaction tree ... done [0.00s].

checking subsets of size 1 2 3 4 5 6 done [0.01s].

writing ... [2918 rule(s)] done [0.00s]. ######

creating S4 object ... done [0.00s].

#作成2918条规则散点图,横轴表示支持度，纵轴表示置信度，阴影像表示提升度
> plot(rules)

#获取前10条提升度最高的规则信息
> inspect(head(sort(rules,by="lift"),10))

 lhs rhs support confidence lift count
[1] {Instant food products, 
 soda} => {hamburger meat} 0.001220132 0.6315789 18.995654 12
[2] {soda, 
 popcorn} => {salty snack} 0.001220132 0.6315789 16.697793 12
[3] {ham, 
 processed cheese} => {white bread} 0.001931876 0.6333333 15.045491 19
[4] {tropical fruit, 
 other vegetables,  
 yogurt, 
 white bread} => {butter} 0.001016777 0.6666667 12.030581 10
[5] {hamburger meat, 
 yogurt, 
 whipped/sour cream} => {butter} 0.001016777 0.6250000 11.278670 10
[6] {tropical fruit, 
 other vegetables, 
 whole milk, 
 yogurt, 
 domestic eggs} => {butter} 0.001016777 0.6250000 11.278670 10
[7] {liquor, 
 red/blush wine} => {bottled beer} 0.001931876 0.9047619 11.235269 19
[8] {other vegetables, 
 butter, 
 sugar} => {whipped/sour cream} 0.001016777 0.7142857 9.964539 10
[9] {whole milk, 
 butter, 
 hard cheese} => {whipped/sour cream} 0.001423488 0.6666667 9.300236 14
[10] {tropical fruit, 
 other vegetables, 
 butter, 
 fruit/vegetable juice} => {whipped/sour cream} 0.001016777 0.6666667 9.300236 10

#从rules的2918条规则里提取 置信度>0.9 的规则127条
> confidentRules <- rules[quality(rules)$confidence > 0.9]
> confidentRules


set of 127 rules

#生成confidentRules内127条规则的矩阵图，可视化每个矩阵内含有规则的数量，置信度，提升度
> plot(confidentRules,method = "matrix",measure = c("lift","confidence"),control = list(reorder=TRUE))




#将提升度最高的5条规则带入函数highLiftRules中
> highLiftRules <- head(sort(rules,by="lift"),5)

#将提升度最高的5条规则进行可视化，由LHS指向RHS，大小表示支持度，颜色表示提升度
> plot(highLiftRules,method = "graph",control = list(type = "items"))