R_Studio(关联)使用apriori函数简单查看数据存在多少条关联规则,并按支持度降序排序输出
查看数据menu_orders.txt文件存在多少条关联规则,并按支持度降序排序输出
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
#导入arules包 install.packages("arules") library ( arules ) setwd('D:\\data') Gary<- read.transactions("menu_orders.txt", format = "basket", sep=",") summary(Gary) #查看部分规则 inspect(Gary) #支持度0.2,置信度0.5 rules0=apriori(Gary,parameter=list(support=0.2,confidence=0.5)) #按支持度降序排序输出 rules0.sorted_sup = sort(rules0, by="support") #读取rules0中存在多少条数据 rules0 inspect(rules0)
apriori函数
apriori(data, parameter = NULL, appearance = NULL, control = NULL)
data:数据
parameter 设置参数,默认情况下parameter=list(supp=0.1,conf=0.8,maxlen=10,minlen=1,target=”rules”)
supp: 支持度(support)
conf: 置信度(confidence)
maxlen,minlen: 每个项集所含项数的最大最小值(lhs+rhs的长度)
target: “rules”或“frequent itemsets”(输出关联规则/频繁项集)
apperence: 对先决条件X(lhs),关联结果Y(rhs)中具体包含哪些项进行限制,如:设置lhs=beer,将仅输出lhs含有beer这一项的关联规则。默认情况下,所有项都将无限制出现。
control: 控制函数性能,如可以设定对项集进行升序sort=1或降序sort=-1排序,是否向使用者报告进程(verbose=F/T)
排序:
通过支持度控制:rules.sorted_sup = sort(rules, by=”support”)
通过置信度控制:rules.sorted_con = sort(rules, by=”confidence”)
通过提升度控制:rules.sorted_lift = sort(rules, by=”lift”)
![](https://images.cnblogs.com/OutliningIndicators/ContractedBlock.gif)
read.transactions(file, format =c("basket", "single"), sep = NULL,
cols = NULL, rm.duplicates =FALSE, encoding = "unknown")
file:文件名,对应click_detail中的“click_detail.txt”
format:文件格式,可以有两种,分别为“basket”,“single”,click_detail.txt中用的是basket。basket: basket就是篮子,一个顾客买的东西都放到同一个篮子,所有顾客的transactions就是一个个篮子的组合 结果。如下形式,每条交易都是独立的。single: single的意思,顾名思义,就是单独的交易,简单说,交易记录为:顾客1买了产品1, 顾客1买了产品2,顾客2买了产品3……(产品1,产品2,产品3中可以是单个产品,也可以是多个产品)
sep:文件中数据是怎么被分隔的,默认为空格,click_detail里面用逗号分隔
cols:对basket, col=1,表示第一列是数据的transaction ids(交易号),如果col=NULL,则表示数据里面没有交易号这一列;对single,col=c(1,2)表示第一列是transaction ids,第二列是item ids
rm.duplicates:是否移除重复项,默认为FALSE
encoding:写到这里研究了encoding是什么意思,发现前面txt可以不是”ANSI”类型,如果TXT是“UTF-8”,写encoding=”UTF-8”。
实现过程
读取数据并展示
> setwd('D:\\data') > Gary<- read.transactions("menu_orders.txt", format = "basket", sep=",") > summary(Gary)
transactions as itemMatrix in sparse format with 10 rows (elements/itemsets/transactions) #10行(元素/项集/事务) 5 columns (items) and a density of 0.54 #5列(项)和0.54的密度 most frequent items: b a c e d (Other) 8 7 7 3 2 0 element (itemset/transaction) length distribution: #元素(项集/事务)长度分布 sizes 2 3 4 5 3 2 Min. 1st Qu. Median Mean 3rd Qu. Max. 2.0 2.0 2.5 2.7 3.0 4.0 includes extended item information - examples: labels 1 a 2 b 3 c
查看部分规则
> inspect(Gary) items [1] {a,c,e} [2] {b,d} [3] {b,c} [4] {a,b,c,d} [5] {a,b} [6] {b,c} [7] {a,b} [8] {a,b,c,e} [9] {a,b,c} [10] {a,c,e}
支持度0.2,置信度0.5
> rules0=apriori(Gary,parameter=list(support=0.2,confidence=0.5)) Apriori Parameter specification: confidence minval smax arem aval originalSupport maxtime support minlen maxlen target ext 0.5 0.1 1 none FALSE TRUE 5 0.2 1 10 rules FALSE Algorithmic control: #算法控制: filter tree heap memopt load sort verbose #过滤树堆 0.1 TRUE TRUE FALSE TRUE 2 TRUE Absolute minimum support count: 2 #绝对最小支持计数:2 set item appearances ...[0 item(s)] done [0.00s]. set transactions ...[5 item(s), 10 transaction(s)] done [0.00s]. sorting and recoding items ... [5 item(s)] done [0.00s]. creating transaction tree ... done [0.00s]. checking subsets of size 1 2 3 done [0.00s]. writing ... [18 rule(s)] done [0.00s]. creating S4 object ... done [0.00s].
按支持度降序排序输出
> rules0.sorted_sup = sort(rules0, by="support") > rules0 set of 18 rules
#根据支持度对求得的关联规则子集进行查看 > inspect(rules0) lhs rhs support confidence lift count [1] {} => {c} 0.7 0.7000000 1.0000000 7 [2] {} => {b} 0.8 0.8000000 1.0000000 8 [3] {} => {a} 0.7 0.7000000 1.0000000 7 [4] {d} => {b} 0.2 1.0000000 1.2500000 2 [5] {e} => {c} 0.3 1.0000000 1.4285714 3 [6] {e} => {a} 0.3 1.0000000 1.4285714 3 [7] {c} => {b} 0.5 0.7142857 0.8928571 5 [8] {b} => {c} 0.5 0.6250000 0.8928571 5 [9] {c} => {a} 0.5 0.7142857 1.0204082 5 [10] {a} => {c} 0.5 0.7142857 1.0204082 5 [11] {b} => {a} 0.5 0.6250000 0.8928571 5 [12] {a} => {b} 0.5 0.7142857 0.8928571 5 [13] {c,e} => {a} 0.3 1.0000000 1.4285714 3 [14] {a,e} => {c} 0.3 1.0000000 1.4285714 3 [15] {a,c} => {e} 0.3 0.6000000 2.0000000 3 [16] {b,c} => {a} 0.3 0.6000000 0.8571429 3 [17] {a,c} => {b} 0.3 0.6000000 0.7500000 3 [18] {a,b} => {c} 0.3 0.6000000 0.8571429 3