规则:如何在R或SQL WHERE子句中找到与lhs(rule)匹配的数据? [英] arules: How find the data matching an lhs(rule) in R or an SQL WHERE clause?

问题描述

我发现使用arule软件包有些棘手.我正在使用apriori算法查找关联规则；与arules文档中的示例类似.

I'm finding working with the arule package a bit tricky. I'm using the apriori algorithm to find association rules; something similar to an example in the arules documentation.

data("AdultUCI")
dim(AdultUCI)
AdultUCI[1:2,]

#Ignore everything from here to the last two lines, this is just data preparation

## remove attributes
AdultUCI[["fnlwgt"]] <- NULL
AdultUCI[["education-num"]] <- NULL

## map metric attributes
AdultUCI[[ "age"]] <- ordered(cut(AdultUCI[[ "age"]], c(15,25,45,65,100)),
                              labels = c("Young", "Middle-aged", "Senior", "Old"))

AdultUCI[[ "hours-per-week"]] <- ordered(cut(AdultUCI[[ "hours-per-week"]],
                                             c(0,25,40,60,168)),
                                         labels = c("Part-time", "Full-time", "Over-time", "Workaholic"))

AdultUCI[[ "capital-gain"]] <- ordered(cut(AdultUCI[[ "capital-gain"]],
                                           c(-Inf,0,median(AdultUCI[[ "capital-gain"]][AdultUCI[[ "capital-gain"]]>0]),
                                             Inf)), labels = c("None", "Low", "High"))

AdultUCI[[ "capital-loss"]] <- ordered(cut(AdultUCI[[ "capital-loss"]],
                                           c(-Inf,0, median(AdultUCI[[ "capital-loss"]][AdultUCI[[ "capital-loss"]]>0]),
                                             Inf)), labels = c("None", "Low", "High"))

#resume reading here
rules <- apriori(AdultUCI, parameter=list(support=0.6, confidence=0.75, minlen=4))
inspect(rules)

哪个返回以下四个规则

lhs                               rhs                             support confidence      lift
1 {race=White,                                                                                  
   capital-gain=None,                                                                           
   native-country=United-States} => {capital-loss=None}            0.680398  0.9457029 0.9920537
2 {race=White,                                                                                  
   capital-loss=None,                                                                           
   native-country=United-States} => {capital-gain=None}            0.680398  0.9083504 0.9901500
3 {race=White,                                                                                  
   capital-gain=None,                                                                           
   capital-loss=None}            => {native-country=United-States} 0.680398  0.9189249 1.0239581
4 {capital-gain=None,                                                                           
   capital-loss=None,                                                                           
   native-country=United-States} => {race=White}                   0.680398  0.8730100 1.0210133

我必须缺少一些东西:如何仅使用arules函数在源数据中找到与lhs规则匹配的行?

I must be missing something: how do you find the rows in the source data that match an lhs rule using just arules functions?

是否有一种简单的方法可以从lhs(规则)构建SQL WHERE子句?

Is there an easy way to build an SQL WHERE clause from the lhs(rules)?

谢谢

推荐答案

此答案基于以下答案:

This answer is based in the following answer: https://stats.stackexchange.com/questions/21340/finding-suitable-rules-for-new-data-using-arules. The solution is very slow, i´m not sure if will work for large aplications.

library(arules)

rules <- apriori(AdultUCI, parameter=list(support=0.4, confidence=0.75, minlen=4))
inspect(rules)

rec <- function(rules, data, iter){
  basket <- data[iter]
  rulesMatchLHS <- is.subset(rules@lhs,basket)
  suitableRules <-  rulesMatchLHS & !(is.subset(rules@rhs,basket))
  rules <- sort(rules[rulesMatchLHS], decreasing=TRUE, by="lift")
  as(head(rules, 1), "data.frame")
}

recom_loop <- function(rules, data){
  temp <- lapply(seq_along(data), function(x) rec(rules, data, x))
  temp <- do.call("rbind", temp)
  recom <- gsub(".*=> |\\{|\\}", "", temp$rules)
  as.data.frame(cbind(as(data, "data.frame"), recom))  
}

trans <- as(AdultUCI, "transactions")
recom <- recom_loop(rules, trans[1:50])

以下是一些示例输出:

head(recom)
  transactionID
1             1
2             2
3             3
4             4
5             5
6             6
                                                                                                                                                                                                                                                                     items
1      {age=Middle-aged,workclass=State-gov,education=Bachelors,marital-status=Never-married,occupation=Adm-clerical,relationship=Not-in-family,race=White,sex=Male,capital-gain=Low,capital-loss=None,hours-per-week=Full-time,native-country=United-States,income=small}
2 {age=Senior,workclass=Self-emp-not-inc,education=Bachelors,marital-status=Married-civ-spouse,occupation=Exec-managerial,relationship=Husband,race=White,sex=Male,capital-gain=None,capital-loss=None,hours-per-week=Part-time,native-country=United-States,income=small}
3         {age=Middle-aged,workclass=Private,education=HS-grad,marital-status=Divorced,occupation=Handlers-cleaners,relationship=Not-in-family,race=White,sex=Male,capital-gain=None,capital-loss=None,hours-per-week=Full-time,native-country=United-States,income=small}
4             {age=Senior,workclass=Private,education=11th,marital-status=Married-civ-spouse,occupation=Handlers-cleaners,relationship=Husband,race=Black,sex=Male,capital-gain=None,capital-loss=None,hours-per-week=Full-time,native-country=United-States,income=small}
5                {age=Middle-aged,workclass=Private,education=Bachelors,marital-status=Married-civ-spouse,occupation=Prof-specialty,relationship=Wife,race=Black,sex=Female,capital-gain=None,capital-loss=None,hours-per-week=Full-time,native-country=Cuba,income=small}
6        {age=Middle-aged,workclass=Private,education=Masters,marital-status=Married-civ-spouse,occupation=Exec-managerial,relationship=Wife,race=White,sex=Female,capital-gain=None,capital-loss=None,hours-per-week=Full-time,native-country=United-States,income=small}
              recom
1        race=White
2        race=White
3        race=White
4        race=White
5        race=White
6 capital-gain=None

这篇关于规则:如何在R或SQL WHERE子句中找到与lhs(rule)匹配的数据?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！