There is a sample data set with informations about diabetic people. I would like to find sequence rules (using arulesSequences library), which have only one element in rhs - "id_58". I am posting below code which download the data set (565 KB) and mine some rules. Could you tell me what should I do to reach what I scheduled?
library(arulesSequences)
download.file('http://staff.ii.pw.edu.pl/~gprotazi/dydaktyka/dane/diab_trans.data','diab_trans.data')
# some operations which result in transaction form of data
diab.df <- read.csv("diab_trans.data", header=TRUE, stringsAsFactors = FALSE)
write.table(diab.df, "diab_trans2.data", sep = "," , row.names = FALSE, col.names = FALSE )
diabSeq <- read_baskets(con = "diab_trans2.data", sep =",", info = c("sequenceID","eventID"))
# setting parameter, mining frequent sequential patterns and rules
seqParam = new ("SPparameter",support = 0.6, maxsize = 4, mingap=600, maxgap =150000, maxlen = 3)
patSeq= cspade(diabSeq,seqParam, control = list(verbose = TRUE, tidLists = FALSE, summary= TRUE))
seqRules = ruleInduction(patSeq,confidence = 0.8)
# inspect(seqRules)
# ideas which do not work
# finalSeq <- subset(seqRules, subset = (rhs %in% "id_58"))
# finalSeq <- subset(seqRules, rhs(seqRules) %in% c('id_58'))
Your item labels contain double quotes:
> itemLabels(rhs(seqRules))
[1] "\"id_33\"" "\"id_60\"" "\"id_62\"" "2" "\"id_64\"" "\"id_34\""
[7] "0" "3" "4" "5" "6" "7"
[13] "72" "8" "9" "\"id_57\"" "\"id_58\""
So you need to clean them or use:
finalSeq <- subset(seqRules, rhs(x) %ain% "\"id_58\"")