r关联规则先验

Question

hh<-read.csv("MT_MBR_CTGR_BUY_PTTRN_DAY.csv")

library(arules)

aa<-subset(hh, select=c(mbr_no,ctgr_flag_nm))

'data.frame':   643241 obs. of  2 variables:
 $ mbr_no      : num  2.01e+14 2.01e+14 2.01e+14 2.01e+14 2.01e+14 ...
 $ ctgr_flag_nm: Factor w/ 7 levels "그린핑거","기저귀",..: 1 4 4 4 4 4 4 4 7 7 ...

aa$mbr_no<-as.factor(aa$mbr_no)

rioter.transaction<-as(aa, "transactions")

rioter.transaction

transactions in sparse format with
 643241 transactions (rows) and
 178834 items (columns)

rules = apriori(rioter.transaction)

summary(rules)
set of 0 rules

Why do I have 0 rules?

I was tring to do read.transactions

or mbr_no type conversion in other ways

but it still doesn't work

how can I fix it?

Answer 1

Your variable mbr_no seems to be continuous with 178834-7 different values occurring in your data. You need to discretize the continuous variable. as.factor will not do this, but assign a level to each distinct value of the variable. So you should do something like this instead:

aa$mbr_no <- discretize(aa$mbr_no)

discretize is part of the arules package (see ? discretize ).