Geek asks and answers

Read position pairs associated with a column value

I am trying to solve this problem in R. I have the following data:

item   id
1      500
2      500
2      600
2      700
3      500
3      600

data.frame(item = c(1, 2, 2, 2, 3, 3),
           id = c(500, 500, 600, 700, 500, 600))

And I want to count the number of cases when a pair of elements is associated with the same identifier. So I want this conclusion:

item1    item2    count
    1        2        1
    2        3        2
    1        3        2

I tried to get closer to this with commands like:

x_agg = aggregate(x, by=list(x$id), c)

and then

x_agg_id = lapply(x_agg$item, unique)

thinking that I could count the appearance of each element. But the function byseems to create a list object, which I don't know how to manipulate. I hope there is an easier way ...

+5
source share
2 answers
# your data
df<-read.table(text="item   id
1      500
2      500
2      600
2      700
3      500
3      600",header=TRUE)


library(tnet)
item_item<-projecting_tm(df, method="sum")
names(item_item)<-c("item1","item2","count")

item_item

  #item1 item2 count
#1     1     2     1
#2     1     3     1
#3     2     1     1
#4     2     3     2
#5     3     1     1
#6     3     2     2

EDIT

how many identifiers and items do you have? You can always rename things. eg.

numberitems<-length(unique(df$id))+9000
items<-data.frame(item=unique(df$item),newitems=c(9000:(numberitems-1)))
numberids<-length(unique(df$id))+1000
ids<-data.frame(id=unique(df$id),newids=c(1000:(numberids-1)))
newdf<-merge(df,items,by="item")
newdf<-merge(newdf,ids,by="id")
DF<-data.frame(item=newdf$newitems,id=newdf$newids)

library(tnet)
item_item<-projecting_tm(DF, method="sum")
names(item_item)<-c("item1","item2","count")

then merge the original names later ....

+3
source

, , @user1317221_G , . 2 3 4 , item1 = 2, item2 = 3 item1 = 3, item2 = 2.

combn. , , , , .

.

  • , , .

    myfun = function(x) { apply(combn(x, 2), 2, paste, sep="", collapse="") }

  • split() item id lapply id.

    temp = split(df$item, df$id)
# Drop any list items that have only one value--combn won't work there!
temp = temp[-(which(sapply(temp,function(x) length(x) == 1),
                    arr.ind=TRUE))]
temp1 = lapply(temp, function(x) myfun(unique(x)))

  • unlist, table .

    table(unlist(temp1))
# 
# 12 13 23 
#  1  1  2

data.frame, .

data.frame(table(unlist(temp)))
#   Var1 Freq
# 1   12    1
# 2   13    1
# 3   23    2

Update

, , :

myfun = function(x) { apply(combn(x, 2), 2, paste, sep="", collapse=",") }
temp = split(df$item, df$id)
temp = temp[-(which(sapply(temp,function(x) length(x) == 1),
                    arr.ind=TRUE))]
temp1 = lapply(temp, function(x) myfun(unique(x)))
temp1 = data.frame(table(unlist(temp1)))
OUT = data.frame(do.call(rbind, 
                         strsplit(as.character(temp1$Var1), ",")),
                 temp1$Freq)
names(OUT) = c("item1", "item2", "count")
OUT
#   item1 item2 count
# 1     1     2     1
# 2     1     3     1
# 3     2     3     2
+2

More articles:


All Articles