Create a new dataframe with the all possible combinations - r

Question

Having a dataframe like this:
data.frame(previous = c(1,2,2,1,3,3), next = c(1,1,2,3,1,3), id = c(1,2,3,4,5,6))
How is it possible to exatract a data frame which will check the previous and next columns and create 9 new columns which will have 1 only if the combination of previous and next exist. Example if previous if 2 and next 1 the combination is 2 1 and receives one.
Example of expected output:
data.frame(previous = c(1,2,2,1,3,3), next = c(1,1,2,3,1,3),
col1_1 = c(1,0,0,0,0,0),
col1_2 = c(0,0,0,0,0,0),
col1_3 = c(0,0,0,1,0,0),
col2_1 = c(0,1,0,0,0,0),
col2_2 = c(0,0,1,0,0,0),
col2_3 = c(0,0,0,0,0,0),
col3_1 = c(0,0,0,0,1,0),
col3_2 = c(0,0,0,0,0,0),
col3_3 = c(0,0,0,0,0,1), id = c(1,2,3,4,5,6))

Answer 1

You could use expand.grid to get all the combinations.
Assuming your data frame is called df and the column next is actually called next. to avoid clashing with the keyword next:
as.data.frame(apply(expand.grid(1:3, 1:3), 1, function(x) {
as.numeric(x[1] == df$previous & x[2] == df$next.)}))
#> V1 V2 V3 V4 V5 V6 V7 V8 V9
#> 1 1 0 0 0 0 0 0 0 0
#> 2 0 1 0 0 0 0 0 0 0
#> 3 0 0 0 0 1 0 0 0 0
#> 4 0 0 0 0 0 0 1 0 0
#> 5 0 0 1 0 0 0 0 0 0
#> 6 0 0 0 0 0 0 0 0 1

Answer 2

An step by step approach might be the following one. I have changed the next column name for next1 to avoid problems:
AllComb<-expand.grid(unique(df$previous),unique(df$next1))# Creating all possible combinations
myframe <- matrix(rep(0,nrow(AllComb)*nrow(df)),ncol=nrow(AllComb),nrow =nrow(df))
colnames(myframe)<-paste("col_",AllComb$Var1,"_",AllComb$Var2, sep ="")
for(id_row in 1:ncol(df)){
myvec <- df[id_row,]
Word <- paste("col_",myvec[1],"_",myvec[2], sep ="")# Finding Word
Colindex <-which(colnames(myframe)==Word) #Finding Column index
myframe[id_row, Colindex] <-1 # Replacing in column index and vetor
}
dfRes<-cbind(previous =df$previous, "next"= df$next1, myframe, id=df$id)
# previous next col_1_1 col_2_1 col_3_1 col_1_2 col_2_2 col_3_2 col_1_3 col_2_3 col_3_3 id
# [1,] 1 1 1 0 0 0 0 0 0 0 0 1
# [2,] 2 1 0 1 0 0 0 0 0 0 0 2
# [3,] 2 2 0 0 0 0 1 0 0 0 0 3
# [4,] 1 3 0 0 0 0 0 0 0 0 0 4
# [5,] 3 1 0 0 0 0 0 0 0 0 0 5
# [6,] 3 3 0 0 0 0 0 0 0 0 0 6

Answer 3

Inside a by you could use a switch, because your values are nicely consecutive 1:3. Finally we merge to get the result.
tmp <- by(dat, dat$next., function(x) {
x1 <- x$previous
o <- `colnames<-`(t(sapply(x1, function(z)
switch(z, c(1, 0, 0), c(0, 1, 0), c(0, 0, 1)))),
paste(el(x1), 1:3, sep="_"))
cbind(x, col=o)
})
res <- Reduce(function(...) merge(..., all=TRUE), tmp)
res[is.na(res)] <- 0 ## set NA to zero if wanted
Result
res[order(res$id),] ## order by ID if needed
# previous next. id col.1_1 col.1_2 col.1_3 col.2_1 col.2_2 col.2_3
# 1 1 1 1 1 0 0 0 0 0
# 3 2 1 2 0 1 0 0 0 0
# 4 2 2 3 0 0 0 0 1 0
# 2 1 3 4 1 0 0 0 0 0
# 5 3 1 5 0 0 1 0 0 0
# 6 3 3 6 0 0 1 0 0 0
Data
dat <- structure(list(previous = c(1, 2, 2, 1, 3, 3), next. = c(1, 1,
2, 3, 1, 3), id = c(1, 2, 3, 4, 5, 6)), class = "data.frame", row.names = c(NA,
-6L))
Note: next as column name is not particularly a good idea, since it has a special meaning in R.

Answer 4

Here is a tidyverse approach:
library(tidyr)
library(dplyr)
df %>%
rowid_to_column() %>%
complete(previous, nxt) %>%
unite(col , previous, nxt, sep = "_", remove = FALSE) %>%
pivot_wider(names_from = col, values_from = rowid, values_fn = list(rowid = ~1), values_fill = list(rowid = 0)) %>%
na.omit() %>%
arrange(id)
# A tibble: 6 x 12
previous nxt id `1_1` `1_2` `1_3` `2_1` `2_2` `2_3` `3_1` `3_2` `3_3`
<dbl> <dbl> <dbl> <int> <int> <int> <int> <int> <int> <int> <int> <int>
1 1 1 1 1 0 0 0 0 0 0 0 0
2 2 1 2 0 0 0 1 0 0 0 0 0
3 2 2 3 0 0 0 0 1 0 0 0 0
4 1 3 4 0 0 1 0 0 0 0 0 0
5 3 1 5 0 0 0 0 0 0 1 0 0
6 3 3 6 0 0 0 0 0 0 0 0 1

Answer 5

This is another tidyverse solution that differ a little (maybe more concise) from #H1's one.
library(dplyr)
library(tidyr)
df %>%
mutate(n = 1) %>%
complete(id, previous, next., fill = list(n = 0)) %>%
unite(col, previous, next.) %>%
pivot_wider(names_from = col, names_prefix = "col", values_from = n) %>%
right_join(df)
# # A tibble: 6 x 12
# id col1_1 col1_2 col1_3 col2_1 col2_2 col2_3 col3_1 col3_2 col3_3 previous next.
# <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
# 1 1 1 0 0 0 0 0 0 0 0 1 1
# 2 2 0 0 0 1 0 0 0 0 0 2 1
# 3 3 0 0 0 0 1 0 0 0 0 2 2
# 4 4 0 0 1 0 0 0 0 0 0 1 3
# 5 5 0 0 0 0 0 0 1 0 0 3 1
# 6 6 0 0 0 0 0 0 0 0 1 3 3

Answer 6

You can try the code below
dfout <- within(df,
col <- `colnames<-`(t(sapply((Previous-1)*3+Next,
function(v) replace(rep(0,9),v,1))),
do.call(paste,c(expand.grid(1:3,1:3),sep = "_"))))
such that
> dfout
Previous Next id col.1_1 col.2_1 col.3_1 col.1_2 col.2_2 col.3_2 col.1_3 col.2_3 col.3_3
1 1 1 1 1 0 0 0 0 0 0 0 0
2 2 1 2 0 0 0 1 0 0 0 0 0
3 2 2 3 0 0 0 0 1 0 0 0 0
4 1 3 4 0 0 1 0 0 0 0 0 0
5 3 1 5 0 0 0 0 0 0 1 0 0
6 3 3 6 0 0 0 0 0 0 0 0 1