Creating a new column conditionally based on previous n rows

Question

I have a data frame set up like the following:

 df <- data.frame("id" = c(111,111,111,222,222,222,222,333,333,333,333), 
                  "Location" = c("A","B","A","A","C","B","A","B","A","A","A"), 
                  "Encounter" = c(1,2,3,1,2,3,4,1,2,3,4))

      id Location Encounter
1  111        A         1
2  111        B         2
3  111        A         3
4  222        A         1
5  222        C         2
6  222        B         3
7  222        A         4
8  333        B         1
9  333        A         2
10 333        B         3
11 333        A         4

I'm basically trying to create a binary flag a location is in a previous Encounter for each id group. So it would look like:

    id Location Encounter Flag
1  111        A         1    0
2  111        B         2    0
3  111        A         3    1
4  222        A         1    0
5  222        C         2    0
6  222        B         3    0
7  222        A         4    1
8  333        B         1    0
9  333        A         2    0
10 333        B         3    1
11 333        A         4    1

I was trying to figure out how to do an if statement like:

library(dplyr)

df$Flag <- case_when((df$id - lag(df$id)) == 0 ~ 
                case_when(df$Location == lag(df$Location, 1) | 
                          df$Location == lag(df$Location, 2) | 
                          df$Location == lag(df$Location, 3) ~ 1, T ~ 0), T ~ 0)

    id Location Flag
1  111        A    0
2  111        B    0
3  111        A    1
4  222        A    0
5  222        C    0
6  222        B    0
7  222        A    1
8  333        B    0
9  333        A    1
10 333        B    1
11 333        A    1

But this has the issue where Row 9 is getting incorrectly assigned a 1, and there are cases with 15+ encounters in the actual data so this becomes pretty cumbersome. I was hoping to find a way to do something like

lag(df$Location, 1:df$Encounter)

But I know lag() needs an integer for k, so that specific command wouldn't work.

Answer 1

An option with duplicated

library(dplyr)
df %>% 
  group_by(id) %>% 
  mutate(Flag = +(duplicated(Location)))
# A tibble: 11 x 4
# Groups:   id [3]
#      id Location Encounter  Flag
#   <dbl> <fct>        <dbl> <int>
# 1   111 A                1     0
# 2   111 B                2     0
# 3   111 A                3     1
# 4   222 A                1     0
# 5   222 C                2     0
# 6   222 B                3     0
# 7   222 A                4     1
# 8   333 B                1     0
# 9   333 A                2     0
#10   333 A                3     1
#11   333 A                4     1

Answer 2

In base R, we can use ave grouped by id and Location and turn all the values from second row of the group to 1.

df$Flag <- as.integer(with(df, ave(Encounter, id, Location, FUN = seq_along) > 1))
df

#    id Location Encounter Flag
#1  111        A         1    0
#2  111        B         2    0
#3  111        A         3    1
#4  222        A         1    0
#5  222        C         2    0
#6  222        B         3    0
#7  222        A         4    1
#8  333        B         1    0
#9  333        A         2    0
#10 333        A         3    1
#11 333        A         4    1

Using dplyr, that would be

library(dplyr)

df %>%  group_by(id, Location) %>%  mutate(Flag = as.integer(row_number() > 1))

Answer 3

A more generic data.table solution would be using .N or rowid:

library(data.table)

setDT(dt)[, Flag := +(rowid(id, Location)>1)][]

or

setDT(df)[, Flag := +(seq_len(.N)>1), .(id, Location)][]

#>      id Location  Encounter Flag
#> 1:  111        A         1    0
#> 2:  111        B         2    0
#> 3:  111        A         3    1
#> 4:  222        A         1    0
#> 5:  222        C         2    0
#> 6:  222        B         3    0
#> 7:  222        A         4    1
#> 8:  333        B         1    0
#> 9:  333        A         2    0
#> 10: 333        A         3    1
#> 11: 333        A         4    1

Answer 4

Using data.table:

library(data.table)

dt[, flag:=1]
dt[, flag:=cumsum(flag), by=.(id,Location)]
dt[, flag:=ifelse(flag>1,1,0)]

Data:

dt <- data.table("id" = c(111,111,111,222,222,222,222,333,333,333,333), 
                 "Location" = c("A","B","A","A","C","B","A","B","A","A","A"),
                 "Encounter" = c(1,2,3,1,2,3,4,1,2,3,4))