Count distinct by group- moving window

Question

Let\'s say I have a dataset contain visits in a hospital. My goal is to generate a variable that counts the number of unique patients the visitor has seen before at the date

Answer 1

We can use dplyr

library(dplyr)   
df1 %>%
   group_by(visitor) %>%
    mutate(goal = cummax(match(patient, unique(patient))))
    #or with factor
    # mutate(goal1 = cummax(as.integer(factor(patient, levels = unique(patient)))))

# A tibble: 10 x 4
# Groups:   visitor [1]
#   visitor visitdt   patient  goal
#              
# 1  125469 1/12/2018   15200     1
# 2  125469 1/19/2018   15200     1
# 3  125469 2/16/2018   15200     1
# 4  125469 2/23/2018   52607     2
# 5  125469 3/9/2018    52607     2
# 6  125469 3/16/2018   52607     2
# 7  125469 3/23/2018   15200     2
# 8  125469 3/29/2018   15200     2
# 9  125469 3/30/2018   20589     3
#10  125469 4/6/2018    20589     3

data

df1 <- structure(list(visitor = c(125469L, 125469L, 125469L, 125469L, 
125469L, 125469L, 125469L, 125469L, 125469L, 125469L), visitdt = c("1/12/2018", 
"1/19/2018", "2/16/2018", "2/23/2018", "3/9/2018", "3/16/2018", 
"3/23/2018", "3/29/2018", "3/30/2018", "4/6/2018"), patient = c(15200L, 
15200L, 15200L, 52607L, 52607L, 52607L, 15200L, 15200L, 20589L, 
20589L), goal = c(1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L)),
class = "data.frame", row.names = c(NA, 
-10L))