R dplyr to data table - Group and Filter

Question

I am trying to transform my data manipulation code from dplyr to data.table for speed reasons. I am almost there but missing the final step.

I have some sample data to replicate my problem.

c_dt = data.table(u_id=rep(c("u1", "u2"),each=5),
                  p_id=c("p1", "p1", "p1", "p2","p2", "p1", "p2", "p2", "p2", "p2" ), 
                  c_dt=c("2015-12-01", "2015-12-02", "2015-12-03", "2015-12-02",
                         "2015-12-05", "2015-12-02", "2015-12-03", "2015-12-04", 
                         "2015-12-05", "2015-12-06"))

I wish to identify the rows where u_id and p_id is duplicated; and keep only the row with the minimum c_dt (essentially keep the first instance). I use the following dplyr code for this:

c_df <- as.data.frame(c_dt)
cdedup_df <- c_df %>% group_by(p_id, u_id) %>% filter(c_dt == min(c_dt))

Which give the below output

> cdedup_df
Source: local data frame [4 x 3]
Groups: p_id, u_id

  u_id p_id       c_dt
1   u1   p1 2015-12-01
2   u1   p2 2015-12-02
3   u2   p1 2015-12-02
4   u2   p2 2015-12-03

I have the following data.table code that correctly identifies the required rows but I am unable to figure out how to just filter and the row as it is.

cdedup_dt <- c_dt[,c_dt == min(c_dt),by = list(u_id, p_id)]
cdedup_dt
    u_id p_id    V1
 1:   u1   p1  TRUE
 2:   u1   p1 FALSE
 3:   u1   p1 FALSE
 4:   u1   p2  TRUE
 5:   u1   p2 FALSE
 6:   u2   p1  TRUE
 7:   u2   p2  TRUE
 8:   u2   p2 FALSE
 9:   u2   p2 FALSE
10:   u2   p2 FALSE

Answer 1

Below my approach. I would expect it scales better for big dataset, as there is no min by group, just single sort which data.table makes very efficient and then subset first by group.

setorderv(c_dt, "c_dt")[, .SD[1L], .(u_id, p_id)]
# in data.table 1.9.7+ you can also use `head`
setorderv(c_dt, "c_dt")[, head(.SD, 1L), .(u_id, p_id)]

Below code includes validation of current other answers.
If OP will provide big dataset I can add benchmarks.

library(data.table)
c_dt = data.table(u_id=rep(c("u1", "u2"),each=5), p_id=c("p1", "p1", "p1", "p2","p2", "p1", "p2", "p2", "p2", "p2" ), c_dt=c("2015-12-01", "2015-12-02", "2015-12-03", "2015-12-02", "2015-12-05", "2015-12-02", "2015-12-03", "2015-12-04", "2015-12-05", "2015-12-06"))

zero = c_dt[, list(c_dt=min(c_dt)), by=list(u_id, p_id)]
ananda = c_dt[, list(c_dt = c_dt[c_dt == min(c_dt)]), by = .(u_id, p_id)]
tal = c_dt[, .SD[rank(c_dt, ties.method = c("first")) == 1],by = .(u_id, p_id)]
all.equal(zero, ananda)
#[1] TRUE
all.equal(ananda, tal)
#[1] TRUE

jan = setorderv(c_dt, "c_dt")[, .SD[1L], .(u_id, p_id)]
all.equal(tal, jan)
#[1] TRUE

Answer 2

Something like this should do the trick:

c_dt[, list(c_dt=min(c_dt)), by=list(u_id, p_id)]
##    u_id p_id       c_dt
## 1:   u1   p1 2015-12-01
## 2:   u1   p2 2015-12-02
## 3:   u2   p1 2015-12-02
## 4:   u2   p2 2015-12-03

Answer 3

So indeed you are very close. All you were missing is to pass .SD in the j column. Let's see how is works:

library(data.table)
c_dt = data.table(u_id=rep(c("u1", "u2"),each=5),  
                  p_id=c("p1", "p1", "p1", "p2","p2", "p1", "p2", "p2", "p2", "p2" ), 
                  c_dt=c("2015-12-01", "2015-12-02",  
                   "2015-12-03", "2015-12-02", "2015-12-05", 
                   "2015-12-02", "2015-12-03", "2015-12-04", 
                   "2015-12-05", "2015-12-06"))
c_dt
    u_id p_id       c_dt
 1:   u1   p1 2015-12-01
 2:   u1   p1 2015-12-02
 3:   u1   p1 2015-12-03
 4:   u1   p2 2015-12-02
 5:   u1   p2 2015-12-05
 6:   u2   p1 2015-12-02
 7:   u2   p2 2015-12-03
 8:   u2   p2 2015-12-04
 9:   u2   p2 2015-12-05
10:   u2   p2 2015-12-06

Now we will group by u_id and p_id and filter by the minimum value of c_df:

cdedup_dt <- c_dt[ , .SD[c_dt == min(c_dt)], by = .(u_id, p_id)]
cdedup_dt
   u_id p_id       c_dt
1:   u1   p1 2015-12-01
2:   u1   p2 2015-12-02
3:   u2   p1 2015-12-02
4:   u2   p2 2015-12-03

Note that .(u_id, p_id) is equal to list(u_id, p_id) and .SD refers to the Subset of the Data.table for each group. All you were missing is that .SD.
As mentioned by @zero323 min will keep duplicates (which basically means that we have some duplicate rows in our example). If you only wish to keep one record for each group a safer bet will be to use the rank function:

cdedup_dt <- c_dt[, .SD[rank(c_dt, ties.method = c("first")) == 1],by = .(u_id, p_id)]

cdedup_dt
   u_id p_id       c_dt
1:   u1   p1 2015-12-01
2:   u1   p2 2015-12-02
3:   u2   p1 2015-12-02
4:   u2   p2 2015-12-03