The number of unique values ​​in the rental date range for R

Question

This question already has an answer for SQL , and I was able to implement this solution in R with sqldf. However, I could not find a way to implement it using data.table.

The challenge is to calculate the individual values ​​of a single column within the range of rental dates, for example. (and quoting directly from a related question) if the data looked like this:

Date   | email 
-------+----------------
1/1/12 | [e-mail]
1/1/12 | [e-mail]
1/1/12 | [e-mail]
1/2/12 | [e-mail]
1/2/12 | [e-mail]
1/3/12 | [e-mail]
1/4/12 | [e-mail]
1/5/12 | [e-mail]
1/5/12 | [e-mail]
1/6/12 | [e-mail]
1/6/12 | [e-mail]
1/6/12 | [e-mail]

Then the result will look something like this if we used a 3 day date period

date   | count(distinct email)
-------+------
1/1/12 | 3
1/2/12 | 3
1/3/12 | 3
1/4/12 | 3
1/5/12 | 2
1/6/12 | 2

Here is the code to create the same data in R using data.table:

date <- as.Date(c('2012-01-01','2012-01-01','2012-01-01',
                  '2012-01-02','2012-01-02','2012-01-03',
                  '2012-01-04','2012-01-05','2012-01-05',
                  '2012-01-06','2012-01-06','2012-01-06'))
email <- c('[e-mail]', '[e-mail]','[e-mail]',
           '[e-mail]', '[e-mail]','[e-mail]',
           '[e-mail]','[e-mail]','[e-mail]',
           '[e-mail]','[e-mail]','[e-mail]')
dt <- data.table(date, email)

Any help on this would be greatly appreciated. Thank!

Change 1:

, , . - SQL, . , , :

SELECT day
     ,(SELECT count(DISTINCT email)
       FROM   tbl
       WHERE  day BETWEEN t.day - 2 AND t.day -- period of 3 days
      ) AS dist_emails
FROM   tbl t
WHERE  day BETWEEN '2012-01-01' AND '2012-01-06'  
GROUP  BY 1
ORDER  BY 1;

2: , @MichaelChirico, @jangorecki:

# The data
> dim(temp)
[1] 2627785       4
> head(temp)
         date category1 category2 itemId
1: 2013-11-08         0         2   1713
2: 2013-11-08         0         2  90485
3: 2013-11-08         0         2  74249
4: 2013-11-08         0         2   2592
5: 2013-11-08         0         2   2592
6: 2013-11-08         0         2    765
> uniqueN(temp$itemId)
[1] 13510
> uniqueN(temp$date)
[1] 127

# Timing for data.table
> system.time(dtTime <- temp[,
+   .(count = temp[.(seq.Date(.BY$date - 6L, .BY$date, "day"), 
+   .BY$category1, .BY$category2 ), uniqueN(itemId), nomatch = 0L]), 
+  by = c("date","category1","category2")])
   user  system elapsed 
  6.913   0.130   6.940 
> 
# Time for sqldf
> system.time(sqlDfTime <- 
+ sqldf(c("create index ldx on temp(date, category1, category2)",
+ "SELECT date, category1, category2,
+ (SELECT count(DISTINCT itemId)
+   FROM   temp
+   WHERE category1 = t.category1 AND category2 = t.category2 AND
+   date BETWEEN t.date - 6 AND t.date 
+   ) AS numItems
+ FROM temp t
+ GROUP BY date, category1, category2
+ ORDER BY 1;"))
   user  system elapsed 
 87.225   0.098  87.295 

, data.table, sqldf 12,5 . !

Answer 1

- , non-equijoins data.table.

dt[dt[ , .(date3=date, date2 = date - 2, email)], 
   on = .(date >= date2, date<=date3), 
   allow.cartesian = TRUE
   ][ , .(count = uniqueN(email)), 
      by = .(date = date + 2)]
#          date V1
# 1: 2011-12-30  3
# 2: 2011-12-31  3
# 3: 2012-01-01  3
# 4: 2012-01-02  3
# 5: 2012-01-03  1
# 6: 2012-01-04  2

, , , , dt date, date 2 . , , date = date + 2 .

---

:

setkey(dt, date)

dt[ , .(count = dt[.(seq.Date(.BY$date - 2L, .BY$date, "day")),
                   uniqueN(email), nomatch = 0L]), by = date]

Answer 2

non-equi data.table, v1.9.7, :

dt[.(date3=unique(dt$date2)), .(count=uniqueN(email)), on=.(date>=date3, date2<=date3), by=.EACHI]
#          date      date2 count
# 1: 2011-12-30 2011-12-30     3
# 2: 2011-12-31 2011-12-31     3
# 3: 2012-01-01 2012-01-01     3
# 4: 2012-01-02 2012-01-02     3
# 5: 2012-01-03 2012-01-03     1
# 6: 2012-01-04 2012-01-04     2