dplyr summarize with subtotals

Also possible by simply joining the two group results:

cyl_carb <- mtcars %>% group_by(cyl,carb) %>% summarize(mean(disp))
cyl <- mtcars %>% group_by(cyl) %>% summarize(mean(disp))
joined <- full_join(cyl_carb, cyl)
result <- arrange(joined, cyl)
result

gives:

Source: local data frame [12 x 3]
Groups: cyl [3]

     cyl  carb mean(disp)
   (dbl) (dbl)      (dbl)
1      4     1    91.3800
2      4     2   116.6000
3      4    NA   105.1364
4      6     1   241.5000
5      6     4   163.8000
6      6     6   145.0000
7      6    NA   183.3143
8      8     2   345.5000
9      8     3   275.8000
10     8     4   405.5000
11     8     8   301.0000
12     8    NA   353.1000

or with an additional column:

cyl_carb <- mtcars %>% group_by(cyl,carb) %>% summarize(mean(disp))
cyl <- mtcars %>% group_by(cyl) %>% summarize(mean.cyl = mean(disp))
joined <- full_join(cyl_carb, cyl)
joined

gives:

Source: local data frame [9 x 4]
Groups: cyl [?]

    cyl  carb mean(disp) mean.cyl
  (dbl) (dbl)      (dbl)    (dbl)
1     4     1      91.38 105.1364
2     4     2     116.60 105.1364
3     6     1     241.50 183.3143
4     6     4     163.80 183.3143
5     6     6     145.00 183.3143
6     8     2     345.50 353.1000
7     8     3     275.80 353.1000
8     8     4     405.50 353.1000
9     8     8     301.00 353.1000

data.table It's very clunky, but this is one way:

library(data.table)
DT <- data.table(mtcars)
rbind(
  DT[,.(mean(disp)),          by=.(cyl,carb)],
  DT[,.(mean(disp), carb=NA), by=.(cyl) ],
  DT[,.(mean(disp), cyl=NA),  by=.(carb)]
)[order(cyl,carb)]

This gives

    cyl carb       V1
 1:   4    1  91.3800
 2:   4    2 116.6000
 3:   4   NA 105.1364
 4:   6    1 241.5000
 5:   6    4 163.8000
 6:   6    6 145.0000
 7:   6   NA 183.3143
 8:   8    2 345.5000
 9:   8    3 275.8000
10:   8    4 405.5000
11:   8    8 301.0000
12:   8   NA 353.1000
13:  NA    1 134.2714
14:  NA    2 208.1600
15:  NA    3 275.8000
16:  NA    4 308.8200
17:  NA    6 145.0000
18:  NA    8 301.0000

I'd rather see results in something like an R table, but don't know of any functions for that.


dplyr @akrun found this analogous code

bind_rows(
  mtcars %>% 
    group_by(cyl, carb) %>% 
    summarise(Mean= mean(disp)), 
  mtcars %>% 
    group_by(cyl) %>% 
    summarise(carb=NA, Mean=mean(disp)), 
  mtcars %>% 
    group_by(carb) %>% 
    summarise(cyl=NA, Mean=mean(disp))
) %>% arrange(cyl, carb)

We could wrap the repeat operations in a function

library(lazyeval)
f1 <- function(df, grp, Var, func){
  FUN <- match.fun(func)
   df %>% 
     group_by_(.dots=grp) %>%
     summarise_(interp(~FUN(v), v=as.name(Var)))
  }

 m1 <- f1(mtcars, c('carb', 'cyl'), 'disp', 'mean')
 m2 <- f1(mtcars, 'carb', 'disp', 'mean')
 m3 <- f1(mtcars, 'cyl', 'disp', 'mean')

 bind_rows(list(m1, m2, m3)) %>%
              arrange(cyl, carb) %>%
              rename(Mean=`FUN(disp)`)
   carb cyl     Mean
1     1   4  91.3800
2     2   4 116.6000
3    NA   4 105.1364
4     1   6 241.5000
5     4   6 163.8000
6     6   6 145.0000
7    NA   6 183.3143
8     2   8 345.5000
9     3   8 275.8000
10    4   8 405.5000
11    8   8 301.0000
12   NA   8 353.1000
13    1  NA 134.2714
14    2  NA 208.1600
15    3  NA 275.8000
16    4  NA 308.8200
17    6  NA 145.0000
18    8  NA 301.0000

Either option can be made a little less ugly with data.table's rbindlist with fill:

rbindlist(list(
  mtcars %>% group_by(cyl) %>% summarise(mean(disp)),
  mtcars %>% group_by(carb) %>% summarise(mean(disp)),
  mtcars %>% group_by(cyl,carb) %>% summarise(mean(disp))
),fill=TRUE) %>% arrange(cyl,carb)

rbindlist(list(
  DT[,mean(disp),by=.(cyl,carb)],
  DT[,mean(disp),by=.(cyl)],
  DT[,mean(disp),by=.(carb)]
),fill=TRUE)[order(cyl,carb)]

Something similar to table with addmargins (although actually a data.frame)

library(dplyr)
library(reshape2)
out <- bind_cols(
    mtcars %>% group_by(cyl, carb) %>%
      summarise(mu = mean(disp)) %>%
      dcast(cyl ~ carb),
    (mtcars %>% group_by(cyl) %>% summarise(Total=mean(disp)))[,2]
)

margin <- t((mtcars %>% group_by(carb) %>% summarise(Total=mean(disp)))[,2])
rbind(out, c(NA, margin, mean(mtcars$disp))) %>%
  `rownames<-`(c(paste("cyl", c(4,6,8)), "Total"))  # add some row names
#      cyl        1      2     3      4   6   8    Total
# cyl 4   4  91.3800 116.60    NA     NA  NA  NA 105.1364
# cyl 6   6 241.5000     NA    NA 163.80 145  NA 183.3143
# cyl 8   8       NA 345.50 275.8 405.50  NA 301 353.1000
# Total  NA 134.2714 208.16 275.8 308.82 145 301 230.7219

The bottom row is the column wise margins, columns named 1:8 are carbs, and Total is the rowwise margins.