Dplyr weighted average for multiple columns

Question

I am trying to calculate a weighted average for several columns using dplyr. I'm currently stuck in sumize_each, which seems like part of the solution to me. here is a sample code:

library(dplyr)
f2a <- c(1,0,0,1)
f2b <- c(0,0,0,1)
f2c <- c(1,1,1,1)
clustervar <- c("A","B","B","A")
weight <- c(10,20,30,40)

df <- data.frame (f2a, f2b, f2c, clustervar, weight, stringsAsFactors=FALSE)
df

I'm looking for something like

df %>%
  group_by (clustervar) %>%
  summarise_each(funs(weighted.mean(weight)), select=cbind(clustervar, f2a:f2c))

The result of this is only:

# A tibble: 2 × 4
  clustervar select4 select5 select6
       <chr>   <dbl>   <dbl>   <dbl>
1          A      25      25      25
2          B      25      25      25

What am I missing here?

Answer 1

You can use summarise_atto indicate which columns you want to work with:

df %>% group_by(clustervar) %>% 
    summarise_at(vars(starts_with('f2')), 
                 funs(weighted.mean(., weight)))
#> # A tibble: 2 × 4
#>   clustervar   f2a   f2b   f2c
#>        <chr> <dbl> <dbl> <dbl>
#> 1          A     1   0.8     1
#> 2          B     0   0.0     1

Answer 2

We can change it to a "long" format and then do it

library(tidyverse)
gather(df, Var, Val, f2a:f2c) %>% 
        group_by(clustervar, Var) %>% 
        summarise(wt =weighted.mean(Val, weight)) %>%
        spread(Var, wt)

---

Or another option

df %>%
    group_by(clustervar) %>% 
    summarise_each(funs(weighted.mean(., weight)), matches("^f"))
# A tibble: 2 × 4     
#    clustervar   f2a   f2b   f2c
#         <chr> <dbl> <dbl> <dbl>
# 1          A     1   0.8     1
# 2          B     0   0.0     1

---

Or with summarise_atand matches(another variant of another message - did not see another post at the time of publication)

df %>% 
   group_by(clustervar) %>% 
   summarise_at(vars(matches('f2')), funs(weighted.mean(., weight)))
# A tibble: 2 × 4
#   clustervar   f2a   f2b   f2c
#        <chr> <dbl> <dbl> <dbl>
#1          A     1   0.8     1
#2          B     0   0.0     1

---

Or another option data.table

library(data.table)
setDT(df)[, lapply(.SD, function(x) weighted.mean(x, weight)),
                       by = clustervar, .SDcols  = f2a:f2c]
#    clustervar f2a f2b f2c
#1:          A   1 0.8   1
#2:          B   0 0.0   1

. tidyverse/data.table

, dplyr ( 0.6.0). Enquo , quosures. group_by/summary/mutate quosure unquoting (UQ !!) it

wtFun <- function(dat, pat, wtcol, grpcol){
       wtcol <- enquo(wtcol)
       grpcol <- enquo(grpcol)
       dat %>%
           group_by(!!grpcol) %>%
           summarise_at(vars(matches(pat)), funs(weighted.mean(., !!wtcol)))
 }

wtFun(df, "f2", weight, clustervar)
# A tibble: 2 × 4
#   clustervar   f2a   f2b   f2c
#       <chr> <dbl> <dbl> <dbl>
#1          A     1   0.8     1
#2          B     0   0.0     1