Combine multiple factor columns into a single numeric column - r

Question

Can someone think of a more interesting way to combine multiple factor columns into a single numeric column?
MWE dataset:
df <- data.frame(q.82=factor(c(1,2,2,1,1)), q.77=factor(c(2,1,1,1,1)), q.72=factor(c(1,1,1,2,2)))
levels(df$q.82) <- c("","$80 and above")
levels(df$q.77) <- c("", "$75 to $79")
levels(df$q.72) <- c("", "$70 to $74")
str(df$q.82)
Factor w/ 2 levels "","$80 and above": 1 2 2 1 1
df looks like this:
q.82 q.77 q.72
1 $74 to $79
2 $80 and above
3 $80 and above
4 $70 to $74
5 $70 to $74
What I'd like is something like this, where the columns are numeric:
q.82 q.77 q.72 q
1 0 77 0 77
2 82 0 0 82
3 82 0 0 82
4 0 0 72 72
5 0 0 72 72
The following works, but seems klunky—mostly because the actual dataset has many columns.
df$q.82 <- as.numeric(as.factor(df$q.82))
df$q.82[df$q.82 == 2] <- 82
df$q.82[df$q.82 == 1] <- 0
df$q.77 <- as.numeric(as.factor(df$q.77))
df$q.77[df$q.77 == 2] <- 77
df$q.77[df$q.77 == 1] <- 0
df$q.72 <- as.numeric(as.factor(df$q.72))
df$q.72[df$q.72 == 2] <- 72
df$q.72[df$q.72 == 1] <- 0
df <- df %>% mutate(q=q.82+q.77+q.72)

Answer 1

A possible approach with base R using sapply:
For each column, replace non-empty strings by the numeric part of the column name and replace empty strings by zero.
Add an additional column q that contains the summed value of each row.
out_df <- sapply(names(df), function(name) {
ifelse(nchar(as.character(df[[name]])) > 0, as.numeric(sub("^q\\.", "", name)), 0)
})
out_df <- transform(out_df, q = rowSums(out_df))
out_df
#> q.82 q.77 q.72 q
#> 1 0 77 0 77
#> 2 82 0 0 82
#> 3 82 0 0 82
#> 4 0 0 72 72
#> 5 0 0 72 72
Similarly, using the tidyverse:
library(tidyverse)
df_out <- imap_dfc(.x = df, .f = ~{
if_else(nchar(as.character(.x)) > 0, as.numeric(str_remove(.y, "^q\\.")), 0)
}) %>%
mutate(q = rowSums(.))
df_out
#> # A tibble: 5 x 4
#> q.82 q.77 q.72 q
#> <dbl> <dbl> <dbl> <dbl>
#> 1 0 77 0 77
#> 2 82 0 0 82
#> 3 82 0 0 82
#> 4 0 0 72 72
#> 5 0 0 72 72
Or with data.table:
library(data.table)
setDT(df)
for(j in names(df))
set(df, j = j, value = ifelse(nchar(as.character(df[[j]])) > 0, as.numeric(sub("^q\\.", "", j)), 0))
df[, q := rowSums(.SD)][]
#> q.82 q.77 q.72 q
#> 1: 0 77 0 77
#> 2: 82 0 0 82
#> 3: 82 0 0 82
#> 4: 0 0 72 72
#> 5: 0 0 72 72
Data
df <- data.frame(q.82=factor(c(1,2,2,1,1)), q.77=factor(c(2,1,1,1,1)), q.72=factor(c(1,1,1,2,2)))
levels(df$q.82) <- c("","$80 and above")
levels(df$q.77) <- c("", "$75 to $79")
levels(df$q.72) <- c("", "$70 to $74")

Answer 2

Here is another base R method, where we replace non-blank value in the column with the numeric part in the column name using sub.
df[] <- t(as.integer(sub(".*?(\\d+)", "\\1", names(df))) * t(df != ""))
df
# q.82 q.77 q.72
#1 0 77 0
#2 82 0 0
#3 82 0 0
#4 0 0 72
#5 0 0 72
and then if you want to row-wise sum the values you can use rowSums
df$q <- rowSums(df)