calculate the mean of column and also the comments in next column - r

Question

I want to calculate the mean of column and and also concatenate the texts in second column output.
for example in below i want to calculate the mean of C1 and then concatenate all texts in C1T in next column if there is more than one text in C1T.
df <- data.frame(A1 = c("class","type","class","type","class","class","class","class","class"),
B1 = c("b2","b3","b3","b1","b3","b3","b3","b2","b1"),
C1=c(6, NA, 1, 6, NA, 1, 6, 6, 2),
C1T=c(NA, "Part of other business", NA, NA, NA, NA, NA, NA, NA),
C2=c(NA, 4, 1, 2, 4, 4, 3, 3, NA),
C2T=c(NA, NA, NA, NA, NA, NA, NA, NA, NA),
C3=c(3, 4, 3, 3, 6, NA, 2, 4, 1),
C3T=c(NA, NA, NA, NA, "two part are available but not in source", NA, NA, NA, NA),
C4=c(5, 5, 2, NA, NA, 6, 4, 1, 2),
C5T=c(NA, NA, NA, NA, NA, NA, NA, "Critical Expert", NA),
C5=c(6, 2, 6, 4, 2, 2, 5, 4, 1),
C5T=c(NA, NA, NA, NA, NA, "most of things are stuck", "weather responsible", NA, NA))
var <- "C1"
var1 <- "C1T"
var <- rlang::parse_expr(var)
var1 <- rlang::parse_expr(var1)
df1 <- df%>%filter(A1 == "class")
T1<- df1 %>%group_by(B1)%>%summarise(mean=round(mean(!!var,na.rm = TRUE),1))
Comments <- df1 %>% group_by(B1) %>% summarise_at(vars(var1), paste0, collapse = " ") %>%
select(var1) %>% unlist() %>% gsub("NA","",.) %>% stringi::stri_trim_both()
cbind(T1,Comments)

Answer 1

Edited Answer:
var <- "C1"
var1 <- "C1T"
filtercol <- "A1"
filterval <- "class"
groupingvar <- "B1"
var <- rlang::parse_expr(var)
var1 <- rlang::parse_expr(var1)
filtercol <- rlang::parse_expr(filtercol)
groupingvar <- rlang::parse_expr(groupingvar)
library(dplyr)
df1 <- df %>% filter(!!filtercol == filterval)
T1 <- df1 %>% group_by(!!groupingvar) %>% summarise(mean=round(mean(as.numeric(!!var),na.rm = TRUE),1))
Comments <- df1 %>% select(!!groupingvar, !!var1) %>%
group_by(!!groupingvar) %>%
summarise_at(vars(!!var1), paste0, collapse = " ") %>%
select(!!var1) %>% unlist() %>% gsub("NA", "", .) %>%
stringi::stri_trim_both()
T1 <- cbind(T1,Comments)

Answer 2

Update on OP's request (see comments):
library(dplyr)
# helper function to coalesce by column
coalesce_by_column <- function(df) {
return(coalesce(df[1], df[2]))
}
df %>%
pivot_longer(
cols = contains("T"),
names_to = "names",
values_to = "values"
) %>%
filter(names == "C1T") %>%
group_by(names) %>%
summarise(Mean = mean(c_across(C1:C5 & where(is.numeric)), na.rm = TRUE),
Comments = coalesce_by_column(values))
Output:
names Mean Comments
<chr> <dbl> <chr>
1 C1T 3.47 Part of other business
First answer
coalesce to construct Comments column
rowwise with c_across to calculate the mean rowwise.
In case you need to group, you can use ``group_by`
library(dplyr)
df %>%
mutate(Comments = coalesce(C1T, C2T, C3T, C4T, C5T),.keep="unused") %>%
rowwise() %>%
mutate(Mean = mean(c_across(C1:C5 & where(is.numeric)), na.rm = TRUE)) %>%
select(A1, B1, Mean, Comments)
Output:
A1 B1 Mean Comments
<chr> <chr> <dbl> <chr>
1 class b2 5 NA
2 type b3 3.75 Part of other business
3 class b3 2.6 NA
4 type b1 3.75 NA
5 class b3 4 two part are available but not in source
6 class b3 3.25 most of things are stuck
7 class b3 4 weather responsible
8 class b2 3.6 Critical Expert
9 class b1 1.5 NA