Merge (make mean) columns with partially matched header name - r

Question

I have a data which look like:
AAA_1 AAA_2 AAA_3 BBB_1 BBB_2 BBB_3 CCC
1 1 1 1 2 2 2 1
2 3 1 4 0 0 0 0
3 5 3 0 1 1 1 1
For each row, I want to make a mean for those columns which have a common feature as follow
feature <- c("AAA","BBB","CCC")
the desired output should look like:
AAA BBB CCC
1 1 2 1
2 2.6 0 0
3 2.6 1 1
for each pattern separately I was able to do that:
data <- read.table("data.txt",header=T,row.name=1)
AAA <- as.matrix(rowMeans(data[ , grepl("AAA" , names( data ) ) ])
But I did not know how to do partially match for different patterns in one row
Also tried some other things like :
for (i in 1:length(features)){
feature[i] <- as.matrix(rowMeans(data[ , grepl(feature[i] , names( data ) ) ]))
}

Answer 1

Assuming your colnames are always structured as shown in your example, then you can split the names and aggregate.
new_names <- unlist(strsplit(names(df),"\\_.*"))
colnames(df) <- new_names
#Testing with your data, we need to prevent the loss of dimension by using drop = FALSE
sapply(unique(new_names), function(i) rowMeans(df[, new_names==i, drop = FALSE]))
# AAA BBB CCC
#[1,] 1.000000 2 1
#[2,] 2.666667 0 0
#[3,] 2.666667 1 1
Data:
df <- structure(list(AAA_1 = c(1L, 3L, 5L), AAA_2 = c(1L, 1L, 3L),
AAA_3 = c(1L, 4L, 0L), BBB_1 = c(2L, 0L, 1L), BBB_2 = c(2L,
0L, 1L), BBB_3 = c(2L, 0L, 1L), CCC = c(1L, 0L, 1L)), .Names = c("AAA_1",
"AAA_2", "AAA_3", "BBB_1", "BBB_2", "BBB_3", "CCC"), class = "data.frame", row.names = c(NA,
-3L))

Answer 2

Here is another option for you. Seeing your column pattern, I chose to use gsub() and get the first three letters. Using ind which includes AAA, BBB, and CCC, I used lapply(), subsetted the data for each element of ind, calculated row means, and extracted a column for row mean only. Then, I used bind_cols() and created foo. The last thing was to assign column names to foo.
library(dplyr)
ind <- unique(gsub("_\\d+$", "", names(mydf)))
lapply(ind, function(x){
select(mydf, contains(x)) %>%
transmute(out = rowMeans(.))
}) %>%
bind_cols() %>%
add_rownames -> foo
names(foo) <- ind
# AAA BBB CCC
# (dbl) (dbl) (dbl)
#1 1.000000 2 1
#2 2.666667 0 0
#3 2.666667 1 1
DATA
mydf <- structure(list(AAA_1 = c(1L, 3L, 5L), AAA_2 = c(1L, 1L, 3L),
AAA_3 = c(1L, 4L, 0L), BBB_1 = c(2L, 0L, 1L), BBB_2 = c(2L,
0L, 1L), BBB_3 = c(2L, 0L, 1L), CCC = c(1L, 0L, 1L)), .Names = c("AAA_1",
"AAA_2", "AAA_3", "BBB_1", "BBB_2", "BBB_3", "CCC"), class = "data.frame", row.names = c(NA,
-3L))

Answer 3

library(dplyr)
library(tidyr)
data %>%
add_rownames() %>%
gather("variable", "value", -rowname) %>%
mutate(variable = gsub("_.*$", "", variable)) %>%
group_by(rowname, variable) %>%
summarise(mean = mean(value)) %>%
spread(variable, mean)