mjhjmtu

I am currently working with a series of large datasets and I'm trying to improve how I write scripts in R. I tend to mostly make use of for loops which I know can be cumbersome and slow, espeically with very large datasets.

I have heard a lot of people recommending the apply() family to avoid complex for loops, but I am struggling to get my head around using them to apply multiple functions in one go.

Here is some simple example data:

A <- data.frame('Area' = c(4, 6, 5),
 'flow' = c(1, 1, 1))
B <- data.frame('Area' = c(6, 8, 4),
 'flow' = c(1, 2, 1))
files <- list(A, B)
frames <- list('A', 'B')

What I want to do is sort the data by the 'flow' variable, then add columns for the portion of total 'flow' and 'area' each data point represents, before finally adding a further two columns of the cumulative percentage of each variable.

Currently I use this for loop:

sort_files <- list()
n <- 1
for(i in files)
 name <- frames[n]
 nom <- paste(name,'_sorted', sep = '')
 data <- i[order(-i$flow),]
 area <- sum(i$Area)
 total <- sum(i$flow)
 data$area_portion <- (data$Area/area)*100
 data$flow_portion <- (data$flow/total)*100
 data$cum_area <- cumsum(data$area_portion)
 data$cum_flow <- cumsum(data$flow_portion)
 assign(nom, data)
 df <- get(paste(name,'_sorted', sep = ''))
 sort_files[[nom]] <- df
 n <- n + 1

Which works, but seems overly complex and ugly, and I'm sure it will run far slower than better scripts.

How can I simplify and neaten up the above code?

This is the expected output:

sort_files

$`A_sorted`
 Area flow area_portion flow_portion cum_area cum_flow
1 4 1 26.66667 33.33333 26.66667 33.33333
2 6 1 40.00000 33.33333 66.66667 66.66667
3 5 1 33.33333 33.33333 100.00000 100.00000

$B_sorted
 Area flow area_portion flow_portion cum_area cum_flow
2 8 2 44.44444 50 44.44444 50
1 6 1 33.33333 25 77.77778 75
3 4 1 22.22222 25 100.00000 100

Using lapply to loop over files and dplyr mutate to add new columns

library(dplyr)

setNames(lapply(files, function(x) 
 x %>%
 arrange(desc(flow)) %>%
 mutate(area_portion = Area/sum(Area)*100, 
 flow_portion = flow/sum(flow) * 100, 
 cum_area = cumsum(area_portion),
 cum_flow = cumsum(flow_portion))
),paste0(frames, "_sorted"))


#$A_sorted
# Area flow area_portion flow_portion cum_area cum_flow
#1 4 1 26.66667 33.33333 26.66667 33.33333
#2 6 1 40.00000 33.33333 66.66667 66.66667
#3 5 1 33.33333 33.33333 100.00000 100.00000

#$B_sorted
# Area flow area_portion flow_portion cum_area cum_flow
#1 8 2 44.44444 50 44.44444 50
#2 6 1 33.33333 25 77.77778 75
#3 4 1 22.22222 25 100.00000 100

Or completely going tidyverse way we can change lapply with map and setNames with set_names

library(tidyverse)

map(set_names(files, str_c(frames, "_sorted")), 
 . %>% arrange(desc(flow)) %>%
 mutate(area_portion = Area/sum(Area)*100, 
 flow_portion = flow/sum(flow) * 100, 
 cum_area = cumsum(area_portion),
 cum_flow = cumsum(flow_portion)))

Updated the tidyverse approach following some pointers from @Moody_Mudskipper.

You could also define a function first ..

f <- function(data) 

 # sort data by flow
 data <- data[order(data['flow'], decreasing = TRUE), ]

 # apply your functions
 data["area_portion"] <- data['Area'] / sum(data['Area']) * 100
 data["flow_portion"] <- data['flow'] / sum(data['flow']) * 100
 data["cum_area"] <- cumsum(data['area_portion'])
 data["cum_flow"] <- cumsum(data['flow_portion'])
 data
 

.. and use lapply to, ahhm, apply f to your list

out <- lapply(files, f)
out
#[[1]]
# Area flow area_portion flow_portion cum_area cum_flow
#1 4 1 26.66667 33.33333 26.66667 33.33333
#2 6 1 40.00000 33.33333 66.66667 66.66667
#3 5 1 33.33333 33.33333 100.00000 100.00000

#[[2]]
# Area flow area_portion flow_portion cum_area cum_flow
#2 8 2 44.44444 50 44.44444 50
#1 6 1 33.33333 25 77.77778 75
#3 4 1 22.22222 25 100.00000 100

If you want to change the names of out you can use setNames

out <- setNames(lapply(files, f), paste0(c("A", "B"), "_sorted"))
# or
# out <- setNames(lapply(files, f), paste0(unlist(frames), "_sorted"))