R help - Apr 2022 - [External] "apply" a function that takes two or more vectors as arguments, such as cor(x, y), over a "category" or "grouping variable" or "index"?

#Q. How can I "apply" a function that takes two or more vectors as
arguments, such as cor(x, y), over a "category" or "grouping
variable"
or "index"?
#I'm using cor() as an example, I'd like to find a way to do this for
any function that takes 2 or more vectors as arguments.


#create example data

my_category <- rep ( c("a","b","c"),  4)

set.seed(12345)
my_x <- rnorm(12)

set.seed(54321)
my_y <- rnorm(12)

my_df <- data.frame(my_category, my_x, my_y)

#review data
my_df

#If i wanted to get the correlation of x and y grouped by category, I
could use this code and loop:

my_category_unique <- unique(my_category)

my_results <- vector("list", length(my_category_unique) )
names(my_results) <- my_category_unique

#start i loop
  for (i in 1:length(my_category_unique) ) {
    my_criteria_i <- my_category == my_category_unique[i]
    my_x_i <- my_x[which(my_criteria_i)]
    my_y_i <- my_y[which(my_criteria_i)]
    my_correl_i <- cor(x = my_x_i, y = my_y_i)
    my_results[i] <- list(my_correl_i)
} # end i loop

#review results
my_results

#Q. Is there a better or more "elegant" way to do this, using by(),
aggregate(), apply(), or some other function?

#This does not work and results in this error message: "Error in
FUN(dd[x, ], ...) : incompatible dimensions"
by (data = my_x, INDICES = my_category, FUN = cor, y = my_y)

#This does not work and results in this error message: "Error in
cor(my_df$x, my_df$y) : ... supply both 'x' and 'y' or a
matrix-like
'x' "
by (data = my_df, INDICES = my_category, FUN = function(x, y) { cor
(my_df$x, my_df$y) } )


#if I wanted the mean of x by category, I could use by() or aggregate():
by (data = my_x, INDICES = my_category, FUN = mean)

aggregate(x = my_x, by = list(my_category), FUN = mean)

#Thanks!

look at
?mapply
Apply a Function to Multiple List or Vector Arguments

to see if that meets your needs
> On Apr 08, 2022, at 21:26, Kelly Thompson <kt1572757 at gmail.com>
wrote:
> 
> #Q. How can I "apply" a function that takes two or more vectors
as
> arguments, such as cor(x, y), over a "category" or "grouping
variable"
> or "index"?
> #I'm using cor() as an example, I'd like to find a way to do this
for
> any function that takes 2 or more vectors as arguments.
> 
> 
> #create example data
> 
> my_category <- rep ( c("a","b","c"),  4)
> 
> set.seed(12345)
> my_x <- rnorm(12)
> 
> set.seed(54321)
> my_y <- rnorm(12)
> 
> my_df <- data.frame(my_category, my_x, my_y)
> 
> #review data
> my_df
> 
> #If i wanted to get the correlation of x and y grouped by category, I
> could use this code and loop:
> 
> my_category_unique <- unique(my_category)
> 
> my_results <- vector("list", length(my_category_unique) )
> names(my_results) <- my_category_unique
> 
> #start i loop
>  for (i in 1:length(my_category_unique) ) {
>    my_criteria_i <- my_category == my_category_unique[i]
>    my_x_i <- my_x[which(my_criteria_i)]
>    my_y_i <- my_y[which(my_criteria_i)]
>    my_correl_i <- cor(x = my_x_i, y = my_y_i)
>    my_results[i] <- list(my_correl_i)
> } # end i loop
> 
> #review results
> my_results
> 
> #Q. Is there a better or more "elegant" way to do this, using
by(),
> aggregate(), apply(), or some other function?
> 
> #This does not work and results in this error message: "Error in
> FUN(dd[x, ], ...) : incompatible dimensions"
> by (data = my_x, INDICES = my_category, FUN = cor, y = my_y)
> 
> #This does not work and results in this error message: "Error in
> cor(my_df$x, my_df$y) : ... supply both 'x' and 'y' or a
matrix-like
> 'x' "
> by (data = my_df, INDICES = my_category, FUN = function(x, y) { cor
> (my_df$x, my_df$y) } )
> 
> 
> #if I wanted the mean of x by category, I could use by() or aggregate():
> by (data = my_x, INDICES = my_category, FUN = mean)
> 
> aggregate(x = my_x, by = list(my_category), FUN = mean)
> 
> #Thanks!
> 
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
>
https://nam10.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstat.ethz.ch%2Fmailman%2Flistinfo%2Fr-help&amp;data=04%7C01%7Crmh%40temple.edu%7C4c8a50fd1bf14b2cf7b408da19c7fe20%7C716e81efb52244738e3110bd02ccf6e5%7C0%7C0%7C637850644148770767%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&amp;sdata=23Y%2Fqw7G1gb4ACIz5V41DjBIR8c2IFkkZgud9dGaftE%3D&amp;reserved=0
> PLEASE do read the posting guide
https://nam10.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.r-project.org%2Fposting-guide.html&amp;data=04%7C01%7Crmh%40temple.edu%7C4c8a50fd1bf14b2cf7b408da19c7fe20%7C716e81efb52244738e3110bd02ccf6e5%7C0%7C0%7C637850644148770767%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000&amp;sdata=3vIZYrMBnAZKZhZCwHcLpILHEE72NuLc03LXAxr%2BXQ4%3D&amp;reserved=0
> and provide commented, minimal, self-contained, reproducible code.

On Sat, Apr 9, 2022 at 6:56 AM Kelly Thompson <kt1572757 at gmail.com>
wrote:
>
> #Q. How can I "apply" a function that takes two or more vectors
as
> arguments, such as cor(x, y), over a "category" or "grouping
variable"
> or "index"?
> #I'm using cor() as an example, I'd like to find a way to do this
for
> any function that takes 2 or more vectors as arguments.
>
> #create example data
>
> my_category <- rep ( c("a","b","c"),  4)
>
> set.seed(12345)
> my_x <- rnorm(12)
>
> set.seed(54321)
> my_y <- rnorm(12)
>
> my_df <- data.frame(my_category, my_x, my_y)
>
> #review data
> my_df
>
> #If i wanted to get the correlation of x and y grouped by category, I
> could use this code and loop:
>
> my_category_unique <- unique(my_category)
>
> my_results <- vector("list", length(my_category_unique) )
> names(my_results) <- my_category_unique
>
> #start i loop
>   for (i in 1:length(my_category_unique) ) {
>     my_criteria_i <- my_category == my_category_unique[i]
>     my_x_i <- my_x[which(my_criteria_i)]
>     my_y_i <- my_y[which(my_criteria_i)]
>     my_correl_i <- cor(x = my_x_i, y = my_y_i)
>     my_results[i] <- list(my_correl_i)
> } # end i loop
>
> #review results
> my_results
>
> #Q. Is there a better or more "elegant" way to do this, using
by(),
> aggregate(), apply(), or some other function?
split() is another generally useful function to know about: e.g.,

s <- split(my_df, ~ my_category)
lapply(s, function(d) with(d, cor(my_x, my_y)))

Best,
-Deepayan
> #This does not work and results in this error message: "Error in
> FUN(dd[x, ], ...) : incompatible dimensions"
> by (data = my_x, INDICES = my_category, FUN = cor, y = my_y)
>
> #This does not work and results in this error message: "Error in
> cor(my_df$x, my_df$y) : ... supply both 'x' and 'y' or a
matrix-like
> 'x' "
> by (data = my_df, INDICES = my_category, FUN = function(x, y) { cor
> (my_df$x, my_df$y) } )
>
>
> #if I wanted the mean of x by category, I could use by() or aggregate():
> by (data = my_x, INDICES = my_category, FUN = mean)
>
> aggregate(x = my_x, by = list(my_category), FUN = mean)
>
> #Thanks!
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

Hello,

Another option is ?by.


by(my_df[-1], my_df$my_category, cor)
by(my_df[-1], my_df$my_category, \(x) cor(x)[1,2])


Hope this helps,

Rui Barradas

?s 02:26 de 09/04/2022, Kelly Thompson escreveu:
> #Q. How can I "apply" a function that takes two or more vectors
as
> arguments, such as cor(x, y), over a "category" or "grouping
variable"
> or "index"?
> #I'm using cor() as an example, I'd like to find a way to do this
for
> any function that takes 2 or more vectors as arguments.
> 
> 
> #create example data
> 
> my_category <- rep ( c("a","b","c"),  4)
> 
> set.seed(12345)
> my_x <- rnorm(12)
> 
> set.seed(54321)
> my_y <- rnorm(12)
> 
> my_df <- data.frame(my_category, my_x, my_y)
> 
> #review data
> my_df
> 
> #If i wanted to get the correlation of x and y grouped by category, I
> could use this code and loop:
> 
> my_category_unique <- unique(my_category)
> 
> my_results <- vector("list", length(my_category_unique) )
> names(my_results) <- my_category_unique
> 
> #start i loop
>    for (i in 1:length(my_category_unique) ) {
>      my_criteria_i <- my_category == my_category_unique[i]
>      my_x_i <- my_x[which(my_criteria_i)]
>      my_y_i <- my_y[which(my_criteria_i)]
>      my_correl_i <- cor(x = my_x_i, y = my_y_i)
>      my_results[i] <- list(my_correl_i)
> } # end i loop
> 
> #review results
> my_results
> 
> #Q. Is there a better or more "elegant" way to do this, using
by(),
> aggregate(), apply(), or some other function?
> 
> #This does not work and results in this error message: "Error in
> FUN(dd[x, ], ...) : incompatible dimensions"
> by (data = my_x, INDICES = my_category, FUN = cor, y = my_y)
> 
> #This does not work and results in this error message: "Error in
> cor(my_df$x, my_df$y) : ... supply both 'x' and 'y' or a
matrix-like
> 'x' "
> by (data = my_df, INDICES = my_category, FUN = function(x, y) { cor
> (my_df$x, my_df$y) } )
> 
> 
> #if I wanted the mean of x by category, I could use by() or aggregate():
> by (data = my_x, INDICES = my_category, FUN = mean)
> 
> aggregate(x = my_x, by = list(my_category), FUN = mean)
> 
> #Thanks!
> 
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.