R help - May 2008 - Extract lags from a formula

Hi folks!

 

How do I extract lags from a formula?  An example:

 

mod.eq<-formula(x~lag(x,-1)+lag(x,-2))
> mod.eq
x ~ lag(x, -1) + lag(x, -2)
> mod.eq[1]
"~"()
> mod.eq[2]
x()
> mod.eq[3]
lag(x, -1) + lag(x, -2)()

 

I'm trying to extract the lags into a vector that would be simply [1,2].
How do I do this?  I'm using the dyn package to do dynamic regression.

 

John


	[[alternative HTML version deleted]]

On Fri, May 2, 2008 at 1:35 PM, Kerpel, John <John.Kerpel at infores.com>
wrote:
> Hi folks!
>
>
>
>  How do I extract lags from a formula?  An example:
>
>
>
>  mod.eq<-formula(x~lag(x,-1)+lag(x,-2))
>
>  > mod.eq
>
>  x ~ lag(x, -1) + lag(x, -2)
>
>  > mod.eq[1]
>
>  "~"()
>
>  > mod.eq[2]
>
>  x()
>
>  > mod.eq[3]
>
>  lag(x, -1) + lag(x, -2)()
>
>
>
>  I'm trying to extract the lags into a vector that would be simply
[1,2].
>  How do I do this?  I'm using the dyn package to do dynamic regression.
Maybe something like:

f <- formula(x~lag(x,-1)+lag(x,-2))

lags <- function(x) {
  if (length(x) != 3) return()

  if (x[[1]] == as.name("lag")) {
    return(eval(x[[3]]))
  } else {
    return(c(lags(x[[2]]), lags(x[[3]])))
  }
}

R expressions are preorder trees.

Hadley

-- 
http://had.co.nz/

If x is a zoo object note that zoo (and therefore dyn) allows the more compact
form lag(x, -(1:2)) so if we write:

mod.eq <- x ~ lag(x, -(1:2))

then mod.eq[[3]][[3]] is the vector -(1:2) or if you like you can define
Lag <- function(x, k) lag(x, -k) in which case you can write it:

mod.eq <- x ~ Lag(x, 1:2)

and the same expression extracts 1:2.


On Fri, May 2, 2008 at 2:35 PM, Kerpel, John <John.Kerpel at infores.com>
wrote:
> Hi folks!
>
>
>
> How do I extract lags from a formula?  An example:
>
>
>
> mod.eq<-formula(x~lag(x,-1)+lag(x,-2))
>
> > mod.eq
>
> x ~ lag(x, -1) + lag(x, -2)
>
> > mod.eq[1]
>
> "~"()
>
> > mod.eq[2]
>
> x()
>
> > mod.eq[3]
>
> lag(x, -1) + lag(x, -2)()
>
>
>
> I'm trying to extract the lags into a vector that would be simply
[1,2].
> How do I do this?  I'm using the dyn package to do dynamic regression.
>
>
>
> John
>
>
>        [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> 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.
>