Maybe efficiency is less of an issue than I thought, on 2 million
rows, it only took a bit over a minute, and my system only jumped up ~
600 MB of memory so it wasn't much of a strain there either.
> data.test <- matrix(
+ sample(seq(min(yourdata),max(yourdata)), size = 10000000, replace = TRUE),
+ ncol = 5)
> nrow(data.test)
[1] 2000000
> system.time(my.finder(data.test))
user system elapsed
74.54 0.20 75.20
On Fri, Jul 23, 2010 at 11:01 PM, Joshua Wiley <jwiley.ps...@gmail.com> wrote:
> Hi,
>
> Here is a little function that will do what you want and return a nice output:
>
> #Function To calculate top two values and return
> my.finder <- function(mydata) {
> my.fun <- function(data) {
> strongest <- which.max(data)
> secondstrongest <- which.max(data[-strongest])
> strongestantenna <- names(data)[strongest]
> secondstrongantenna <- names(data[-strongest])[secondstrongest]
> value <- matrix(c(data[strongest], data[secondstrongest],
> strongestantenna, secondstrongantenna), ncol =4)
> return(value)
> }
> dat <- apply(mydata, 1, my.fun)
> dat <- t(dat)
> dat <- as.data.frame(dat, stringsAsFactors = FALSE)
> colnames(dat) <- c("strongest", "secondstrongest",
> "strongestantenna", "secondstrongantenna")
> dat[ , "strongest"] <- as.numeric(dat[ , "strongest"])
> dat[ , "secondstrongest"] <- as.numeric(dat[ , "secondstrongest"])
> return(dat)
> }
>
>
> #Using your example data:
>
> yourdata <- structure(list(value0 = c(-13007L, -12838L, -12880L, -12805L,
> -12834L, -11068L, -12807L, -12770L, -12988L, -11779L), value60 = c(-11707L,
> -13210L, -11778L, -11653L, -13527L, -11698L, -14068L, -11665L,
> -11736L, -12873L), value120 = c(-11072L, -11176L, -11113L, -11071L,
> -11067L, -12430L, -11092L, -11061L, -11137L, -12973L), value180 = c(-12471L,
> -11799L, -12439L, -12385L, -11638L, -12430L, -11709L, -12373L,
> -12570L, -12537L), value240 = c(-12838L, -13210L, -13089L, -11561L,
> -13527L, -12430L, -11607L, -11426L, -13467L, -12973L), value300 = c(-13357L,
> -13845L, -13880L, -13317L, -13873L, -12814L, -13025L, -12805L,
> -13739L, -11146L)), .Names = c("value0", "value60", "value120",
> "value180", "value240", "value300"), class = "data.frame", row.names = c("1",
> "2", "3", "4", "5", "6", "7", "8", "9", "10"))
>
> my.finder(yourdata) #and what you want is in a nicely labeled data frame
>
> #A potential problem is that it is not very efficient
>
> #Here is a test using a matrix of 100,000 rows
> #sampled from the same range as your data
> #with the same number of columns
>
> data.test <- matrix(
> sample(seq(min(yourdata),max(yourdata)), size = 500000, replace = TRUE),
> ncol = 5)
>
> system.time(my.finder(data.test))
>
> #On my system I get
>
>> system.time(my.finder(data.test))
> user system elapsed
> 2.89 0.00 2.89
>
> Hope that helps,
>
> Josh
>
>
>
> On Fri, Jul 23, 2010 at 6:20 PM, <mpw...@illinois.edu> wrote:
>> I have a data frame with a couple million lines and want to retrieve the
>> largest and second largest values in each row, along with the label of the
>> column these values are in. For example
>>
>> row 1
>> strongest=-11072
>> secondstrongest=-11707
>> strongestantenna=value120
>> secondstrongantenna=value60
>>
>> Below is the code I am using and a truncated data.frame. Retrieving the
>> largest value was easy, but I have been getting errors every way I have
>> tried to retrieve the second largest value. I have not even tried to
>> retrieve the labels for the value yet.
>>
>> Any help would be appreciated
>> Mike
>>
>>
>>> data<-data.frame(value0,value60,value120,value180,value240,value300)
>>> data
>> value0 value60 value120 value180 value240 value300
>> 1 -13007 -11707 -11072 -12471 -12838 -13357
>> 2 -12838 -13210 -11176 -11799 -13210 -13845
>> 3 -12880 -11778 -11113 -12439 -13089 -13880
>> 4 -12805 -11653 -11071 -12385 -11561 -13317
>> 5 -12834 -13527 -11067 -11638 -13527 -13873
>> 6 -11068 -11698 -12430 -12430 -12430 -12814
>> 7 -12807 -14068 -11092 -11709 -11607 -13025
>> 8 -12770 -11665 -11061 -12373 -11426 -12805
>> 9 -12988 -11736 -11137 -12570 -13467 -13739
>> 10 -11779 -12873 -12973 -12537 -12973 -11146
>>> #largest value in the row
>>> strongest<-apply(data,1,max)
>>>
>>>
>>> #second largest value in the row
>>> n<-function(data)(1/(min(1/(data[1,]-max(data[1,]))))+ (max(data[1,])))
>>> secondstrongest<-apply(data,1,n)
>> Error in data[1, ] : incorrect number of dimensions
>>>
>>
>> ______________________________________________
>> R-help@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.
>>
>
>
>
> --
> Joshua Wiley
> Ph.D. Student, Health Psychology
> University of California, Los Angeles
> http://www.joshuawiley.com/
>
--
Joshua Wiley
Ph.D. Student, Health Psychology
University of California, Los Angeles
http://www.joshuawiley.com/
______________________________________________
R-help@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.
