R help - Jun 2008 - Binding result of a function to a data frame

Hi,

I have the following function:
> kurtosis <-function(x) (mean((x-mean(x))^4))/(sd(x)^4)  #x is a vector
and data
> print(mydata)
                                    V1             V2      V3      V4      V5
1                       1007_s_at           DDR1  2865.1  2901.3  1978.3
2                         1053_at           RFC2   103.6    81.6   108.0
3                          117_at          HSPA6   222.0   222.5   306.2
4                          121_at           PAX8  2146.3  2457.2  1901.9
5                       1255_g_at         GUCA1A   226.5   321.2   109.2
6                         1294_at          UBE1L   296.6   424.6   406.1
7                         1316_at           THRA   339.9   354.2   178.3
8                         1320_at         PTPN21    78.4    36.2   185.2

Now, I want to:
1.  apply the kurtosis function to every row in the data (starting
from V3 to V5)
2.  bind the output of the kurtosis function to mydata.

Why my code below doesn't work? What's the solution for it?

 binded_mydata_withkurt <- cbind(mydata,
kurt=apply(mydata,1,kurtosis(mydata[,3:ncol(repo.dat)]),na.rm = TRUE))


- Gundala Viswanath
Jakarta - Indonesia

is this what you are looking for:
> x <- read.table(textConnection("                                  
V1             V2      V3      V4      V5
+ 1                       1007_s_at           DDR1  2865.1  2901.3  1978.3
+ 2                         1053_at           RFC2   103.6    81.6   108.0
+ 3                          117_at          HSPA6   222.0   222.5   306.2
+ 4                          121_at           PAX8  2146.3  2457.2  1901.9
+ 5                       1255_g_at         GUCA1A   226.5   321.2   109.2
+ 6                         1294_at          UBE1L   296.6   424.6   406.1
+ 7                         1316_at           THRA   339.9   354.2   178.3
+ 8                         1320_at         PTPN21    78.4    36.2
185.2"), header=TRUE)
> closeAllConnections()
> kurtosis <-function(x) (mean((x-mean(x))^4))/(sd(x)^4)  #x is a vector
> cbind(x, kurtosis=apply(x, 1, function(z)
kurtosis(as.numeric(unlist(z[3:5])))))
         V1     V2     V3     V4     V5  kurtosis
1 1007_s_at   DDR1 2865.1 2901.3 1978.3 0.6666667
2   1053_at   RFC2  103.6   81.6  108.0 0.6666667
3    117_at  HSPA6  222.0  222.5  306.2 0.6666667
4    121_at   PAX8 2146.3 2457.2 1901.9 0.6666667
5 1255_g_at GUCA1A  226.5  321.2  109.2 0.6666667
6   1294_at  UBE1L  296.6  424.6  406.1 0.6666667
7   1316_at   THRA  339.9  354.2  178.3 0.6666667
8   1320_at PTPN21   78.4   36.2  185.2 0.6666667
>

On Mon, Jun 23, 2008 at 10:31 PM, Gundala Viswanath <gundalav at
gmail.com> wrote:
> Hi,
>
> I have the following function:
>
>> kurtosis <-function(x) (mean((x-mean(x))^4))/(sd(x)^4)  #x is a
vector
>
> and data
>
>> print(mydata)
>                                    V1             V2      V3      V4     
V5
> 1                       1007_s_at           DDR1  2865.1  2901.3  1978.3
> 2                         1053_at           RFC2   103.6    81.6   108.0
> 3                          117_at          HSPA6   222.0   222.5   306.2
> 4                          121_at           PAX8  2146.3  2457.2  1901.9
> 5                       1255_g_at         GUCA1A   226.5   321.2   109.2
> 6                         1294_at          UBE1L   296.6   424.6   406.1
> 7                         1316_at           THRA   339.9   354.2   178.3
> 8                         1320_at         PTPN21    78.4    36.2   185.2
>
> Now, I want to:
> 1.  apply the kurtosis function to every row in the data (starting
> from V3 to V5)
> 2.  bind the output of the kurtosis function to mydata.
>
> Why my code below doesn't work? What's the solution for it?
>
>  binded_mydata_withkurt <- cbind(mydata,
> kurt=apply(mydata,1,kurtosis(mydata[,3:ncol(repo.dat)]),na.rm = TRUE))
>
>
> - Gundala Viswanath
> Jakarta - Indonesia
>
> ______________________________________________
> 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.
>


-- 
Jim Holtman
Cincinnati, OH
+1 513 646 9390

What is the problem you are trying to solve?