R help - Feb 2010 - svm regression

Hi,

I am trying to use svm  for regression data.

this is how my data looks like:
>dataTrain
x  y   z
1  4  6
2  5  4
3  7  5
>classTrain
a
2
3
4
>dataTest
x y  z
1 7  2
2 8  3
>classTest
a
3
4
5


building the model

model<-svm(dataTrain,classTrain,type="nu-regression")
pred <- predict(model, dataTest)
> pred
       1        2
3.008842 3.120078

I don't understand what the above value means.i need the results similar to
classTest.

Thanks,
Joji.

	[[alternative HTML version deleted]]

Hi,

I am having trouble with svm regression.it is not giving the right results.

example
> model <- svm(dataTrain,classTrain,type="eps-regression")
> predict(model, dataTest)
        36         37         38         39         40         41
42
-13.838257  -1.475401  10.502739  -3.047656  -8.713697   3.812873
1.741999
        43         44         45         46         47         48
49
 -6.034361 -13.469742   7.628642 -22.197060  -3.417444  -8.536890
-11.876133
        50
 -5.877457


My dataSet has 50 columns and 19 rows
my classSet has 50 columns and 1 row

My dataTrain has 35(1:35) columns and 19 rows
My classTrain has 35(1:35) columns and 1 row

My dataTest has 15(36:50) columns and 19 rows
My classTest has 15(36:50) columns and 1 row

My results should be as follows:

 [1] -25.70  30.30 -58.50  -1.12   7.62 -16.10 -48.50  21.10  12.60 -43.00
[11] -47.30 -47.90 -38.40 -21.30  22.40

But instead i get the wrong values.can anyone help me with it.

Thanks,
Joji.

	[[alternative HTML version deleted]]

On 18.02.2010 17:54, madhu sankar wrote:
> Hi,
>
> I am trying to use svm  for regression data.
>
> this is how my data looks like:
>
>> dataTrain
>
> x  y   z
> 1  4  6
> 2  5  4
> 3  7  5
>
>> classTrain
>
> a
> 2
> 3
> 4
>
>> dataTest
>
> x y  z
> 1 7  2
> 2 8  3
>
>> classTest
>
> a
> 3
> 4
> 5
>
>
> building the model
>
> model<-svm(dataTrain,classTrain,type="nu-regression")
> pred<- predict(model, dataTest)
>
>> pred
>         1        2
> 3.008842 3.120078
>
> I don't understand what the above value means.i need the results
similar to
> classTest.

They are similar, aren't they?
You talk about svm *regression* rather than classification and call your 
object "class....." which makes me worry you failed to understand some
basics of the method.

Uwe Ligges


>
> Thanks,
> Joji.
>
> 	[[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.

On 18.02.2010 19:43, madhu sankar wrote:
> Hi,
>
> I am having trouble with svm regression.it is not giving the right results.
>
> example
>
>> model<- svm(dataTrain,classTrain,type="eps-regression")
>> predict(model, dataTest)
>          36         37         38         39         40         41
> 42
> -13.838257  -1.475401  10.502739  -3.047656  -8.713697   3.812873
> 1.741999
>          43         44         45         46         47         48
> 49
>   -6.034361 -13.469742   7.628642 -22.197060  -3.417444  -8.536890
> -11.876133
>          50
>   -5.877457
>
>
> My dataSet has 50 columns and 19 rows
> my classSet has 50 columns and 1 row
>
> My dataTrain has 35(1:35) columns and 19 rows
> My classTrain has 35(1:35) columns and 1 row
>
> My dataTest has 15(36:50) columns and 19 rows
> My classTest has 15(36:50) columns and 1 row

Same problems as in my last mail:

I fear you are mixing up several things: regression vs. classification, 
rows vs. columns....

> My results should be as follows:
>
>   [1] -25.70  30.30 -58.50  -1.12   7.62 -16.10 -48.50  21.10  12.60 -43.00
> [11] -47.30 -47.90 -38.40 -21.30  22.40
Why do you know?

Uwe Ligges

> But instead i get the wrong values.can anyone help me with it.
>
> Thanks,
> Joji.
>
> 	[[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.