[R] SVM

From: simon abai bisrat <sabisrat_at_yahoo.com>
Date: Wed, 26 Nov 2008 12:51:15 -0800 (PST)

Hi All,

I fitted several classifiers in a two class problem. I then used the package 'yaImpute' - to apply my predictive models to asciigrids and thereby generate a probability maps. So far I successfully used yaImpute to generate maps for Random Forests, Classification trees, Generalized Linear Models (GLMs) and Generalized Additive Models (GAMs). But when I try to use it to two other classifiers
- support vector machine (SVM) and linear discriminant analysis (LDA) - I am
getting an error message which I am not really sure what it is trying to tell me. Can you please take few minutes of your time to help me understand what these error messages are?

I used the following piece of code to apply my models to grids once I fit the model for both LDA and SVM:

AsciiGridPredict(lda.fit,xfiles=namelist,outfiles = as.character(outfile)) AsciiGridPredict(svm.fit,xfiles=namelist,outfiles = as.character(outfile))

I am getting the following error message for LDA:

Rows per dot: 1 Rows to do: 163
ToDo:

...................................................................................................................................................................
Done: .
First six lines of predicted data for map row: 2   predict.class predict.posterior.0 predict.posterior.1 predict.LD1
1         
<NA>              

-9999
-9999 -9999
2 <NA>
-9999
-9999 -9999
3 <NA>
-9999
-9999 -9999
4 <NA>
-9999
-9999 -9999
5 <NA>
-9999
-9999 -9999
6 <NA>
-9999
-9999 -9999

Error in AsciiGridImpute(object, xfiles, outfiles, xtypes = xtypes, lon = lon, :
  predict is not present in the predicted data In addition: Warning message:
In `[<-.factor`(`*tmp*`, ri, value = c(-9999, -9999, -9999, -9999, :   invalid factor level, NAs generated

I am getting the following error message for SVM:

Rows per dot: 1 Rows to do: 163
ToDo:

...................................................................................................................................................................
Done:
...................................................................................................................................................................
Legend of levels in output grids:
  predict
1       0
2       1

There were 50 or more warnings (use warnings() to see the first 50) > warnings()
Warning messages:
1: In `[<-.factor`(`*tmp*`, ri, value = c(-9999, -9999, -9999, ... :   invalid factor level, NAs generated
2: In `[<-.factor`(`*tmp*`, ri, value = c(-9999, -9999, -9999, ... :   invalid factor level, NAs generated
3: In `[<-.factor`(`*tmp*`, ri, value = c(-9999, -9999, -9999, ... :   invalid factor level, NAs generated
4: In `[<-.factor`(`*tmp*`, ri, value = c(-9999, -9999, -9999, ... :   invalid factor level, NAs generated
5: In `[<-.factor`(`*tmp*`, ri, value = c(-9999, -9999, -9999, ... :   invalid factor level, NAs generated

I hope my writing is clear and my questions make sense.

      
	[[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. Received on Wed 26 Nov 2008 - 22:07:20 GMT

Archive maintained by Robert King, hosted by the discipline of statistics at the University of Newcastle, Australia.
Archive generated by hypermail 2.2.0, at Wed 26 Nov 2008 - 23:30:27 GMT.

Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help. Please read the posting guide before posting to the list.

list of date sections of archive