[BioC] Error in pamr.predict

Hervé Pagès hpages at fhcrc.org
Tue Apr 14 18:55:05 CEST 2009


Hi Richard,

Please update both your R and your pamr. R 2.6.1 is 1.5 year old. The
current stable version is 2.8 and that's the only version supported by
Bioconductor 2.3 (our current release). When you reinstall pamr (and
Bioconductor packages in general), please use biocLite() so that you
get the latest versions of everything + their dependencies. In particular,
that will give you the latest pamr (currently 1.40.0, the pamr on CRAN
is 1.31 only).

See http://bioconductor.org/docs/install/

Cheers,
H.


Richard Yanicky wrote:
> I have an error that occurs with various dataset but always occurs with a
> particular dataset. The dataset is not large and has no missing values.
> I am using R 2.6.1 as a suggestion to isolate the error. Later versions of R
> can cause this error(I am told) and can confirm that this works better under
> 2.6.1.
> 
> copied from below (The error:):
> 
> pred=pamr.predict(pamr.fit,newx=as.matrix(t(d.mv2[,pamrimp])),threshold=Thresh)
> Error in diag.disc((newx - centroid.overall)/sd, delta.shrunk, prior,  :
>   (subscript) logical subscript too long
> 
> If there is other information needed please let me know.
> 
>> pamr.fit<-pamr.train(mydata,n.threshold=50);
> 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950>
> pamcv<-pamr.cv(pamr.fit,mydata);
> 12Fold 1
> :1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
> Fold 2
> :1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
> Fold 3
> :1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
> Fold 4
> :1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
> Fold 5
> :1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
> Fold 6
> :1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
> Fold 7
> :1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
> Fold 8
> :1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
> Fold 9
> :1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
> Fold 10
> :1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950
>> Thresh<-max(pamcv$threshold[pamcv$error== min(pamcv$error)]);
>> Thresh
> [1] 3.692809
>> pamrimplist<-pamr.listgenes(fit=pamr.fit, data=mydata,
>  threshold=Thresh,genenames=TRUE);
>       id name                  1-score 2-score
>  [1,] 1  MMSE                  -1.2997 1.2759
>  [2,] 2  Ab1.42                -0.3874 0.3803
>  [3,] 3  Tau                   0.2667  -0.2618
>  [4,] 4  P.Tau.181P            0.2084  -0.2045
>  [5,] 48 HIPPL.uas             -0.1698 0.1667
>  [6,] 49 HIPPR.uas             -0.1557 0.1529
>  [7,] 10 VENTVOL.bsi           0.1162  -0.114
>  [8,] 6  LEFTHIPPO.ucsfsntvol  -0.0931 0.0914
>  [9,] 7  RIGHTHIPPO.ucsfsntvol -0.0825 0.081
> [10,] 11 VENTVOL.uwo           0.0538  -0.0528
>> pamrimp<-pamrimplist[,2];
>> Thresh
> [1] 3.692809
> pred=pamr.predict(pamr.fit,newx=as.matrix(t(d.mv2[,pamrimp])),threshold=Thresh)
> Error in diag.disc((newx - centroid.overall)/sd, delta.shrunk, prior,  :
>   (subscript) logical subscript too long
> In addition: Warning messages:
> 1: In newx - centroid.overall :
>   longer object length is not a multiple of shorter object length
> 2: In (newx - centroid.overall)/sd :
>   longer object length is not a multiple of shorter object length
>> sessionInfo()
> R version 2.6.1 (2007-11-26)
> i386-pc-mingw32
> 
> locale:
> LC_COLLATE=English_United States.1252;LC_CTYPE=English_United
> States.1252;LC_MONETARY=English_United
> States.1252;LC_NUMERIC=C;LC_TIME=English_United States.1252
> 
> attached base packages:
> [1] splines   stats     graphics  grDevices utils     datasets  methods
> base
> 
> other attached packages:
> [1] pamr_1.31      survival_2.34  cluster_1.11.9
> 
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/bioconductor
> Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor

-- 
Hervé Pagès

Program in Computational Biology
Division of Public Health Sciences
Fred Hutchinson Cancer Research Center
1100 Fairview Ave. N, M2-B876
P.O. Box 19024
Seattle, WA 98109-1024

E-mail: hpages at fhcrc.org
Phone:  (206) 667-5791
Fax:    (206) 667-1319



More information about the Bioconductor mailing list