All,
I am beginner in R here.I am working on SVM and am getting the below errors
wheneverI call the predict function.I have tried reading the manual for
predict() butI am totally stumped and not able to move further.
> pred <- predict(model, Test[,-1])Error in scale(newdata[, object$scaled, drop
> = FALSE], center = object$x.scale$"scaled:center", : (subscript) logical
> subscript too long The actual data sets are very huge , hence I am
> replicating it on a smaller basis. My dataset contains lots of 'NA' values.
The code I am calling is > TrainingSet <-
read.csv('TrainA.csv',header=TRUE)> TestingSet <-
read.csv('TestA.csv',header=TRUE)
> Train <- subset(TrainingSet, select=c(-Class)) > Train_Class <-
> subset(TrainingSet, select=Class)
> Test <- subset(TestingSet, select=c(-Class))> Test_Class <-
> subset(TestingSet, select=Class)
> model <- svm(Train[,-1], Train_Class, kernel="linear", cross=10,
> na.action=na.omit)> model
Call:svm.default(x = Train[, -1], y = Train_Class, kernel = "linear", cross =
10, na.action = na.omit)
Parameters: SVM-Type: eps-regression SVM-Kernel: linear cost: 1
gamma: 0.3333333 epsilon: 0.1
Number of Support Vectors: 18
> Class <- Test_Class$Class> pred <- predict(model, Test[,-1])Error in
> scale(newdata[, object$scaled, drop = FALSE], center =
> object$x.scale$"scaled:center", : (subscript) logical subscript too long
Training data set:
Gene_Symbol Class Subj-1 Subj-2 Subj-313CDNA73 0 0.225 -0.378
0.92720D7-FC4 0 1.668 1.762 1.445384D8-2 0 0.52 -1.019
1.58854TM 0 3.094 5.114 2.7435T4 0 -1.138 1.158
0.0176P 0 1.588 -2.541 -1.023A 0 -0.649 -1.884 1.253A2LP
0 1.765 3.75 -0.259AAMP 0 -1.133 -0.309 -1.557AARS
1 3.132 0.432 2.4AB026190 1 -0.244 -0.06 -0.021ABCA3
1 -0.003 -1.673 1.272ABCA4 1 -1.017 -0.493 -0.751ABCA5
1 3.319 3.234 0.503ABCA6 1 2.692 0.039 4.017ABCB1
1 0.362 -0.362 0.862ABCB10 1 0.028 -1.962 -0.795ABCC1
1 1.963 3.475 0.202ABCC2 1 -0.942 -3.496 0.297
Test Gene_Symbol Class Subj-1 Subj-2RBP3 0 -0.762
-1.132RBP4 0 0.494 3.802RBPMS 0 -0.311 0.612RBSK
0 -0.759 1.206RBX1 0 0.047 -0.31RCD-8 0 -0.42
-3.001RCL 1 -0.388 1.046RCN1 1 0.476 -1.092RCN2
1 -0.469 -0.707RCV1 1 -2.071 -0.854RDBP 1 0.904
1.325RDC1 1 1.668 1.905REA 1 0.09 -0.531RECQL
1 -1.957 -2.481
Any pointers on how to deal with the error would be greatly
appreciated.ThanksSavitha
[[alternative HTML version deleted]]
______________________________________________
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.
