Hi experts,
I am working on Fix 1.06 on R 3.3.3
The .Rlog1 shows that
...
> # # (1)
> train.data <- hcp.data
> # SVM
> svm.rbf1 <- svm(class.labs ~ ., data = train.data, probability = T, scale = T, kernel = "radial")
Warning message:
In svm.default(x, y, scale = scale, ..., na.action = na.action) :
Variable(s) ‘number.of.ics’ and ‘xlen’ and ‘zlen’ and ‘tlen’ and ‘xres’ and ‘tres’ constant. Cannot scale data.
> svm.rbf.prd1 <- attributes(predict(svm.rbf1, train.data, probability=T))$probabilities[,2]
> svm.lin1 <- svm(class.labs ~ ., data = train.data, probability = T, scale = T, kernel = "linear")
Warning message:
In svm.default(x, y, scale = scale, ..., na.action = na.action) :
Variable(s) ‘number.of.ics’ and ‘xlen’ and ‘zlen’ and ‘tlen’ and ‘xres’ and ‘tres’ constant. Cannot scale data.
> svm.lin.prd1 <- attributes(predict(svm.lin1, train.data, probability=T))$probabilities[,2]
> svm.pol1 <- svm(class.labs ~ ., data = train.data, probability = T, scale = T, kernel = "polynomial")
Warning message:
In svm.default(x, y, scale = scale, ..., na.action = na.action) :
Variable(s) ‘number.of.ics’ and ‘xlen’ and ‘zlen’ and ‘tlen’ and ‘xres’ and ‘tres’ constant. Cannot scale data.
> svm.pol.prd1 <- attributes(predict(svm.pol1, train.data, probability=T))$probabilities[,2]
> # KNN
> tmp <- knn(train.data[,-dim(train.data)[2]], train.data[,-dim(train.data)[2]], train.data[,dim(train.data)[2]], k = k.knn, prob = T)
Error in knn(train.data[, -dim(train.data)[2]], train.data[, -dim(train.data)[2]], :
no missing values are allowed
Execution halted
When I checked the "features.csv", it showes on column 179 'xLen' with 'NaN'.
When normal Image Acquisition Parameters for this study retrieved in 'features.csv' are: 88 88 64 941 2.5 2.5 2.5 0.607
the csv that missed the xLen shows: NaN 88 88 64 16 2.5 2.5 2.5
The 'fslinfo' returned:
data_type FLOAT32
dim1 88
dim2 88
dim3 64
dim4 941
datatype 16
pixdim1 2.500000
pixdim2 2.500000
pixdim3 2.500000
pixdim4 0.607000
cal_max 0.0000
cal_min 0.0000
file_type NIFTI-1+
The misplacement of the parameters occurred on two scans. How shall I fix this?
Thank you!
Jianhang
Project Assistant
Imaging Genetics Center
USC, US
########################################################################
To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1
|