Caret: undefined columns selected

Question

I try this model fit but it gives me this error :

Error in [.data.frame(data, , all.vars(Terms), drop = FALSE) : undefined columns selected

library(caret) ; library(kernlab) ; data(spam)

intrain <- createDataPartition(spam$type,p=0.75,list = F)
training <- spam\[intrain,]
test <- spam[-intrain,]

preProc <- preProcess(log10(training\[,-58\]+1),method="pca",pcaComp=2)
trainPC <- predict(preProc,log10(training\[,-58]+1))

Error in the line below

modelFit <- train(training$type~.,method="glm",data=trainPC)

Or

modelFit <- train(training$type~ .,method="glm",preProcess="pca",data=training)

Answer 1

While there are warnings (not the best method as data is categorical). This works:

modelFit <- train(y=training$type,
                  x=trainPC,
                  method="glm")

summary(modelFit)

Call:
NULL

Deviance Residuals: 
    Min       1Q   Median       3Q      Max  
-3.8587  -0.3801  -0.0874   0.1967   3.7056  

Coefficients:
            Estimate Std. Error z value Pr(>|z|)    
(Intercept) -1.07856    0.09537 -11.309   <2e-16 ***
PC1         -1.79073    0.09707 -18.448   <2e-16 ***
PC2          0.62770    0.06655   9.432   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

(Dispersion parameter for binomial family taken to be 1)

    Null deviance: 4628.1  on 3450  degrees of freedom
Residual deviance: 1755.1  on 3448  degrees of freedom
AIC: 1761.1

Number of Fisher Scoring iterations: 7