PreprocessExample

#Build two predictive models, one using the predictors as they are and one using PCA with principal components explaining 80% of the variance in the predictors. Use method="glm" in the train function.

#What is the accuracy of each method in the test set? Which is more accurate?

library(caret)
library(AppliedPredictiveModeling)
set.seed(3433)

data(AlzheimerDisease)
adData = data.frame(diagnosis,predictors)
inTrain = createDataPartition(adData$diagnosis, p = 3/4, list = FALSE)
training <- adData[inTrain, ]
testing = adData[-inTrain,]

#Column including "IL"
grepIL <- grep("^[Ii][Ll].*", names(training))
new_training <- training[,c(grepIL)]
new_training <- cbind(new_training, diagnosis = training$diagnosis)
new_testing <- testing[,c(grepIL)]
new_testing <- cbind(new_testing, diagnosis = testing$diagnosis)

preProc <- preProcess(new_training[-13], method = "pca", thresh = 0.8)
trainPC <- predict(preProc, new_training[-13])
trainPC <- cbind(trainPC, diagnosis = new_training$diagnosis)
testPC <- predict(preProc, new_testing[-13])
testPC <- cbind(testPC, diagnosis = new_testing$diagnosis)

pcFit <- train(diagnosis~., data = trainPC, method = "glm")
predpcFit <- predict(pcFit, newdata = testPC)
confusionMatrix(predpcFit,testPC$diagnosis)

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction Impaired Control
##   Impaired        3       4
##   Control        19      56
##                                           
##                Accuracy : 0.7195          
##                  95% CI : (0.6094, 0.8132)
##     No Information Rate : 0.7317          
##     P-Value [Acc > NIR] : 0.651780        
##                                           
##                   Kappa : 0.0889          
##  Mcnemar's Test P-Value : 0.003509        
##                                           
##             Sensitivity : 0.13636         
##             Specificity : 0.93333         
##          Pos Pred Value : 0.42857         
##          Neg Pred Value : 0.74667         
##              Prevalence : 0.26829         
##          Detection Rate : 0.03659         
##    Detection Prevalence : 0.08537         
##       Balanced Accuracy : 0.53485         
##                                           
##        'Positive' Class : Impaired        
## 

NonPcFit <- train(diagnosis~., data = new_training, method = "glm")
predNonPcFit <- predict(NonPcFit, newdata = new_testing)
confusionMatrix(predNonPcFit, new_testing$diagnosis)

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction Impaired Control
##   Impaired        2       9
##   Control        20      51
##                                          
##                Accuracy : 0.6463         
##                  95% CI : (0.533, 0.7488)
##     No Information Rate : 0.7317         
##     P-Value [Acc > NIR] : 0.96637        
##                                          
##                   Kappa : -0.0702        
##  Mcnemar's Test P-Value : 0.06332        
##                                          
##             Sensitivity : 0.09091        
##             Specificity : 0.85000        
##          Pos Pred Value : 0.18182        
##          Neg Pred Value : 0.71831        
##              Prevalence : 0.26829        
##          Detection Rate : 0.02439        
##    Detection Prevalence : 0.13415        
##       Balanced Accuracy : 0.47045        
##                                          
##        'Positive' Class : Impaired       
## 

Results : the accuracy of Non-Processd is 0.65, Preprocessd is 0.72.