#load the packages
library(caret)
## Warning: package 'caret' was built under R version 4.3.3
## Loading required package: ggplot2
## Loading required package: lattice
library(klaR)
## Warning: package 'klaR' was built under R version 4.3.3
## Loading required package: MASS
#load the iris dataset
data(iris)

#define 80%/20% train/test split of the dataset
trainIndex <- createDataPartition(iris$Species, p=0.80, list=FALSE)
dataTrain <- iris[ trainIndex, ]
dataTest <- iris[ -trainIndex, ]

#train a naive Bayes moddel
fit <- NaiveBayes(Species~., data=dataTrain)
#make predictions
predictions <- predict(fit, dataTest[,1:4])
#summarize results
confusionMatrix(predictions$class, dataTest$Species)
## Confusion Matrix and Statistics
## 
##             Reference
## Prediction   setosa versicolor virginica
##   setosa         10          0         0
##   versicolor      0          9         1
##   virginica       0          1         9
## 
## Overall Statistics
##                                           
##                Accuracy : 0.9333          
##                  95% CI : (0.7793, 0.9918)
##     No Information Rate : 0.3333          
##     P-Value [Acc > NIR] : 8.747e-12       
##                                           
##                   Kappa : 0.9             
##                                           
##  Mcnemar's Test P-Value : NA              
## 
## Statistics by Class:
## 
##                      Class: setosa Class: versicolor Class: virginica
## Sensitivity                 1.0000            0.9000           0.9000
## Specificity                 1.0000            0.9500           0.9500
## Pos Pred Value              1.0000            0.9000           0.9000
## Neg Pred Value              1.0000            0.9500           0.9500
## Prevalence                  0.3333            0.3333           0.3333
## Detection Rate              0.3333            0.3000           0.3000
## Detection Prevalence        0.3333            0.3333           0.3333
## Balanced Accuracy           1.0000            0.9250           0.9250
#define training control- bootstrap method
trainControl <- trainControl(method="boot", number=100)
#evaluate the model
fit <- train(Species~., data=iris, trControl=trainControl, method="nb")
#display the results
print(fit)
## Naive Bayes 
## 
## 150 samples
##   4 predictor
##   3 classes: 'setosa', 'versicolor', 'virginica' 
## 
## No pre-processing
## Resampling: Bootstrapped (100 reps) 
## Summary of sample sizes: 150, 150, 150, 150, 150, 150, ... 
## Resampling results across tuning parameters:
## 
##   usekernel  Accuracy   Kappa    
##   FALSE      0.9552417  0.9321643
##    TRUE      0.9576018  0.9357006
## 
## Tuning parameter 'fL' was held constant at a value of 0
## Tuning
##  parameter 'adjust' was held constant at a value of 1
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were fL = 0, usekernel = TRUE and adjust
##  = 1.
#define training control- k-fold cv method
trainControl <- trainControl(method="cv", number=10)
#evaluate the model
fit <- train(Species~., data=iris, trControl=trainControl, method="nb")
#display the results
print(fit)
## Naive Bayes 
## 
## 150 samples
##   4 predictor
##   3 classes: 'setosa', 'versicolor', 'virginica' 
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold) 
## Summary of sample sizes: 135, 135, 135, 135, 135, 135, ... 
## Resampling results across tuning parameters:
## 
##   usekernel  Accuracy   Kappa
##   FALSE      0.9533333  0.93 
##    TRUE      0.9600000  0.94 
## 
## Tuning parameter 'fL' was held constant at a value of 0
## Tuning
##  parameter 'adjust' was held constant at a value of 1
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were fL = 0, usekernel = TRUE and adjust
##  = 1.
#define training control- repeated k-fold cv method
trainControl <- trainControl(method="repeatedcv", number=10, repeats=3)
#results in 30 folds total (10*3)
#evaluate the model
fit <- train(Species~., data=iris, trControl=trainControl, method="nb")
#display the results
print(fit)
## Naive Bayes 
## 
## 150 samples
##   4 predictor
##   3 classes: 'setosa', 'versicolor', 'virginica' 
## 
## No pre-processing
## Resampling: Cross-Validated (10 fold, repeated 3 times) 
## Summary of sample sizes: 135, 135, 135, 135, 135, 135, ... 
## Resampling results across tuning parameters:
## 
##   usekernel  Accuracy   Kappa    
##   FALSE      0.9533333  0.9300000
##    TRUE      0.9555556  0.9333333
## 
## Tuning parameter 'fL' was held constant at a value of 0
## Tuning
##  parameter 'adjust' was held constant at a value of 1
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were fL = 0, usekernel = TRUE and adjust
##  = 1.
#define training control- Leave out one CV method
trainControl <- trainControl(method="LOOCV")
#evaluate the model
fit <- train(Species~., data=iris, trControl=trainControl, method="nb")
#display the results
print(fit)
## Naive Bayes 
## 
## 150 samples
##   4 predictor
##   3 classes: 'setosa', 'versicolor', 'virginica' 
## 
## No pre-processing
## Resampling: Leave-One-Out Cross-Validation 
## Summary of sample sizes: 149, 149, 149, 149, 149, 149, ... 
## Resampling results across tuning parameters:
## 
##   usekernel  Accuracy   Kappa
##   FALSE      0.9533333  0.93 
##    TRUE      0.9600000  0.94 
## 
## Tuning parameter 'fL' was held constant at a value of 0
## Tuning
##  parameter 'adjust' was held constant at a value of 1
## Accuracy was used to select the optimal model using the largest value.
## The final values used for the model were fL = 0, usekernel = TRUE and adjust
##  = 1.