## load packages
library (caret)
## 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 Iris Dataset
data(iris)

set.seed(1234)
#defin an 80%/20% train/test split of the dataset
trainIndex <- createDataPartition(iris$Species, p=0.80, list=FALSE)
dataTrain <- iris[trainIndex,]
dataTest <- iris[-trainIndex,]

#Train Naive Bayes Model
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         2
##   virginica       0          1         8
## 
## Overall Statistics
##                                           
##                Accuracy : 0.9             
##                  95% CI : (0.7347, 0.9789)
##     No Information Rate : 0.3333          
##     P-Value [Acc > NIR] : 1.665e-10       
##                                           
##                   Kappa : 0.85            
##                                           
##  Mcnemar's Test P-Value : NA              
## 
## Statistics by Class:
## 
##                      Class: setosa Class: versicolor Class: virginica
## Sensitivity                 1.0000            0.9000           0.8000
## Specificity                 1.0000            0.9000           0.9500
## Pos Pred Value              1.0000            0.8182           0.8889
## Neg Pred Value              1.0000            0.9474           0.9048
## Prevalence                  0.3333            0.3333           0.3333
## Detection Rate              0.3333            0.3000           0.2667
## Detection Prevalence        0.3333            0.3667           0.3000
## Balanced Accuracy           1.0000            0.9000           0.8750
####################################Boostrapping #############33

library(caret)
#LOAD IRIS dataset
data(iris)
#define trainining control
tfControl <- trainControl(method="boot", number=100)
#trainControl
fit <- train (Species ~ . , data=iris , trControl=tfControl , method="nb")
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      0.9489081  0.9227193
##    TRUE      0.9497630  0.9240659
## 
## 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.
################ Cross Validation, CV #######################3

library(caret)
#LOAD IRIS dataset
data(iris)
#define trainining control
tfControl <- trainControl(method="cv", number=10)
#trainControl
fit <- train (Species ~ . , data=iris , trControl=tfControl , method="nb")
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.
################ Repeated Cross Validation, CV #######################3

library(caret)
#LOAD IRIS dataset
data(iris)
#define trainining control
tfControl <- trainControl(method="repeatedcv", number=10, repeats=3)
#trainControl
fit <- train (Species ~ . , data=iris , trControl=tfControl , method="nb")
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  0.93 
##    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.
################ LOOCV #######################3

library(caret)
#LOAD IRIS dataset
data(iris)
#define trainining control
tfControl <- trainControl(method="LOOCV")
#trainControl
fit <- train (Species ~ . , data=iris , trControl=tfControl , method="nb")
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.