#load the package
library(caret)
## Warning: package 'caret' was built under R version 4.3.2
## Loading required package: ggplot2
## Warning: package 'ggplot2' was built under R version 4.3.2
## Loading required package: lattice
## Warning: package 'lattice' was built under R version 4.3.2
library(klaR)
## Warning: package 'klaR' was built under R version 4.3.3
## Loading required package: MASS
#load the iris dataset
data(iris)
#define an 80%/20% train/test split of the dataset
trainIndex<- createDataPartition(iris$Species, p=0.80, list=FALSE)
dataTrain <- iris[trainIndex,]
dataTest <- iris[-trainIndex,]
#train a naive bayes model
fit <- NaiveBayes(Species~., data=dataTrain)
# make prediction
prediction <- predict(fit, dataTest[,1:4])
#summarize result
confusionMatrix(prediction$class, dataTest$Species)
## Confusion Matrix and Statistics
##
## Reference
## Prediction setosa versicolor virginica
## setosa 10 0 0
## versicolor 0 10 0
## virginica 0 0 10
##
## Overall Statistics
##
## Accuracy : 1
## 95% CI : (0.8843, 1)
## No Information Rate : 0.3333
## P-Value [Acc > NIR] : 4.857e-15
##
## Kappa : 1
##
## Mcnemar's Test P-Value : NA
##
## Statistics by Class:
##
## Class: setosa Class: versicolor Class: virginica
## Sensitivity 1.0000 1.0000 1.0000
## Specificity 1.0000 1.0000 1.0000
## Pos Pred Value 1.0000 1.0000 1.0000
## Neg Pred Value 1.0000 1.0000 1.0000
## Prevalence 0.3333 0.3333 0.3333
## Detection Rate 0.3333 0.3333 0.3333
## Detection Prevalence 0.3333 0.3333 0.3333
## Balanced Accuracy 1.0000 1.0000 1.0000
# ************************************************************
#load library
library(caret)
#load iris dataset
data(iris)
#define training control
trainControl <- trainControl(method="boot", number=100)
#evaluate the model
fit<- train(Species~., data=iris, trControl= trainControl, method= "nb")
## Warning in FUN(X[[i]], ...): Numerical 0 probability for all classes with
## observation 19
#display the result
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 0.9507018 0.9252543
## TRUE 0.9539190 0.9301592
##
## 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.
#load library
library(caret)
#load iris dataset
data(iris)
#define training control
trainControl <- trainControl(method="cv", number=10)
#evaluate the model
fit <- train(Species~., data=iris, trControl=trainControl, method = "nb")
#display the result
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 0.9533333 0.93
##
## 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 = FALSE and adjust
## = 1.
library(caret)
data(iris)
trainControl <- trainControl(method= "repeatedcv", number=10, repeats=3)
fit <- train(Species~., data=iris, trControl=trainControl, 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 0.9555556 0.9333333
## TRUE 0.9533333 0.9300000
##
## 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 = FALSE and adjust
## = 1.
# LEAVE ONE OUT CROSS VALIDATION
library(caret)
data(iris)
trainControl <- trainControl(method="LOOCV")
fit <- train(Species~., data=iris, trControl=trainControl, 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.