Data

library(readxl)
prakt<-read_excel("D:/praktikumnaive.xlsx")
head(prakt)

## # A tibble: 6 × 5
##   age   income student credit_rating buys_computer
##   <chr> <chr>  <chr>   <chr>         <chr>        
## 1 a     high   no      fair          no           
## 2 a     high   no      excellent     no           
## 3 b     high   no      fair          yes          
## 4 c     medium no      fair          yes          
## 5 c     low    yes     fair          yes          
## 6 c     low    yes     excellent     no

Splitting Data

set.seed(101)
#- split data in training and test set.
Index <- sample(1:nrow(prakt), size = round(0.7*nrow(prakt)), replace=FALSE)
train <- prakt[Index ,]
test <- prakt[-Index ,]

train

## # A tibble: 10 × 5
##    age   income student credit_rating buys_computer
##    <chr> <chr>  <chr>   <chr>         <chr>        
##  1 a     low    yes     fair          yes          
##  2 c     medium no      excellent     no           
##  3 b     low    yes     excellent     yes          
##  4 a     high   no      fair          no           
##  5 c     medium yes     fair          yes          
##  6 c     low    yes     excellent     no           
##  7 b     high   no      fair          yes          
##  8 a     medium no      fair          no           
##  9 a     medium yes     excellent     yes          
## 10 b     medium no      excellent     yes

test

## # A tibble: 4 × 5
##   age   income student credit_rating buys_computer
##   <chr> <chr>  <chr>   <chr>         <chr>        
## 1 a     high   no      excellent     no           
## 2 c     medium no      fair          yes          
## 3 c     low    yes     fair          yes          
## 4 b     high   Yes     fair          yes

Naive Bayes Classifier

NBClassifier <- naiveBayes(buys_computer ~., data = train)
NBClassifier

## 
## Naive Bayes Classifier for Discrete Predictors
## 
## Call:
## naiveBayes.default(x = X, y = Y, laplace = laplace)
## 
## A-priori probabilities:
## Y
##  no yes 
## 0.4 0.6 
## 
## Conditional probabilities:
##      age
## Y             a         b         c
##   no  0.5000000 0.0000000 0.5000000
##   yes 0.3333333 0.5000000 0.1666667
## 
##      income
## Y          high       low    medium
##   no  0.2500000 0.2500000 0.5000000
##   yes 0.1666667 0.3333333 0.5000000
## 
##      student
## Y            no       yes
##   no  0.7500000 0.2500000
##   yes 0.3333333 0.6666667
## 
##      credit_rating
## Y     excellent fair
##   no        0.5  0.5
##   yes       0.5  0.5

# Predict using Naive Bayes
test$predicted <- predict(NBClassifier,test)
test$actual <- test$buys_computer

#confusion matrix
confusionMatrix(factor(test$predicted),
                factor(test$actual))

## Confusion Matrix and Statistics
## 
##           Reference
## Prediction no yes
##        no   1   1
##        yes  0   2
##                                           
##                Accuracy : 0.75            
##                  95% CI : (0.1941, 0.9937)
##     No Information Rate : 0.75            
##     P-Value [Acc > NIR] : 0.7383          
##                                           
##                   Kappa : 0.5             
##                                           
##  Mcnemar's Test P-Value : 1.0000          
##                                           
##             Sensitivity : 1.0000          
##             Specificity : 0.6667          
##          Pos Pred Value : 0.5000          
##          Neg Pred Value : 1.0000          
##              Prevalence : 0.2500          
##          Detection Rate : 0.2500          
##    Detection Prevalence : 0.5000          
##       Balanced Accuracy : 0.8333          
##                                           
##        'Positive' Class : no              
##