Naive Bayes for Las Vegas Trip Advisor Dataset

#Import the dataset

data=read.csv("lasvegas.csv")
View(data)
data=data[c(5,8,9,10,11,12,13)]
summary(data)

##      Score           Pool               Gym            Tennis.court      
##  Min.   :1.000   Length:504         Length:504         Length:504        
##  1st Qu.:4.000   Class :character   Class :character   Class :character  
##  Median :4.000   Mode  :character   Mode  :character   Mode  :character  
##  Mean   :4.123                                                           
##  3rd Qu.:5.000                                                           
##  Max.   :5.000                                                           
##      Spa               Casino          Free.internet     
##  Length:504         Length:504         Length:504        
##  Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character  
##                                                          
##                                                          
## 

data$Score <- with(data, ifelse(Score<=3,"Worst",("Best")))
data$Score<-factor(data$Score)
View(data)

#Splitting the dataset

library(caTools)
set.seed(899)
split=sample.split(data$Score,SplitRatio = 2/3)
training_set=subset(data,split==T)
test_set=subset(data,split==F)
dim(training_set)

## [1] 336   7

#Fitting a training model

library(e1071)
classifier=naiveBayes(x=training_set[-1],y=training_set$Score)
summary(classifier)

##           Length Class  Mode     
## apriori   2      table  numeric  
## tables    6      -none- list     
## levels    2      -none- character
## isnumeric 6      -none- logical  
## call      3      -none- call

#Prediction
y_pred=predict(object = classifier,newdata=test_set)
y_pred

##   [1] Worst Worst Worst Worst Best  Best  Best  Best  Best  Best  Best  Best 
##  [13] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
##  [25] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
##  [37] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
##  [49] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
##  [61] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
##  [73] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
##  [85] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
##  [97] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
## [109] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
## [121] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
## [133] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
## [145] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
## [157] Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best  Best 
## Levels: Best Worst

#Confusion matrix
err_metric=function(CM)
{
  
  TN =CM[2,2]
  TP =CM[1,1]
  FP =CM[1,2]
  FN =CM[2,1]
  precision =(TP)/(TP+FP)
  recall_score =(TP)/(TP+FN)
  f1_score=2*((precision*recall_score)/(precision+recall_score))
  accuracy_model  =(TP+TN)/(TP+TN+FP+FN)
  False_positive_rate =(FP)/(FP+TN)
  False_negative_rate =(FN)/(FN+TP)
  print(paste("Precision value of the model: ",round(precision,2)))
  print(paste("Accuracy of the model: ",round(accuracy_model,2)))
  print(paste("Recall value of the model: ",round(recall_score,2)))
  print(paste("False Positive rate of the model: ",round(False_positive_rate,2)))
  print(paste("False Negative rate of the model: ",round(False_negative_rate,2)))
  print(paste("f1 score of the model: ",round(f1_score,2)))
}

cm=table(test_set[,1],y_pred)
cm

##        y_pred
##         Best Worst
##   Best   129     1
##   Worst   35     3

err_metric(cm)

## [1] "Precision value of the model:  0.99"
## [1] "Accuracy of the model:  0.79"
## [1] "Recall value of the model:  0.79"
## [1] "False Positive rate of the model:  0.25"
## [1] "False Negative rate of the model:  0.21"
## [1] "f1 score of the model:  0.88"