# Load required libraries
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.0     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(caret)
## Loading required package: lattice
## 
## Attaching package: 'caret'
## 
## The following object is masked from 'package:purrr':
## 
##     lift
library(rpart)
library(readxl)

# Load the dataset
hotel_data <- read_excel("C:\\Users\\olajide.shittu\\OneDrive\\Documents\\HOTELS_NEW (ori).xlsx")

#Summary 
summary(hotel_data)
##  User country        Nr. reviews     Nr. hotel reviews Helpful votes   
##  Length:504         Min.   :  1.00   Min.   :  0.00    Min.   :  0.00  
##  Class :character   1st Qu.: 12.00   1st Qu.:  5.00    1st Qu.:  8.00  
##  Mode  :character   Median : 23.50   Median :  9.00    Median : 16.00  
##                     Mean   : 48.13   Mean   : 16.02    Mean   : 31.75  
##                     3rd Qu.: 54.25   3rd Qu.: 18.00    3rd Qu.: 35.00  
##                     Max.   :775.00   Max.   :263.00    Max.   :365.00  
##      Score       Period of stay     Traveler type          Pool          
##  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                                                           
##      Gym            Tennis court           Spa               Casino         
##  Length:504         Length:504         Length:504         Length:504        
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##                                                                             
##                                                                             
##                                                                             
##  Free internet       Hotel name         Hotel stars      Nr. rooms   
##  Length:504         Length:504         Min.   :3.000   Min.   :   0  
##  Class :character   Class :character   1st Qu.:3.000   1st Qu.: 716  
##  Mode  :character   Mode  :character   Median :4.000   Median :2700  
##                                        Mean   :4.048   Mean   :2057  
##                                        3rd Qu.:5.000   3rd Qu.:3025  
##                                        Max.   :5.000   Max.   :4027  
##  User continent      Member years        Review month       Review weekday    
##  Length:504         Min.   :-1806.0000   Length:504         Length:504        
##  Class :character   1st Qu.:    0.0000   Class :character   Class :character  
##  Mode  :character   Median :    3.0000   Mode  :character   Mode  :character  
##                     Mean   :   -0.0556                                        
##                     3rd Qu.:    6.0000                                        
##                     Max.   :   13.0000
# Convert relevant columns to factor (string values)
factor_columns <- c("User country", "Period of stay", "Traveler type", "Pool", "Gym", "Tennis court", "Spa", "Casino", "Free internet", "Hotel name", "User continent", "Review month", "Review weekday")
hotel_data[factor_columns] <- lapply(hotel_data[factor_columns], as.factor)

# Convert Member years to factor (assuming it represents membership duration)
hotel_data$`Member years` <- as.factor(hotel_data$`Member years`)

# Split data into training and testing sets
set.seed(123)
train_index <- createDataPartition(hotel_data$Score, p = 0.8, list = FALSE)
train_data <- hotel_data[train_index, ]
test_data <- hotel_data[-train_index, ]

# Train the Decision Tree model
model_tree <- rpart(Score ~ ., data = train_data)

# Make predictions on test data
predictions <- predict(model_tree, test_data)

# Extract predicted values and convert to factor with levels
predicted_values <- as.factor(ifelse(predictions > 0.5, "Positive", "Negative"))
levels(predicted_values) <- c("Positive", "Negative")

# Convert actual values to factor with levels
actual_values <- as.factor(ifelse(test_data$Score > 0.5, "Positive", "Negative"))
levels(actual_values) <- c("Positive", "Negative")

# Evaluate model performance
performance <- confusionMatrix(predicted_values, actual_values)
print(performance)
## Confusion Matrix and Statistics
## 
##           Reference
## Prediction Positive Negative
##   Positive      100        0
##   Negative        0        0
##                                      
##                Accuracy : 1          
##                  95% CI : (0.9638, 1)
##     No Information Rate : 1          
##     P-Value [Acc > NIR] : 1          
##                                      
##                   Kappa : NaN        
##                                      
##  Mcnemar's Test P-Value : NA         
##                                      
##             Sensitivity :  1         
##             Specificity : NA         
##          Pos Pred Value : NA         
##          Neg Pred Value : NA         
##              Prevalence :  1         
##          Detection Rate :  1         
##    Detection Prevalence :  1         
##       Balanced Accuracy : NA         
##                                      
##        'Positive' Class : Positive   
## 
# Load required libraries
library(caret)

# Generate confusion matrix
conf_matrix <- confusionMatrix(predicted_values, actual_values)

# Plot confusion matrix
plot(conf_matrix$table, col = c("darkgreen", "lightgreen"), 
     main = "Confusion Matrix", 
     xlab = "Predicted", 
     ylab = "Actual")