Activity 8

Load Required Libraries

#install.packages("rpart")
#install.packages("rpart.plot")
#install.packages("Cubist")
library(rpart)
library(rpart.plot)
library(Cubist)

# Load insurance dataset
insurance <- read.csv("insurance.csv", stringsAsFactors = TRUE)
str(insurance)

'data.frame':   1338 obs. of  7 variables:
 $ age     : int  19 18 28 33 32 31 46 37 37 60 ...
 $ sex     : Factor w/ 2 levels "female","male": 1 2 2 2 2 1 1 1 2 1 ...
 $ bmi     : num  27.9 33.8 33 22.7 28.9 25.7 33.4 27.7 29.8 25.8 ...
 $ children: int  0 1 3 0 0 0 1 3 2 0 ...
 $ smoker  : Factor w/ 2 levels "no","yes": 2 1 1 1 1 1 1 1 1 1 ...
 $ region  : Factor w/ 4 levels "northeast","northwest",..: 4 3 3 2 2 3 3 2 1 2 ...
 $ expenses: num  16885 1726 4449 21984 3867 ...

# Display statistical summary of expenses
summary(insurance$expenses)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   1122    4740    9382   13270   16640   63770 

# Visualizing the distribution of expenses using a histogram
hist(insurance$expenses, main = "Distribution of Insurance Expenses", xlab = "Expenses", col = "lightblue", border = "black")

# Display frequency distribution of the 'region' variable
table(insurance$region)

northeast northwest southeast southwest 
      324       325       364       325 

# Compute correlation matrix for key numerical variables
correlation_matrix <- cor(insurance[, c("age", "bmi", "children", "expenses")])
print(correlation_matrix)

               age        bmi   children   expenses
age      1.0000000 0.10934101 0.04246900 0.29900819
bmi      0.1093410 1.00000000 0.01264471 0.19857626
children 0.0424690 0.01264471 1.00000000 0.06799823
expenses 0.2990082 0.19857626 0.06799823 1.00000000

# Making predictions using the pre-trained model 'ins_model2'
# Case 1 Prediction
case1_prediction <- predict(ins_model2, newdata = data.frame(
  age = 22, age2 = 22^2, children = 3,
  bmi = 24, sex = "female", bmi30 = 0,
  smoker = "no", region = "northwest"
))

# Case 2 Prediction
case2_prediction <- predict(ins_model2, newdata = data.frame(
  age = 22, age2 = 22^2, children = 1,
  bmi = 27, sex = "male", bmi30 = 0,
  smoker = "yes", region = "southeast"
))

# Output results
cat("Predicted Expense for Case 1:", case1_prediction, "\n")

Predicted Expense for Case 1: 3357.248 

cat("Predicted Expense for Case 2:", case2_prediction, "\n")

Predicted Expense for Case 2: 25760.86