activity 8

#I import the dataset in R
#I did the first stepts of activity 7, then used the MLR solution built during class 
# summarize the charges variable
summary(insurance$expenses)

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

# histogram of insurance charges
hist(insurance$expenses)

# table of region
table(insurance$region)

northeast northwest southeast southwest 
      324       325       364       325 

# exploring relationships among features: correlation matrix
cor(insurance[c("age", "bmi", "children", "expenses")])

               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

# Predict for Case 1
case1 <- predict(ins_model2,
        data.frame(age = 22, age2 = 22^2, children = 3,
                   bmi = 24, sex = "female", bmi30 = 0,
                   smoker = "no", region = "northwest"))

# Predict for Case 2
case2 <- predict(ins_model2,
        data.frame(age = 22, age2 = 22^2, children = 1,
                   bmi = 27, sex = "male", bmi30 = 0,
                   smoker = "yes", region = "southeast"))

# Print results
cat("Case 1 Prediction:", case1, "\n")

Case 1 Prediction: 5858.241 

cat("Case 2 Prediction:", case2, "\n")

Case 2 Prediction: 17219.31