Reading excel into R

install.packages("openxlsx")
install.packages("caret")

# Loading the required libraries
library(openxlsx)
library(caret)

data<- read.xlsx("C:\\Users\\Study\\Desktop\\r files\\DekutR session\\R assignment\\insurance_data.xlsx", sheet=1)

# Checking data
head(data)

# Creating a multiple linear regression model
model <- lm(charges ~ age + children + sex + bmi +smoker + region, data )
summary(model)

Call:
lm(formula = charges ~ age + children + sex + bmi + smoker + 
    region, data = data)

Residuals:
     Min       1Q   Median       3Q      Max 
-11304.9  -2848.1   -982.1   1393.9  29992.8 

Coefficients:
                Estimate Std. Error t value Pr(>|t|)    
(Intercept)     -11938.5      987.8 -12.086  < 2e-16 ***
age                256.9       11.9  21.587  < 2e-16 ***
children           475.5      137.8   3.451 0.000577 ***
sexmale           -131.3      332.9  -0.394 0.693348    
bmi                339.2       28.6  11.860  < 2e-16 ***
smokeryes        23848.5      413.1  57.723  < 2e-16 ***
regionnorthwest   -353.0      476.3  -0.741 0.458769    
regionsoutheast  -1035.0      478.7  -2.162 0.030782 *  
regionsouthwest   -960.0      477.9  -2.009 0.044765 *  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 6062 on 1329 degrees of freedom
Multiple R-squared:  0.7509,    Adjusted R-squared:  0.7494 
F-statistic: 500.8 on 8 and 1329 DF,  p-value: < 2.2e-16

# Converting a column in the data into a factor
data$sex <- as.factor(data$sex)
data$region <- as.factor(data$region)
data$smoker <- as.factor(data$smoker)
print(data)

levels(data$sex)

[1] "female" "male"  

levels(data$region)

[1] "northeast" "northwest" "southeast" "southwest"

levels(data$smoker)

[1] "no"  "yes"

# Creating new data for clients aged 20 and 45
new_data <- data.frame(age = c(20,45),
                       children = c(0,0),
                       sex = factor("male", "female"),levels = levels(data$sex),
                       bmi = c(26.22, 39.6), 
                       smoker = factor("yes", "no"), levels = levels(data$smoker),
                       region = factor("norththeast", "northwest"), levels(data$region))

# making predictions
predictions <- predict(model, new_data)

head(predictions)

 1  2  3  4 
NA NA NA NA