EDA

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
filtered_data<-subset(data,sex=="female"&smoker=="no"& region=="southeast")
oldest_age<-max(filtered_data$age)

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
filtered_data<-subset(data,region=="northwest"&children==0)
avg_bmi<-mean(filtered_data$bmi)
avg_bmi

## [1] 28.92966

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
filtered_data<-subset(data,sex=="male"&smoker=="no"&region=="southwest")
count_male_non_smokers_sw<-nrow(filtered_data)
count_male_non_smokers_sw

## [1] 126

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
filtered_data<-subset(data,sex=="male"&smoker=="no"&region=="southeast")
get_mode <- function(x) {
  uniq_vals <- unique(x)
  uniq_vals[which.max(tabulate(match(x, uniq_vals)))]
}
mode_children<- get_mode(filtered_data$children)
mode_children

## [1] 0

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
filtered_data <- subset(data,sex=="female"&children=="2"&bmi<25)
sd_charges<-sd(filtered_data$charges)
sd_charges

## [1] 7295.462

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
filtered_data<- subset(data, sex == "female" & smoker == "yes")
count_female_smokers <- nrow(filtered_data)
count_female_smokers

## [1] 115

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
library(moments)
charges_skewness <- skewness(data$charges)
charges_skewness

## [1] 1.51418

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
# Filter for participants below 20
filtered_data<-subset(data,age<20)
max_children <- max(filtered_data$children)
max_children

## [1] 5

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
sd_age <- sd(data$age)
sd_age

## [1] 14.04996

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
region_counts <- table(data$region)
region_counts

## 
## northeast northwest southeast southwest 
##       324       325       364       325

min_count <- min(region_counts)
min_count

## [1] 324

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
median_bmi <- median(data$bmi)
median_bmi

## [1] 30.4

data<-read.csv("C://Users/User//Downloads//health_insurance_charges.csv")
filtered_data<- subset(data, bmi > 40)
median_charge <- median(filtered_data$charges)
median_charge

## [1] 9748.911