#±âÃâ¹®Á¦

# ÀÛ¾÷Çü Á¦ 1À¯Çü

.libPaths("C:/myRproject/Library")

#1¹ø ¹®Á¦
install.packages("mlbench")
library(mlbench)

data(BostonHousing)
df<-BostonHousing
str(df)

library(dplyr)
df_1<- df %>% arrange(desc(crim))
df_1[1:10,1]<-df_1[10,1]
result <- df_1 %>% filter(age>=80) %>%  summarise(mean=mean(crim))
print(result)



#2¹ø ¹®Á¦

df<-read.csv("https://raw.githubusercontent.com/ageron/handson-ml/master/datasets/housing/housing.csv")
str(df)
summary(df)
train<-df[c(1:nrow(df)*0.8),]


 
sd_1<- sd(train$total_bedrooms, na.rm=T)
sd_2<-train %>% mutate(new = ifelse(is.na(total_bedrooms), median(total_bedrooms, na.rm=T), total_bedrooms)) %>% summarise(sd=sd(new)) 

print(abs(sd_1-sd_2))


#3¹ø ¹®Á¦

df<-read.csv("https://raw.githubusercontent.com/stedy/Machine-Learning-with-R-datasets/d20658ec6d336af2d4ddb5fd72b6f677dd46136e/insurance.csv")
str(df)
summary(df)

fivenum(df$charges)

low <- fivenum(df[,7])[2] - 1.5*IQR(df[,7])
upp <- fivenum(df[,7])[4] + 1.5*IQR(df[,7])

fivenum(df[,7])

which(df[,7]<low)
result <- sum(df[which(df[,7]>=upp | df[,7]<=low),7])
print(result)