Untitled1

#install.packages("dplyr")
library(dplyr)

## 
## 다음의 패키지를 부착합니다: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

#install.packages("hflights")
library(hflights)

#glimpse(hflights)
#colSums(is.na(hflights))

#1
hf<-hflights %>% count(Dest)
head(hf)

##   Dest    n
## 1  ABQ 2812
## 2  AEX  724
## 3  AGS    1
## 4  AMA 1297
## 5  ANC  125
## 6  ASE  125

hf %>% filter(n==max(n)|n==min(n))

##   Dest    n
## 1  AGS    1
## 2  DAL 9820

# 오답: hf %>% max(hf$n)


#2 DepTime 의 결측치 갯수
table(is.na(hflights$DepTime))

## 
##  FALSE   TRUE 
## 224591   2905

sum(is.na(hflights$DepTime))

## [1] 2905

# 오답: count(is.na(hflights$DepTime))


#3 Cancelled의 건수, 취소가 1
sum(hflights$Cancelled)

## [1] 2973

hflights %>%count(hflights$Cancelled==1)

##   hflights$Cancelled == 1      n
## 1                   FALSE 224523
## 2                    TRUE   2973

table(hflights$Cancelled)

## 
##      0      1 
## 224523   2973

#4 Ozone 에서 결측치 제외한 중위수 구하고, 결측치에 중위수 입력후, 평균구하기
rm(list=ls())
data(airquality)
#glimpse(airquality)
#colSums(is.na(airquality))

median(airquality$Ozone,na.rm=TRUE)

## [1] 31.5

air<-airquality
air$Ozone<- ifelse(is.na(airquality$Ozone),31.5,airquality$Ozone)
# 오답: air$Ozone<- ifelse(airquality$Ozone==NA,31.5,airquality$Ozone)
mean(air$Ozone)

## [1] 39.55882

#5 diamonds 데이터셋에서 price 최댓값
library(ggplot2)
#glimpse(diamonds)
#colSums(is.na(diamonds))
max(diamonds$price)

## [1] 18823

#6 cut,color 범주별로 price 평균 구하고, price 내림차순으로 상위 3개 추출
di<-diamonds
#오답: di %>% group_by(cut,color) %>% mean(price)
di %>% group_by(cut,color) %>% summarize(m=mean(price)) %>%
  arrange(desc(m)) %>% head(3)

## `summarise()` has grouped output by 'cut'. You can override using the `.groups`
## argument.

## # A tibble: 3 × 3
## # Groups:   cut [2]
##   cut       color     m
##   <ord>     <ord> <dbl>
## 1 Premium   J     6295.
## 2 Premium   I     5946.
## 3 Very Good I     5256.

  #7 컬럼cut에서 Ideal의 백분율 구해라
  di %>% group_by(cut) %>% summarize(n=n()) %>% 
  mutate(total=sum(n),pct=n/total*100)

## # A tibble: 5 × 4
##   cut           n total   pct
##   <ord>     <int> <int> <dbl>
## 1 Fair       1610 53940  2.98
## 2 Good       4906 53940  9.10
## 3 Very Good 12082 53940 22.4 
## 4 Premium   13791 53940 25.6 
## 5 Ideal     21551 53940 40.0

#8 Europe과 Africa 대륙 중 가장 많은 인구(pop)을 가졌던 국가와 년도 구해라
#install.packages("gapminder")
library(gapminder)
#glimpse(gapminder)

gap<-gapminder

gap1<-gap %>% filter(gap$continent=="Europe"|gap$continent=="Africa") 
gap1 %>% filter(pop==max(pop))

## # A tibble: 1 × 6
##   country continent  year lifeExp       pop gdpPercap
##   <fct>   <fct>     <int>   <dbl>     <int>     <dbl>
## 1 Nigeria Africa     2007    46.9 135031164     2014.