test

summary(iris)

##   Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
##  Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100  
##  1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300  
##  Median :5.800   Median :3.000   Median :4.350   Median :1.300  
##  Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199  
##  3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800  
##  Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500  
##        Species  
##  setosa    :50  
##  versicolor:50  
##  virginica :50  
##                 
##                 
## 

#1번문제

library(hflights)
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

hflights %>% count(Dest) %>% filter(n==max(n)|n==min(n))

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

#2번문제
table(is.na(hflights$ DepTime))

## 
##  FALSE   TRUE 
## 224591   2905

#3번문제 
table(hflights$Cancelled)

## 
##      0      1 
## 224523   2973

#4번문제
data("airquality")
table(is.na(airquality$Ozone))

## 
## FALSE  TRUE 
##   116    37

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

## [1] 31.5

airquality$Ozone<-ifelse(is.na(airquality$Ozone),31.5,
                        airquality$Ozone)
mean(airquality$Ozone)

## [1] 39.55882

#5번 문제

library("ggplot2")
diamonds %>% select(price) %>% arrange(desc(price)) %>%
  head(3)

## # A tibble: 3 × 1
##   price
##   <int>
## 1 18823
## 2 18818
## 3 18806

print(18823)

## [1] 18823

#6번 문제

diamonds %>% 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.

#7번 문제 

diamonds %>% 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

print(40.0)

## [1] 40

#8번 문제 
library(dplyr)
library(gapminder)
str(gapminder)

## tibble [1,704 × 6] (S3: tbl_df/tbl/data.frame)
##  $ country  : Factor w/ 142 levels "Afghanistan",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ continent: Factor w/ 5 levels "Africa","Americas",..: 3 3 3 3 3 3 3 3 3 3 ...
##  $ year     : int [1:1704] 1952 1957 1962 1967 1972 1977 1982 1987 1992 1997 ...
##  $ lifeExp  : num [1:1704] 28.8 30.3 32 34 36.1 ...
##  $ pop      : int [1:1704] 8425333 9240934 10267083 11537966 13079460 14880372 12881816 13867957 16317921 22227415 ...
##  $ gdpPercap: num [1:1704] 779 821 853 836 740 ...

gapminder %>% filter(continent == "Africa"|continent=="Europe") %>%
  arrange(desc(pop))

## # A tibble: 984 × 6
##    country continent  year lifeExp       pop gdpPercap
##    <fct>   <fct>     <int>   <dbl>     <int>     <dbl>
##  1 Nigeria Africa     2007    46.9 135031164     2014.
##  2 Nigeria Africa     2002    46.6 119901274     1615.
##  3 Nigeria Africa     1997    47.5 106207839     1625.
##  4 Nigeria Africa     1992    47.5  93364244     1620.
##  5 Germany Europe     2007    79.4  82400996    32170.
##  6 Germany Europe     2002    78.7  82350671    30036.
##  7 Germany Europe     1997    77.3  82011073    27789.
##  8 Nigeria Africa     1987    46.9  81551520     1385.
##  9 Germany Europe     1992    76.1  80597764    26505.
## 10 Egypt   Africa     2007    71.3  80264543     5581.
## # ℹ 974 more rows

print(c("Nigeria",2007 ))

## [1] "Nigeria" "2007"

print("Nigeria,2007")

## [1] "Nigeria,2007"