20190717 minhee

data load
select
mutate
summarize
wheater

#install.packages(c("nycflights13","tidyverse"))
library("nycflights13")

## Warning: package 'nycflights13' was built under R version 3.6.1

library("tidyverse")

## Warning: package 'tidyverse' was built under R version 3.6.1

## -- Attaching packages ------------------------------------------------ tidyverse 1.2.1 --

## √ ggplot2 3.2.0     √ purrr   0.3.2
## √ tibble  2.1.3     √ dplyr   0.8.3
## √ tidyr   0.8.3     √ stringr 1.4.0
## √ readr   1.3.1     √ forcats 0.4.0

## Warning: package 'readr' was built under R version 3.6.1

## Warning: package 'dplyr' was built under R version 3.6.1

## Warning: package 'forcats' was built under R version 3.6.1

## -- Conflicts --------------------------------------------------- tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

data load

flights

1월만 추출하기

jan1<-flights%>%
  filter(month==1)
jan1

1월1일 추출

new<-flights%>%
  filter(month==1& day==1)
new<-flights%>%
  filter(month==1, day==1)
new

1월이 아닌날

not<-flights%>%
  filter(!month==1)
not

11월,12월

novdec<-flights%>%
  filter(month %in% c(11,12))

novdec<-flights%>%
  filter(month==11|month==12)
novdec

quiz

month = 12,1,2 dep_delay

flights%>%
  filter(month %in% c(1,2,12)&dep_delay>0)

출반지연시간 기준 오름차순

flights%>%
  arrange(dep_delay)

출반지연시간 기준 내림차순

flights%>%
  arrange(desc(dep_delay))

select

-연월일 추출

flights%>%
  select(-year)

flights%>%
  select(year,month,day)

flights%>%
  select(year:day)

mutate

flights

#새로운 변수 붙여서
flights%>%
  select(dep_time:dep_delay)%>%
  mutate("cal_delay"=dep_time-sched_dep_time)

#새로운 변수만
flights%>%
  select(dep_time:dep_delay)%>%
  transmute("cal_delay"=dep_time-sched_dep_time)

summarize

# 월별
flights%>%
  group_by(month)%>%
   summarize("delay_mean"=mean(dep_delay,na.rm=TRUE),
            "delay_max"=max(dep_delay,na.rm=TRUE),
            "delay_min"=min(dep_delay,na.rm=TRUE),
            "delay_median"=median(dep_delay,na.rm=TRUE))

# 항공사별 
a<-flights%>%
  group_by(carrier)%>%
   summarize("delay_mean" = mean(dep_delay,na.rm=TRUE),
            "delay_max" = max(dep_delay,na.rm=TRUE),
            "delay_min" = min(dep_delay,na.rm=TRUE),
            "delay_median" = median(dep_delay,na.rm=TRUE))
names(flights)

##  [1] "year"           "month"          "day"            "dep_time"      
##  [5] "sched_dep_time" "dep_delay"      "arr_time"       "sched_arr_time"
##  [9] "arr_delay"      "carrier"        "flight"         "tailnum"       
## [13] "origin"         "dest"           "air_time"       "distance"      
## [17] "hour"           "minute"         "time_hour"

# 월별 항공사별
flights%>%
  group_by(month,carrier)%>%
   summarize("delay_mean" = mean(dep_delay,na.rm=TRUE),
            "delay_max" = max(dep_delay,na.rm=TRUE),
            "delay_min" = min(dep_delay,na.rm=TRUE),
            "delay_median" = median(dep_delay,na.rm=TRUE))

# 항공사별- delay_mean 정렬
a<-flights%>%
  group_by(carrier)%>%
   summarize("delay_mean" = mean(dep_delay,na.rm=TRUE),
            "delay_max" = max(dep_delay,na.rm=TRUE),
            "delay_min" = min(dep_delay,na.rm=TRUE),
            "delay_median" = median(dep_delay,na.rm=TRUE))
# 순위 달기             
a%>%
  arrange(desc(delay_mean))%>%
  mutate("rank"=1:16)

# 이런 방법도 있대
#library(magrittr)
#b%<>%
#  mutate(rank=1:16)
#b

wheater

year,mon,day 변수 추가 -추가 시에는 format(object,format=“%y(m,d)”)
춘천만 따로 추출하여 지역,평균 기온 변수만 남기고, 가장 추웠던 날짜 순으로 정렬
월별 평균기온, 평균 강수량 table 생성
지점별 평균 기온, 평균 강수량, 평균 풍속, 평균 상대습도 table 생성
지점별,월별 평균 기온/평균 강수량 테이블 생성 후 지점, 월별, 평균 기온 순으로 정렬

1. year,mon,day 변수 추가

library(readxl)

## Warning: package 'readxl' was built under R version 3.6.1

weather<-read_excel("C:/Users/Hallym/Desktop/hey/data/weather.xlsx")
weather

names(weather)

## [1] "지점"          "지점코드"      "일시"          "평균기온"     
## [5] "일강수량"      "평균 풍속"     "평균 상대습도"

weather$year<-format(weather$'일시', format="%y")
weather$mon<-format(weather$'일시', format="%m")
weather$day<-format(weather$'일시', format="%d")
weather

2. 춘천만 따로 추출하여 지역,평균 기온 변수만 남기고, 가장 추웠던 날짜 순으로 정렬

weather%>%
  filter(지점 =="춘천")%>%
  select(지점, 평균기온)%>%
  arrange(평균기온)

3. 월별 평균기온, 평균 강수량 table 생성

weather%>%
  group_by(mon)%>%
  summarize(mean_tem=mean( 평균기온),
            mean_rian=mean( 일강수량))

4. 지점별 평균 기온, 평균 강수량, 평균 풍속, 평균 상대습도 table 생성

colnames(weather)<-c("region","regopn_code","date","tem","rain","wind","wet","year","mon","day") 

weather%>%
  group_by(region) %>%
 summarize(mean_tem=mean(tem),
           mean_rian=mean(rain),
           mean_wind=mean(wind),
           mean_s=mean(wet))

5. 지점별,월별 평균 기온/평균 강수량 테이블 생성 후 지점, 월별, 평균 기온 순으로 정렬

# 1
 w<-weather%>%
  group_by(region,mon)%>%
  summarize(mean_tem=mean(tem),
           mean_rian=mean(rain))

  w%>%arrange(region,mon,mean_tem)

# 2
  data.frame(weather%>%
  group_by(region,mon)%>%
  summarize(mean_tem=mean(tem),
           mean_rian=mean(rain))%>%
    arrange(region,mon))