빅데이터분석 실무 2일차

getwd()

## [1] "C:/data"

setwd("c:/data")

ls()

## character(0)

rm(list=ls())
ls()

## character(0)

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

df<-read.csv("ta1.csv", fileEncoding = "euc-kr")
View(df)

names(df)

## [1] "가해자연령층별.1." "월별.1."           "X2022"            
## [4] "X2022.1"           "X2022.2"

df1 <- df %>% rename(month=월별.1.,사고건수=X2022,사망자수=X2022.1,
              연령층=가해자연령층별.1.,부상자수=X2022.2)

View(df1)

df2 <- df1 %>% slice(-1)

df2 %>% filter(month!="전체") %>% glimpse()

## Rows: 108
## Columns: 5
## $ 연령층   <chr> "20세이하", "20세이하", "20세이하", "20세이하", "20세이하", "…
## $ month    <chr> "1월", "2월", "3월", "4월", "5월", "6월", "7월", "8월", "9월"…
## $ 사고건수 <chr> "435", "357", "473", "580", "713", "668", "639", "557", "609"…
## $ 사망자수 <chr> "6", "2", "3", "7", "6", "5", "6", "7", "8", "8", "8", "6", "…
## $ 부상자수 <chr> "633", "505", "678", "810", "955", "877", "847", "735", "808"…

df2$사고건수<-as.numeric(df2$사고건수)
glimpse(df2)

## Rows: 117
## Columns: 5
## $ 연령층   <chr> "20세이하", "20세이하", "20세이하", "20세이하", "20세이하", "…
## $ month    <chr> "전체", "1월", "2월", "3월", "4월", "5월", "6월", "7월", "8월…
## $ 사고건수 <dbl> 6508, 435, 357, 473, 580, 713, 668, 639, 557, 609, 618, 532, …
## $ 사망자수 <chr> "72", "6", "2", "3", "7", "6", "5", "6", "7", "8", "8", "8", …
## $ 부상자수 <chr> "8863", "633", "505", "678", "810", "955", "877", "847", "735…

#install.packages("gapminder")
library(gapminder)
y <- gapminder %>% group_by(year, continent) %>% summarize(c_pop=sum(pop))

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

head(y, 20)

## # A tibble: 20 × 3
## # Groups:   year [4]
##     year continent      c_pop
##    <int> <fct>          <dbl>
##  1  1952 Africa     237640501
##  2  1952 Americas   345152446
##  3  1952 Asia      1395357351
##  4  1952 Europe     418120846
##  5  1952 Oceania     10686006
##  6  1957 Africa     264837738
##  7  1957 Americas   386953916
##  8  1957 Asia      1562780599
##  9  1957 Europe     437890351
## 10  1957 Oceania     11941976
## 11  1962 Africa     296516865
## 12  1962 Americas   433270254
## 13  1962 Asia      1696357182
## 14  1962 Europe     460355155
## 15  1962 Oceania     13283518
## 16  1967 Africa     335289489
## 17  1967 Americas   480746623
## 18  1967 Asia      1905662900
## 19  1967 Europe     481178958
## 20  1967 Oceania     14600414

View(gapminder)

plot(y$year, y$c_pop)

plot(log10(gapminder$gdpPercap),gapminder$lifeExp,col=gapminder$continent)
legend("bottomright",legend=levels(gapminder$continent),
        pch=c(1:length(levels(gapminder$continent))),
        col=c(1:length(levels(y$continent))))

#install.packages("ggplot2")
library(ggplot2)

ggplot(gapminder,aes(x=gdpPercap,y=lifeExp,col=continent,size=pop))+
  geom_point()+scale_x_log10()

scale_x_log10()

## <ScaleContinuousPosition>
##  Range:  
##  Limits:    0 --    1

ggplot(gapminder,aes(x=gdpPercap,y=lifeExp,col=continent,size=pop))+
  geom_point(alpha=0.5)+scale_x_log10()

ggplot(gapminder,aes(x=gdpPercap,y=lifeExp,col=continent,size=pop))+
  geom_point(alpha=0.5)+scale_x_log10()+facet_wrap(~year)

gapminder %>% filter(year==1952&continent=="Asia") %>%
  ggplot(aes(reorder(country,pop),pop))+geom_bar(stat='identity')+coord_flip()

gapminder %>% count(continent)

## # A tibble: 5 × 2
##   continent     n
##   <fct>     <int>
## 1 Africa      624
## 2 Americas    300
## 3 Asia        396
## 4 Europe      360
## 5 Oceania      24

gapminder %>% filter(country=='Korea, Rep.')

## # A tibble: 12 × 6
##    country     continent  year lifeExp      pop gdpPercap
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
##  1 Korea, Rep. Asia       1952    47.5 20947571     1031.
##  2 Korea, Rep. Asia       1957    52.7 22611552     1488.
##  3 Korea, Rep. Asia       1962    55.3 26420307     1536.
##  4 Korea, Rep. Asia       1967    57.7 30131000     2029.
##  5 Korea, Rep. Asia       1972    62.6 33505000     3031.
##  6 Korea, Rep. Asia       1977    64.8 36436000     4657.
##  7 Korea, Rep. Asia       1982    67.1 39326000     5623.
##  8 Korea, Rep. Asia       1987    69.8 41622000     8533.
##  9 Korea, Rep. Asia       1992    72.2 43805450    12104.
## 10 Korea, Rep. Asia       1997    74.6 46173816    15994.
## 11 Korea, Rep. Asia       2002    77.0 47969150    19234.
## 12 Korea, Rep. Asia       2007    78.6 49044790    23348.

#gapminder %>% filter(country=='Korea, Rep.') %>% ggplot(aes(year,lifeExp,
#                                                            ))