#欄位簡介
# "country" 國家
# "continent" 洲
# "year"年
# "lifeExp"預期壽命
# "pop" 人口
# "gdpPercap"人均GDP
#一、先安裝下列套件
install.packages("gapminder")
## Installing package into '/home/rstudio-user/R/x86_64-pc-linux-gnu-library/4.0'
## (as 'lib' is unspecified)
install.packages("ggplot2")
## Installing package into '/home/rstudio-user/R/x86_64-pc-linux-gnu-library/4.0'
## (as 'lib' is unspecified)
install.packages("tidyverse")
## Installing package into '/home/rstudio-user/R/x86_64-pc-linux-gnu-library/4.0'
## (as 'lib' is unspecified)
install.packages("gridExtra")
## Installing package into '/home/rstudio-user/R/x86_64-pc-linux-gnu-library/4.0'
## (as 'lib' is unspecified)
#二、呼叫gapminder套件
library(gapminder)
#gapminder套件的內容就是一個名為gapminder的資料檔，以下是查看資料的方式
dim(gapminder)
## [1] 1704 6
head(gapminder)
## # A tibble: 6 x 6
## country continent year lifeExp pop gdpPercap
## <fct> <fct> <int> <dbl> <int> <dbl>
## 1 Afghanistan Asia 1952 28.8 8425333 779.
## 2 Afghanistan Asia 1957 30.3 9240934 821.
## 3 Afghanistan Asia 1962 32.0 10267083 853.
## 4 Afghanistan Asia 1967 34.0 11537966 836.
## 5 Afghanistan Asia 1972 36.1 13079460 740.
## 6 Afghanistan Asia 1977 38.4 14880372 786.
summary(gapminder)
## country continent year lifeExp
## Afghanistan: 12 Africa :624 Min. :1952 Min. :23.60
## Albania : 12 Americas:300 1st Qu.:1966 1st Qu.:48.20
## Algeria : 12 Asia :396 Median :1980 Median :60.71
## Angola : 12 Europe :360 Mean :1980 Mean :59.47
## Argentina : 12 Oceania : 24 3rd Qu.:1993 3rd Qu.:70.85
## Australia : 12 Max. :2007 Max. :82.60
## (Other) :1632
## pop gdpPercap
## Min. :6.001e+04 Min. : 241.2
## 1st Qu.:2.794e+06 1st Qu.: 1202.1
## Median :7.024e+06 Median : 3531.8
## Mean :2.960e+07 Mean : 7215.3
## 3rd Qu.:1.959e+07 3rd Qu.: 9325.5
## Max. :1.319e+09 Max. :113523.1
##
#將gapminder的資料檔存入在一個名為gapminder的變數(物件中)
gapminder <- gapminder
#查看前幾筆資料
head(gapminder)
## # A tibble: 6 x 6
## country continent year lifeExp pop gdpPercap
## <fct> <fct> <int> <dbl> <int> <dbl>
## 1 Afghanistan Asia 1952 28.8 8425333 779.
## 2 Afghanistan Asia 1957 30.3 9240934 821.
## 3 Afghanistan Asia 1962 32.0 10267083 853.
## 4 Afghanistan Asia 1967 34.0 11537966 836.
## 5 Afghanistan Asia 1972 36.1 13079460 740.
## 6 Afghanistan Asia 1977 38.4 14880372 786.
#查看欄位名稱
colnames(gapminder)
## [1] "country" "continent" "year" "lifeExp" "pop" "gdpPercap"
#呼叫tidyverse套件
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
## ✓ ggplot2 3.3.3 ✓ purrr 0.3.4
## ✓ tibble 3.1.1 ✓ dplyr 1.0.5
## ✓ tidyr 1.1.3 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
#1、各洲的壽命分佈
gapminder %>%
filter(year == 2007) %>%
ggplot()+
geom_boxplot(aes(x=continent, y=lifeExp, fill=continent))
#2、查看大洲洲包含那些國家
gapminder %>%
filter(year == 2007) %>%
filter(continent == "Oceania")
## # A tibble: 2 x 6
## country continent year lifeExp pop gdpPercap
## <fct> <fct> <int> <dbl> <int> <dbl>
## 1 Australia Oceania 2007 81.2 20434176 34435.
## 2 New Zealand Oceania 2007 80.2 4115771 25185.
#3、1952年最長壽的前10個國家
gapminder %>%
filter(year==1952) %>%
arrange(desc(lifeExp)) %>%
slice(1:10) %>%
ggplot(aes(x=reorder(country,lifeExp), y=lifeExp))+
geom_col()+
coord_flip()
#4、查看2007年各洲的壽命與人均GDP的關係
gapminder %>%
filter(year == 2007) %>%
group_by(continent, year) %>%
summarize(medianLifeExp = median(lifeExp), medianGdpPercap = median(gdpPercap), sumpop=sum(pop)) %>%
ggplot()+
geom_text(aes(x=medianGdpPercap, y=medianLifeExp, label=continent, size=sumpop))
## `summarise()` has grouped output by 'continent'. You can override using the `.groups` argument.
#5、探索台灣與大陸的人均 GDP 與年份之變化趨勢
gapminder %>%
filter(country %in% c("China", "Taiwan")) %>%
ggplot(aes(x = year,
y = gdpPercap,
group = country,
color= country)) +
geom_line()
#6、查看2007年各國的發展情形
gapminder_2007 <- gapminder %>%
filter(year == 2007)
g1 <- ggplot(gapminder_2007, aes(x = pop, y = lifeExp, color = continent, size = gdpPercap, shape = continent)) +
geom_point() +
scale_x_log10() +
theme_minimal()
g2 <- ggplot(gapminder_2007, aes(x = pop, y = lifeExp, color = continent, size = gdpPercap)) +
geom_point() +
scale_x_log10() +
theme_classic()
# 繪畫多個圖形於一個畫布上
library(gridExtra)
##
## Attaching package: 'gridExtra'
## The following object is masked from 'package:dplyr':
##
## combine
grid.arrange(g1, g2, nrow = 1, ncol = 2)
#常用的幾種風格，包括：theme_bw(), theme_classic(), theme_dark(), theme_minimal(), theme_grey(), theme_linedraw()。
#7、1952到2007各洲國家的變化
gapminder %>%
filter(year %in% c(1952, 2007)) %>%
ggplot(aes(x = gdpPercap, y = lifeExp, color = continent, size=pop)) +
geom_point() +
facet_grid(continent ~ year)
filter(gapminder, year %in% c(1952, 2007)) %>%
ggplot(aes(gdpPercap, lifeExp, col = continent)) +
geom_point() +
facet_grid(continent ~ year)
#練習1、查看各洲的人均gdp分佈。
gapminder %>%
filter(year == 2007) %>%
ggplot()+
geom_boxplot(aes(x=gdpPercap, y=lifeExp, fill=continent))
#練習2、2007年最長壽的前10個國家
gapminder %>%
filter(year==2007) %>%
arrange(desc(lifeExp)) %>%
slice(1:10) %>%
ggplot(aes(x=reorder(country,lifeExp), y=lifeExp))+
geom_col()+
coord_flip()
#練習3、查看2007年各洲的人口數與人均GDP的關係
gapminder %>%
filter(year == 2007) %>%
group_by(continent, year) %>%
summarize(medianpop = median(pop), medianGdpPercap = median(gdpPercap), sumpop=sum(pop)) %>%
ggplot()+
geom_text(aes(x=medianGdpPercap, y=medianpop, label=continent, size=sumpop))
## `summarise()` has grouped output by 'continent'. You can override using the `.groups` argument.
#練習4、自行比較兩個國家的人均 GDP 與年份之變化趨勢
gapminder %>%
filter(country %in% c("Brazil", "China")) %>%
ggplot(aes(x = year,
y = gdpPercap,
group = country,
color= country)) +
geom_line()
