Ch10_데이터 시각화해 봤니?

1. 데이터 정제하기
2. 데이터 시각화하기

1.데이터 정제하기

1. 데이터 불러오기
2. 데이터 요약
3. 데이터 추출
4. 결측치와 이상치 처리

 

1. 데이터 불러오기

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

data(iris)
head(iris)

10.3 히스토그램 geom_histogram()

ggplot(iris,aes(x=Petal.Length)) +
    geom_histogram()

#종별구분색
ggplot(iris,aes(x=Petal.Length, fill=Species)) +
   geom_histogram()

#범례감추기
ggplot(iris,aes(x=Petal.Length, fill=Species)) +
  geom_histogram(show.legend = FALSE) #범례감추기

#10.4 밀도도표 geom_density()

ggplot(iris,aes(x=Petal.Length)) +
   geom_density()

ggplot(iris,aes(x=Petal.Length, fill=Species)) +
   geom_density()

ggplot(iris,aes(x=Petal.Length, fill=Species)) +
   geom_density(show.legend = FALSE)

ggplot(iris,aes(x=Sepal.Length, fill=Species)) +
   geom_density(alpha=0.5) #중첩부분 투명값처리

10.5 상자도표 geom_boxplot()

ggplot(iris,aes(x=Species, y=Sepal.Length)) + geom_boxplot()

ggplot(iris,aes(x=Petal.Length, fill= Species)) + geom_boxplot()
ggplot(iris,aes(x=Petal.Width, fill= Species)) + geom_boxplot()
ggplot(iris,aes(x=Sepal.Length, fill= Species)) + geom_boxplot()
ggplot(iris,aes(x=Sepal.Width, fill= Species)) + geom_boxplot()

ggplot(iris,aes(x=Petal.Length, y=Petal.Width)) + geom_boxplot()

ggplot(iris,aes(x=Petal.Length, y=Petal.Width, fill=Species)) + geom_boxplot()

ggplot(iris,aes(x=Petal.Length, y=Petal.Width, fill=Species)) + geom_boxplot(show.legend = FALSE)

10.6 산점도geom_point()

ggplot(iris,aes(x=Petal.Length, y=Petal.Width)) + geom_point()
ggplot(iris,aes(x=Petal.Length,y=Petal.Width,color= Species)) +
    geom_point()

ggplot(iris,aes(x=Petal.Length,y=Petal.Width,color= Species)) +
  geom_point() +
  labs(x ="꽃잎 길이", y="꽃잎 너비")

ggplot(iris,aes(x=Petal.Length,y=Petal.Width,color= Species)) +
  geom_point(show.legend = FALSE)

10.7 바차트

install.packages("gapminder")
library(gapminder)

data("gapminder")
str(gapminder)

data <- as.data.frame(gapminder)

table(data$country)
table(data$continent)
table(data$year)

ggplot(gapminder,aes(continent)) + geom_bar()

#2007년 기준으로 데이터 추출

gapminder <- as.data.frame(gapminder)
head(gapminder)

gapminder_2007 <- gapminder[gapminder$year==2007,]
head(gapminder_2007)

또는

library(dplyr)

gapminder_2007 <- filter(gapminder, year==2007)

ggplot(gapminder_2007, aes(continent, fill=continent)) + geom_bar(show.legend = F)

dim(kor)
table(kor$year)
kor$year <- as.factor(kor$year)

ggplot(kor, aes(x=year,y=lifeExp))+geom_bar(stat="identity")
ggplot(kor, aes(x=year,y=lifeExp, fill=lifeExp))+geom_bar(stat="identity")

ggplot(kor, aes(x=year,y=gdpPercap, group=1)) + geom_line() + geom_point()

ggplot(kor, aes(x=year,y=gdpPercap, group=1)) +
  geom_line(linetype=2, color="blue") +
  geom_point(shape=1, size=3)