Chapter.3-2

rm(list=ls()) install.packages(“ggplot2”, dependencies = TRUE) install.packages(“cli”, type=“binary”) library(ggplot2)

scatter plot ——————————————————————

ggplot(iris) +
  aes(Sepal.Length, Sepal.Width) +
  geom_point(color = "red", size = 1)

same action

ggplot(iris, aes(Sepal.Length, Sepal.Width)) + geom_point(color = “red”, size = 1) ggplot(iris) + geom_point(aes(Sepal.Length, Sepal.Width), color = “red”, size = 1) ggplot + geom_point(data = iris, aes(Sepal.Length, Sepal.Width), color = “red”, size = 1)

p <- ggplot(iris) + aes(Sepal.Length, Sepal.Width) p + geom_point(color = “red”, size = 1) + geom_point(data=, aes()) # also possible this way

Designate a group variable —————————————————

ggplot(iris) +
  aes(Sepal.Length, Sepal.Width, color=Species) +
  geom_point(size = 1)

# x limitation
ggplot(iris) +
  aes(Sepal.Length, Sepal.Width, color=Species) +
  geom_point(position = "jitter", alpha = 0.4) + 
  xlim(5,7)

Bar plot ———————————————————————-

?economics
data(economics)
str(economics)

spec_tbl_df [574 × 6] (S3: spec_tbl_df/tbl_df/tbl/data.frame)
 $ date    : Date[1:574], format: "1967-07-01" "1967-08-01" "1967-09-01" ...
 $ pce     : num [1:574] 507 510 516 512 517 ...
 $ pop     : num [1:574] 198712 198911 199113 199311 199498 ...
 $ psavert : num [1:574] 12.6 12.6 11.9 12.9 12.8 11.8 11.7 12.3 11.7 12.3 ...
 $ uempmed : num [1:574] 4.5 4.7 4.6 4.9 4.7 4.8 5.1 4.5 4.1 4.6 ...
 $ unemploy: num [1:574] 2944 2945 2958 3143 3066 ...

ggplot(economics) +
  aes(date, unemploy) +
  geom_line() ->abs

ggplot(economics) +
  aes(date, unemploy/pop) +
  geom_line() ->rel

plot_grid(abs, rel, labels = c("abs", "rel"))

#specific year
ggplot(economics) +
  aes(date, unemploy/pop) +
  geom_line() + 
  xlim(as.Date("1967-07-01"), as.Date("1977-07-01"))

#ggplot step
ggplot(economics) +
  aes(date, unemploy/pop) +
  geom_step() + 
  xlim(as.Date("1967-07-01"), as.Date("1977-07-01"))

Practice the commend structure ————————————————

ggplot(economics) +
  aes(date, unemploy/pop) +
  geom_line() + 
  xlim(as.Date("1967-07-01"), as.Date("1977-07-01"))

# when filter situation put more option ; apply aes more
ggplot(economics) +
  aes(date, unemploy/pop) +
  geom_point(size=1) +
  xlim(as.Date("1967-07-01"), as.Date("1977-07-01")) -> def

ggplot(economics, aes(date, unemploy/pop)) +
  geom_point(size=1) +
  geom_line() +
  xlim(as.Date("1967-07-01"), as.Date("1977-07-01")) -> apl
  
plot_grid(def, apl, labels = c("def", "apl"))  

Warning: Removed 453 rows containing missing values (geom_point).Warning: Removed 453 rows containing missing values (geom_point).Warning: Removed 453 row(s) containing missing values (geom_path).

# when aes() and geom_object are designated seperatly  
ggplot(iris) +
  geom_point(aes(Sepal.Length, Sepal.Width), color = "red") +
  geom_point(aes(Sepal.Length, Petal.Length), color = "blue")  

# more grom_object  
ggplot(mpg) + aes(hwy) +geom_bar() -> bar
ggplot(mpg) + aes(hwy) +geom_histogram() -> hist
p <- ggplot(mpg) + aes(hwy) 
p + geom_dotplot() -> dot
p + geom_density() -> den
p + geom_freqpoly() -> fre
plot_grid(bar, hist, dot, den, fre, labels = c("AUTO")) 

`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Bin width defaults to 1/30 of the range of the data. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

# depends on the class
ggplot(mpg) + aes(hwy, fill = class) -> p
p + geom_bar() -> bar
p + geom_histogram() -> hist
p + geom_dotplot() -> dot
p + geom_density() -> den
# p + geom_freqpoly() -> fre ; has to use to color
ggplot(mpg) + aes(hwy, color = class) + geom_freqpoly() -> fre
plot_grid(bar, hist, dot, den, fre, labels = c("AUTO")) 

`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Bin width defaults to 1/30 of the range of the data. Pick better value with `binwidth`.
`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

geom_histogram() ————————————————————–

data(mtcars)
head(mtcars)

?mtcars

ggplot(mtcars) + 
  aes(mpg) +
  geom_histogram(bineidth=1) -> width

Warning: Ignoring unknown parameters: bineidth

ggplot(mtcars) + 
  aes(mpg) +
  geom_histogram(bins=10) -> bins

plot_grid(width, bins, labels = c("width", "bins")) 

`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(mpg) + aes(hwy) + geom_histogram() -> a
ggplot(mpg) + aes(hwy) + geom_histogram(bins = 10, color = "white", fill = "navy") -> b

plot_grid(a, b, labels = c("width", "bins")) 

`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

geom_bar() ——————————————————————–

ggplot(mpg) + aes(hwy, fill = class) + geom_bar() -> stack
ggplot(mpg) + aes(hwy, fill = class) + geom_bar(position="dodge") -> dodge
ggplot(mpg) + aes(hwy, fill = class) + geom_bar(position="fill") -> fill


plot_grid(stack, dodge, fill, labels = c("stack", "dodge", "fill")) 

geom_density() —————————————————————-

ggplot(mpg) + aes(hwy, fill = class) + geom_density() -> a 
ggplot(mpg) + aes(hwy, fill = class) + geom_density(alpha=0.5) -> b 

plot_grid(a, b, labels = "AUTO") 

geom_dotplot() —————————————————————-

ggplot(iris) + aes(Sepal.Length) + geom_dotplot() -> a
ggplot(iris) + aes(Sepal.Length) + geom_dotplot(binwidth = 0.1) -> c 
ggplot(iris) + aes(Sepal.Length) + geom_dotplot(binwidth = 0.1, stackdir = "centerwhole") -> d 
ggplot(iris) + aes(Species, Sepal.Length) + geom_dotplot(binaxis = "y") -> e
ggplot(iris) + aes(Species, Sepal.Length) + geom_dotplot(binaxis = "y", stackdir = "centerwhole") -> f
ggplot(iris) + aes(Species, Sepal.Length, fill = Species) + geom_dotplot(binaxis = "y", stackdir = "centerwhole") -> g

plot_grid(a, c, d, e, f, g, labels = "AUTO") 

Bin width defaults to 1/30 of the range of the data. Pick better value with `binwidth`.
Bin width defaults to 1/30 of the range of the data. Pick better value with `binwidth`.
Bin width defaults to 1/30 of the range of the data. Pick better value with `binwidth`.
Bin width defaults to 1/30 of the range of the data. Pick better value with `binwidth`.

geom_violin() —————————————————————-

ggplot(iris) + aes(Species, Sepal.Length) + geom_violin() -> a 
ggplot(iris) + aes(Species, Sepal.Length) +  geom_violin() + geom_dotplot(aes(fill = Species), binaxis = "y", stackdir = "centerwhole") -> b 

plot_grid(a, b, labels = "AUTO") 

Bin width defaults to 1/30 of the range of the data. Pick better value with `binwidth`.

geom_jitter() —————————————————————–

ggplot(iris) + 
  aes(Species, Sepal.Length, color = Species) + 
  geom_point() -> a 

ggplot(iris) + 
  aes(Species, Sepal.Length, color = Species) + 
  geom_jitter() -> b 

ggplot(iris) + 
  aes(Species, Sepal.Length, color = Species) + 
  geom_jitter(width = 0.25, alpha = 0.5) -> c

plot_grid(a, b, c, labels = "AUTO") 

geom_boxplot() —————————————————————–

ggplot(iris) + 
  aes(Species, Sepal.Length, color = Species) + 
  geom_boxplot() -> a 

ggplot(iris) + 
  aes(Species, Sepal.Length, fill = Species) + 
  geom_boxplot() -> a 

plot_grid(a, b, labels = "AUTO")