#Load Pre - Requisite
library(tidyverse)
## Warning: package 'tidyverse' was built under R version 3.5.2
## -- Attaching packages --------------------------------------------------------------------------------------------------------- tidyverse 1.2.1 --
## v ggplot2 3.1.0 v purrr 0.2.5
## v tibble 2.0.1 v dplyr 0.7.8
## v tidyr 0.8.2 v stringr 1.3.1
## v readr 1.3.1 v forcats 0.3.0
## Warning: package 'ggplot2' was built under R version 3.5.2
## Warning: package 'tibble' was built under R version 3.5.2
## Warning: package 'tidyr' was built under R version 3.5.2
## Warning: package 'readr' was built under R version 3.5.2
## Warning: package 'purrr' was built under R version 3.5.2
## Warning: package 'dplyr' was built under R version 3.5.2
## Warning: package 'stringr' was built under R version 3.5.2
## Warning: package 'forcats' was built under R version 3.5.2
## -- Conflicts ------------------------------------------------------------------------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(ggplot2)
#A geom is the geometrical object that a plot uses to represent data. People often describe plots by the type of geom that the plot uses. For example, bar charts use bar geoms, line charts use line geoms, boxplots use boxplot geoms, and so on.
#To change the geom in your plot, change the geom function that you add to ggplot(). For instance, to make the plots above, you can use this code:
ggplot(data = mpg) +
geom_smooth(mapping = aes(x = displ, y = hwy))
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#NOTE :
#Every geom function in ggplot2 takes a mapping argument. However, not every aesthetic works with every geom.
#You could set the shape of a point, but you couldn’t set the “shape” of a line.
#On the other hand, you could set the linetype of a line. geom_smooth() will draw a different line, with a different linetype, for each unique value of the variable that you map to linetype
#LINETYPE :
ggplot(data = mpg) +
geom_smooth(mapping = aes(x = displ, y = hwy, linetype = drv))
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#Here geom_smooth() separates the cars into three lines based on their drv value, which describes a car’s drivetrain. One line describes all of the points with a 4 value, one line describes all of the points with an f value, and one line describes all of the points with an r value. Here, 4 stands for four-wheel drive, f for front-wheel drive, and r for rear-wheel drive.
#Many geoms, like geom_smooth(), use a single geometric object to display multiple rows of data. For these geoms, you can set the group aesthetic to a categorical variable to draw multiple objects.
#ggplot2 will draw a separate object for each unique value of the grouping variable
ggplot(data = mpg) +
geom_smooth(mapping = aes(x = displ, y = hwy, group = drv))
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#COLOURED LINES :
ggplot(data = mpg) +
geom_smooth(
mapping = aes(x = displ, y = hwy, color = drv),
show.legend = FALSE
)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#To display multiple geoms in the same plot, add multiple geom functions to ggplot():
ggplot(data = mpg) +
geom_point(mapping = aes(x = displ, y = hwy)) +
geom_smooth(mapping = aes(x = displ, y = hwy))
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#Avoid Redundancy :
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) +
geom_point() +
geom_smooth()
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#To display different aesthetics in different layers.
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) +
geom_point(mapping = aes(color = class)) +
geom_smooth()
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#You can use the same idea to specify different data for each layer. #Here, our smooth line displays just a subset of the mpg dataset, the subcompact cars.
#The local data argument in geom_smooth() overrides the global data argument in ggplot() for that layer only.
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) +
geom_point(mapping = aes(color = class)) +
geom_smooth(data = filter(mpg, class == "subcompact"), se = FALSE)
## Warning: package 'bindrcpp' was built under R version 3.5.2
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#EXERCISE
#What geom would you use to draw a line chart? A boxplot? A histogram? An area chart?
#Line chart - geom_line()
#Boxplot - geom_boxplot()
#Histogram - geom_histogram()
#Area chart - geom_area()
#Run this code in your head and predict what the output will look like. Then, run the code in R and check your predictions.
ggplot(data = mpg, mapping = aes(x = displ, y = hwy, color = drv)) +
geom_point() +
geom_smooth(se = FALSE)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#What does show.legend = FALSE do? What happens if you remove it?
#Why do you think I used it earlier in the chapter?
#It removes the legend. The aesthetics are still mapped and plotted, but the key is removed from the graph. I don’t know why used it earlier because he actually did not.
#What does the se argument to geom_smooth() do?
#It determines whether or not to draw a confidence interval around the smoothing line.
#Will these two graphs look different? Why/why not?
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) +
geom_point() +
geom_smooth()
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
ggplot() +
geom_point(data = mpg, mapping = aes(x = displ, y = hwy)) +
geom_smooth(data = mpg, mapping = aes(x = displ, y = hwy))
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#No because they use the same data and mapping settings. The only difference is that by storing it in the ggplot() function, it is automatically reused for each layer
#Generate Code
#a
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) +
geom_point() +
geom_smooth(se = FALSE)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#b
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) +
geom_smooth(aes(group = drv), se = FALSE) +
geom_point()
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#c
ggplot(data = mpg, mapping = aes(x = displ, y = hwy, color = drv)) +
geom_point() +
geom_smooth(se = FALSE)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#d
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) +
geom_point(aes(color = drv)) +
geom_smooth(se = FALSE)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#e
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) +
geom_point(aes(color = drv)) +
geom_smooth(aes(linetype = drv), se = FALSE)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
#f
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) +
geom_point(size = 4, colour = "white") +
geom_point(aes(colour = drv))
