#LOAD LIBRARIES
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)
#You can colour a bar chart using either the colour aesthetic, or, more usefully, fill:
#COLOUR
ggplot(data = diamonds) +
geom_bar(mapping = aes(x = cut, colour = cut))
#FILL
ggplot(data = diamonds) +
geom_bar(mapping = aes(x = cut, fill = cut))
#Note what happens if you map the fill aesthetic to another variable, like clarity: the bars are automatically stacked. Each colored rectangle represents a combination of cut and clarity.
ggplot(data = diamonds) +
geom_bar(mapping = aes(x = cut, fill = clarity))
#The stacking is performed automatically by the position adjustment specified by the position argument. If you don’t want a stacked bar chart, you can use one of three other options: "identity", "dodge" or "fill".
#position = "identity" will place each object exactly where it falls in the context of the graph. This is not very useful for bars, because it overlaps them. To see that overlapping we either need to make the bars slightly transparent by setting alpha to a small value, or completely transparent by setting fill = NA.
#semi transparent
ggplot(data = diamonds, mapping = aes(x = cut, fill = clarity)) +
geom_bar(alpha = 1/5, position = "identity")
#completely transparent
ggplot(data = diamonds, mapping = aes(x = cut, colour = clarity)) +
geom_bar(fill = NA, position = "identity")
#The identity position adjustment is more useful for 2d geoms, like points, where it is the default.
#position = fill
#position = "fill" works like stacking, but makes each set of stacked bars the same height. This makes it easier to compare proportions across groups.
ggplot(data = diamonds) +
geom_bar(mapping = aes(x = cut, fill = clarity), position = "fill")
#position = dodge
#position = "dodge" places overlapping objects directly beside one another. This makes it easier to compare individual values.
ggplot(data = diamonds) +
geom_bar(mapping = aes(x = cut, fill = clarity), position = "dodge")
#OVERPLOTTING
ggplot(data = mpg) +
geom_point(mapping = aes(x = displ, y = hwy))
#Did you notice that the plot displays only 126 points, even though there are 234 observations in the dataset?
#The values of hwy and displ are rounded so the points appear on a grid and many points overlap each other.
#This problem is known as overplotting.
#This arrangement makes it hard to see where the mass of the data is. #Are the data points spread equally throughout the graph, or is there one special combination of hwy and displ that contains 109 values?
#JITTER : SOLUTION TO OVERPLOTTING
#You can avoid this gridding by setting the position adjustment to “jitter”. position = "jitter" adds a small amount of random noise to each point.
#This spreads the points out because no two points are likely to receive the same amount of random noise.
ggplot(data = mpg) +
geom_point(mapping = aes(x = displ, y = hwy), position = "jitter")
#Adding randomness seems like a strange way to improve your plot, but while it makes your graph less accurate at small scales, it makes your graph more revealing at large scales.
#Because this is such a useful operation, ggplot2 comes with a shorthand for geom_point(position = "jitter"): geom_jitter()
#To learn more about a position adjustment, look up the help page associated with each adjustment: ?position_dodge, ?position_fill, ?position_identity, ?position_jitter, and ?position_stack.
#EXERCISE
#What is the problem with this plot? How could you improve it?
ggplot(data = mpg, mapping = aes(x = cty, y = hwy)) +
geom_point()
#Many of the data points overlap. We can jitter the points by adding some slight random noise, which will improve the overall visualization.
ggplot(data = mpg, mapping = aes(x = cty, y = hwy)) +
geom_jitter()
#What parameters to geom_jitter() control the amount of jittering?
#width and height.
#Compare and contrast geom_jitter() with geom_count().
ggplot(data = mpg, mapping = aes(x = cty, y = hwy)) +
geom_jitter()
ggplot(data = mpg, mapping = aes(x = cty, y = hwy)) +
geom_count()
#Rather than adding random noise, geom_count() counts the number of observations at each location, then maps the count to point area. It makes larger points the more observations are located at that area, so the number of visible points is equal to geom_point().
#What’s the default position adjustment for geom_boxplot()? Create a visualisation of the mpg dataset that demonstrates it.
#The default position adjustment is position_dodge().
ggplot(data = mpg, mapping = aes(x = class, y = hwy, color = drv)) +
geom_boxplot(position = "dodge")
