Data Visualisation R code

library(ggplot2)
library(tidyverse)
install.packages("ggplotly")
#mpg frame comes with ggplot

ggplot(data = mpg)
str(mpg)
dim(mpg)

ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy, colour = class))
#ggplot2 will only use six shapes at a time

ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy, alpha = class), colour = "blue")#alpha is for transparency
#Here, the color doesn't convey information about a variable, 
#but only changes the appearance of the plot
 #alpha is for transparency

ggplot(data = mpg) + 
  geom_violin(mapping = aes(x = displ, y = hwy, alpha = class))

ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy, alpha = class), colour = "blue")

ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = class, alpha = hwy,
                           shape = class, colour= displ < 5))+ 
  facet_wrap(~ class, nrow = 3)
            

#facets
#put the variable with more unique levels in the columns
?facet_wrap
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) + 
  facet_wrap(~ class, nrow = 4)

#to facet with two variables 
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) + 
  facet_grid(drv ~ cyl)

#to facet not in row or column dimensions
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) + 
  facet_grid(. ~ cyl)

#facetting on a continuous variable
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = cyl)) + 
  facet_grid(. ~ cty)


ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) +
  facet_grid(drv ~ .)

ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) +
  facet_grid(. ~ cyl)

##geometric objects
#Every geom function in ggplot2 takes a mapping argument. 
#However, not every aesthetic works with every geom

# left
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy))

# right
ggplot(data = mpg) + 
  geom_smooth(mapping = aes(x = displ, y = hwy))
?geom_smooth

#using different linetypes to represent data
#cant map a continuous variable to linetype
ggplot(data = mpg) + 
  geom_smooth(mapping = aes(x = cty, y = hwy, linetype = displ))

#geom smoothe uses one geomobject to represent multiple rows of data
#set the group aesthetic to a categorical variable to draw multiple objects
ggplot(data = mpg) +
  geom_smooth(mapping = aes(x = displ, y = hwy, group = drv))

ggplot(data = mpg) +
  geom_smooth(
    mapping = aes(x = displ, y = hwy, color = drv),
    show.legend = TRUE
  )

#To display multiple geoms in the same plot, add multiple geom functions
ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) +
  geom_smooth(mapping = aes(x = displ, y = hwy, group = drv))

#this introduces duplication into the code. 
#To avoid forgetting to update a  variable in two places, pass mappings to ggplot
#ggplot passes the mappings to each geom in the graph
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) + 
  geom_point() + 
  geom_smooth()+
  ggtitle(label  = ("NEW COVID CASES PER 1000 PEOPLE IN AFRICA"))

#geom function mappings are treated as local mappings for the layer. 
#ggplot extends or overwrites the global mappings for that layer only. 
#This helps to display different aesthetics in different layers.

ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) + 
  geom_point(mapping = aes(color = class)) + 
  geom_smooth()

#there can be different data in each layer
ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) + 
  geom_point(mapping = aes(color = class)) + 
  geom_smooth(data = filter(mpg, class == "subcompact"), se = TRUE)

# se Displays confidence interval around smooth

#statistical Transformations
ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut))


#You can generally use geoms and stats interchangeably
ggplot(data = diamonds) + 
  stat_count(mapping = aes(x = cut))

#Adding labels(ggplot::labs)
# The plot title appears at the top-left, with the subtitle
# display in smaller text underneath it
p + labs(title = "New plot title")
p + labs(title = "New plot title", subtitle = "A subtitle")

# The caption appears in the bottom-right, and is often used for
# sources, notes or copyright
p + labs(caption = "(based on data from ...)")

# The plot tag appears at the top-left, and is typically used
# for labelling a subplot with a letter.
p + labs(title = "title", tag = "A")

# If you want to remove a label, set it to NULL.
p +
  labs(title = "title") +
  labs(title = NULL)


#use to convert several columns in a dataset 
mutate_if(is.double,as.numeric)