Data Visualization

Official book: http://www.cookbook-r.com/Graphs/
ggplot ekstenzije: https://exts.ggplot2.tidyverse.org/gallery/

If you’d like to learn more about the theoretical underpinnings of ggplot2 before you start, I’d recommend reading “The Layered Grammar of Graphics”, http://vita.had.co.nz/papers/layered-grammar.pdf.

All layered grammar of graphics

ggplot(data = <DATA>) +
<GEOM_FUNCTION>( mapping = aes(<MAPPINGS>), stat = <STAT>, position = <POSITION>) +
<COORDINATE_FUNCTION> +
<FACET_FUNCTION>

mpg dataset from ggplot2

head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa~
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa~
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa~
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa~
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa~
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa~

summary(mpg)

##  manufacturer          model               displ            year     
##  Length:234         Length:234         Min.   :1.600   Min.   :1999  
##  Class :character   Class :character   1st Qu.:2.400   1st Qu.:1999  
##  Mode  :character   Mode  :character   Median :3.300   Median :2004  
##                                        Mean   :3.472   Mean   :2004  
##                                        3rd Qu.:4.600   3rd Qu.:2008  
##                                        Max.   :7.000   Max.   :2008  
##       cyl           trans               drv                 cty       
##  Min.   :4.000   Length:234         Length:234         Min.   : 9.00  
##  1st Qu.:4.000   Class :character   Class :character   1st Qu.:14.00  
##  Median :6.000   Mode  :character   Mode  :character   Median :17.00  
##  Mean   :5.889                                         Mean   :16.86  
##  3rd Qu.:8.000                                         3rd Qu.:19.00  
##  Max.   :8.000                                         Max.   :35.00  
##       hwy             fl               class          
##  Min.   :12.00   Length:234         Length:234        
##  1st Qu.:18.00   Class :character   Class :character  
##  Median :24.00   Mode  :character   Mode  :character  
##  Mean   :23.44                                        
##  3rd Qu.:27.00                                        
##  Max.   :44.00

Including Plots

“The greatest value of a picture is when it forces us to notice what we never expected to see.” — John Tukey

ggplot(data = ) + (mapping = aes())

Osnovni grafik i prikaz po klasama:

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

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

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

## Warning: Using size for a discrete variable is not advised.

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

## Warning: Using alpha for a discrete variable is not advised.

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

## Warning: The shape palette can deal with a maximum of 6 discrete values because
## more than 6 becomes difficult to discriminate; you have 7. Consider
## specifying shapes manually if you must have them.

## Warning: Removed 62 rows containing missing values (geom_point).

knitr::include_graphics("shapes.png")

Oblici za tacke

mpg$class = factor(mpg$class)
ggplot(data=mpg) + geom_point(mapping = aes(x=displ, y=hwy, shape=class)) + scale_shape_manual(values=1:nlevels(mpg$class))

Bojenje:

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

Facets

ggplot(data = mpg) + 
  geom_point(mapping = aes(x = displ, y = hwy)) + 
  facet_wrap(~ class, nrow = 2)

Kombinacija dve promenljive:

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

Geometric objects

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

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

# Umesto linetype mogli smo da koristimo 
# 1. group = drv
# 2. color = drv

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

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

multiple geoms in the same plot

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'

# Kraći zapis:

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

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

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'

# Filtriranje podataka:

ggplot(data = mpg, mapping = aes(x = displ, y = hwy)) + 
  geom_point(mapping = aes(color = class)) + 
  geom_smooth(data = filter(mpg, class == "subcompact"), se = FALSE)

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

Domaći

knitr::include_graphics("task1.png")

Statistical transformations; diamond dataset

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

# Ne radi bez group = 1
ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, y = ..prop.., group = 1))

Position adjustments

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, colour = cut))

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, fill = cut))

# stekovanje

ggplot(data = diamonds) + geom_bar(mapping = aes(x = cut, fill = clarity))

# position adjustment: position = "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.

ggplot(data = diamonds, mapping = aes(x = cut, fill = clarity)) + 
  geom_bar(alpha = 1/5, position = "identity")

ggplot(data = diamonds, mapping = aes(x = cut, colour = clarity)) + 
  geom_bar(fill = NA, position = "identity")

ggplot(data = diamonds) + 
  geom_bar(mapping = aes(x = cut, fill = clarity), position = "dodge")

# scatter plot again

# shows only 126 points of 234. This problem is known as overplotting.
ggplot(data = mpg) + geom_point(mapping = aes(x = displ, y = hwy))

ggplot(data = mpg) + geom_point(mapping = aes(x = displ, y = hwy), position = "jitter")

# Check geom_jitter()

Coordinate systems

ggplot(data = mpg, mapping = aes(x = class, y = hwy)) + geom_boxplot()

ggplot(data = mpg, mapping = aes(x = class, y = hwy)) + geom_boxplot() + coord_flip()