Welcome

Ch1 Introduction

The data science project workflow

Prerequisites

  • R
  • RStudio
  • r packages

Install the tidyverse package

Running R code

1+2
## [1] 3

Getting help

  • Google
  • Stackoverflow

Ch2 Introduction to Data Exploration

Ch3 Data Visualization

Set up

library(tidyverse)

data

mpg
## # A tibble: 234 × 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… f        18    29 p     comp…
##  2 audi         a4           1.8  1999     4 manu… f        21    29 p     comp…
##  3 audi         a4           2    2008     4 manu… f        20    31 p     comp…
##  4 audi         a4           2    2008     4 auto… f        21    30 p     comp…
##  5 audi         a4           2.8  1999     6 auto… f        16    26 p     comp…
##  6 audi         a4           2.8  1999     6 manu… f        18    26 p     comp…
##  7 audi         a4           3.1  2008     6 auto… f        18    27 p     comp…
##  8 audi         a4 quattro   1.8  1999     4 manu… 4        18    26 p     comp…
##  9 audi         a4 quattro   1.8  1999     4 auto… 4        16    25 p     comp…
## 10 audi         a4 quattro   2    2008     4 manu… 4        20    28 p     comp…
## # ℹ 224 more rows

aesthetics

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

by size

ggplot(data = mpg) +
    geom_point(mapping = aes(x = displ, y = hwy, size = class))
## Warning: Using size for a discrete variable is not advised.

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

Other

# left
ggplot(data = mpg) +
    geom_point(mapping = aes(x = displ, y = hwy, alpha = class))
## Warning: Using alpha for a discrete variable is not advised.

# right
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
## ℹ you have requested 7 values. Consider specifying shapes manually if you need
##   that many of them.
## Warning: Removed 62 rows containing missing values or values outside the scale range
## (`geom_point()`).

common problems

  • Sometimes you’ll run the code and nothing happens.
  • Putting the + in the wrong place.

How to get help

  • ? function name
  • Select the function name and press F1
  • Read the error message
  • Google the error message

facets

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

facet with 2 variables

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

geometric objects

different visual object to represent data

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

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

not every aesthetic works with every geom

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

two geoms in the same graph!

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

local vs. global mappings This makes it possible to display different aesthetics in different layers.

specify different data for each layer

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

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 = FALSE)

statistical transformation

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

demo = tribble(
    ~ cut,         ~freq,
    "Fair",       1610,
    "Good",       4906,
    "Very Good",  12082,
    "Premium",    13791,
    "Ideal",      21551)

ggplot(data = demo) +
    geom_bar(mapping = aes(x = cut, y = freq), stat = "Identity")

ggplot(data = diamonds) +
    geom_bar(mapping = aes(x = cut, y = stat(prop), group = 1))
## Warning: `stat(prop)` was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(prop)` instead.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

ggplot(data = diamonds) +
    stat_summary(mapping = aes(x = cut, y = depth), fun.min = min, fun.max = max, fun = median)

position adjustments

adjustments for bar charts

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

Others:

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

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

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

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 = "fill")

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

adjustments for scatterplots

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

coordinate systems

switch x and y

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

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

set the aspect ratio correctly for maps

Polar coordinates reveal an interesting connection between a bar chart and a Coxcomb chart.

ggplot(data = diamonds) +
    geom_bar(mapping = aes(x = cut, fill = cut), show.legend = FALSE, width = 1)+
    theme(aspect.ratio = 1) +
    labs(x = NULL, y = NULL)

ggplot(data = diamonds) +
    geom_bar(mapping = aes(x = cut, fill = cut), show.legend = FALSE, width = 1)+
    theme(aspect.ratio = 1) +
    labs(x = NULL, y = NULL) + coord_flip()

ggplot(data = diamonds) +
    geom_bar(mapping = aes(x = cut, fill = cut), show.legend = FALSE, width = 1)+
    theme(aspect.ratio = 1) +
    labs(x = NULL, y = NULL) + coord_polar()

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

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

the layered grammar of graphics

The grammar of graphics is based on the insight that you can uniquely describe any plot as a combination of:

  • a dataset,
  • a geom,
  • a set of mappings,
  • a stat,
  • a position adjustment,
  • a coordinate system, and
  • a faceting scheme.