DANL 310 Lecture 05

Byeong-Hak Choe

February 10, 2022

Make a Plot

Loading the R packages

library(tidyverse)

## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──

## ✓ ggplot2 3.3.5     ✓ purrr   0.3.4
## ✓ tibble  3.1.6     ✓ dplyr   1.0.8
## ✓ tidyr   1.1.4     ✓ stringr 1.4.0
## ✓ readr   2.1.2     ✓ forcats 0.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

library(skimr)   # a better summary of data frame
library(scales)  # scales for ggplot

## 
## Attaching package: 'scales'

## The following object is masked from 'package:purrr':
## 
##     discard

## The following object is masked from 'package:readr':
## 
##     col_factor

Setting the theme for ggplot

theme_set(theme_minimal()) # setting the minimal theme for ggplot

Use theme() if you want to tweak the display of an existing theme.
The following lists the ggplot themes:

theme	theme
theme_grey()	theme_gray()
theme_bw()	theme_linedraw()
theme_light()	theme_dark()
theme_minimal()	theme_classic()
theme_void()	theme_test()

gapminder data

The gapminder package include the gapminder data frame.

library(gapminder)
gapminder

## # A tibble: 1,704 × 6
##    country     continent  year lifeExp      pop gdpPercap
##    <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
##  1 Afghanistan Asia       1952    28.8  8425333      779.
##  2 Afghanistan Asia       1957    30.3  9240934      821.
##  3 Afghanistan Asia       1962    32.0 10267083      853.
##  4 Afghanistan Asia       1967    34.0 11537966      836.
##  5 Afghanistan Asia       1972    36.1 13079460      740.
##  6 Afghanistan Asia       1977    38.4 14880372      786.
##  7 Afghanistan Asia       1982    39.9 12881816      978.
##  8 Afghanistan Asia       1987    40.8 13867957      852.
##  9 Afghanistan Asia       1992    41.7 16317921      649.
## 10 Afghanistan Asia       1997    41.8 22227415      635.
## # … with 1,694 more rows

Descriptive statistics

skim(gapminder)

Mappings link data to things you see

p <- ggplot(data = gapminder)

p <- ggplot(data = gapminder,
            mapping = aes(x = gdpPercap,
                          y = lifeExp))
p

Mappings link data to things you see

p + geom_point()

Build your plots layer by layer

p + geom_smooth()

Build your plots layer by layer

p + geom_point() + geom_smooth()

Build your plots layer by layer

p + geom_point() + geom_smooth(method = "lm")

Build your plots layer by layer

p + geom_point() +
    geom_smooth(method = "gam") +
    scale_x_log10()

Build your plots layer by layer

p + geom_point() +
    geom_smooth(method = "gam") +
    scale_x_log10(labels = scales::dollar)

Mapping aesthetics vs setting them

p <-  ggplot(data = gapminder,
             mapping = aes(x = gdpPercap, y = lifeExp,
                           color = continent))
p

Mapping aesthetics vs setting them

p <- ggplot(data = gapminder,
            mapping = aes(x = gdpPercap, y = lifeExp,
                          color = "purple"))
p + geom_point() +
    geom_smooth(method = "loess") +
    scale_x_log10()

Mapping aesthetics vs setting them

p <- ggplot(data = gapminder,
            mapping = aes(x = gdpPercap,
                          y = lifeExp))
p + geom_point(color = "purple") +
    geom_smooth(method = "loess") +
    scale_x_log10()

Mapping aesthetics vs setting them

p + geom_point(alpha = 0.3) +
    geom_smooth(color = "orange", se = FALSE, size = 8, method = "lm") +
    scale_x_log10()

Mapping aesthetics vs setting them

p + geom_point(alpha = 0.3) +
    geom_smooth(method = "gam") +
    scale_x_log10(labels = scales::dollar) +
    labs(x = "GDP Per Capita", y = "Life Expectancy in Years",
         title = "Economic Growth and Life Expectancy",
         subtitle = "Data points are country-years",
         caption = "Source: Gapminder.")

Mapping aesthetics vs setting them

p <- ggplot(data = gapminder,
            mapping = aes(x = gdpPercap,
                          y = lifeExp,
                          color = continent))
p + geom_point() +
    geom_smooth(method = "loess") +
    scale_x_log10()

Mapping aesthetics vs setting them

p <- ggplot(data = gapminder,
            mapping = aes(x = gdpPercap,
                          y = lifeExp,
                          color = continent,
                          fill = continent))
p + geom_point() +
    geom_smooth(method = "loess") +
    scale_x_log10()

Mapping aesthetics vs setting them

Aesthetics can be mapped per geom

p <- ggplot(data = gapminder, 
            mapping = aes(x = gdpPercap, y = lifeExp))

p + geom_point(mapping = aes(color = continent)) +
    geom_smooth(method = "loess") +
    scale_x_log10()

Aesthetics can be mapped per geom

p + geom_point(mapping = aes(color = log(pop))) +
      scale_x_continuous(trans = scales::log_trans())  # natural log scale

Save your work

knitr::opts_chunk$set(fig.width=8, fig.height=5)

Save your work

p + geom_point()

Save your work

ggsave(filename = "my_figure.png")

Save your work

ggsave(filename = "my_figure.pdf")

Save your work

p_out <- p + geom_point() +
    geom_smooth(method = "loess") +
    scale_x_log10()
ggsave("my_figure.pdf", plot = p_out)

Save your work

library(here)
ggsave(here("figures", "lifexp_vs_gdp_gradient.pdf"), plot = p_out)

here() starts at the directory where the project is created.
Create the “figures” folder in the directory where the project is created.

Save your work

ggsave("lifexp_vs_gdp_gradient.pdf",
       plot = p_out, height = 8, width = 10, units = "in")

Show the right number

Grouped data and the “group” aesthetic

p <- ggplot(data = gapminder,
            mapping = aes(x = year,
                          y = gdpPercap))
p + geom_line()

Grouped data and the “group” aesthetic

p + geom_line(aes(group=country))

Facet to make small multiples

p + geom_line(aes(group = country)) + facet_wrap(~ continent)

Facet to make small multiples

p + geom_line(color="gray70", aes(group = country)) +
    geom_smooth(size = 1.1, method = "loess", se = FALSE) +
    scale_y_log10(labels=scales::dollar) +
    facet_wrap(~ continent, ncol = 5) +
    labs(x = "Year", y = "GDP per capita",
         title = "GDP per capita on Five Continents")

Facet to make small multiples

p + geom_line(color="gray70", aes(group = country)) +
    geom_smooth(size = 1.1, method = "loess", se = FALSE) +
    scale_y_log10(labels=scales::dollar) +
    facet_wrap(~ continent, ncol = 5) +
    labs(x = "Year", y = "GDP per capita",
         title = "GDP per capita on Five Continents") + 
    theme(axis.text.x = element_text(angle = 45),
          axis.title.x = element_text(margin = margin(t = 25)))