Case 2

R Markdown

library(ggplot2)
library(gapminder)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(tidyverse)

## ── Attaching packages
## ───────────────────────────────────────
## tidyverse 1.3.2 ──

## ✔ tibble  3.1.8     ✔ purrr   0.3.4
## ✔ tidyr   1.2.0     ✔ stringr 1.4.1
## ✔ readr   2.1.2     ✔ forcats 0.5.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

Objective

Here I am cleaning the gapminder data set

gapminder_cleaned <- gapminder %>% 
filter(year == "2007") %>% 
mutate(
  pop2 = pop + 1,
  continent = case_when(
    continent == "Oceania" ~ "Asia",
    TRUE ~ as.character(continent)
  ) %>% as.factor %>% 
    fct_relevel("Asia", "Americas", "Europe", "Africa", "Oceania")
) 

## Warning: 1 unknown level in `f`: Oceania

Objective

I am going to build a plot in order to visualize the association between life expectancy and income in different continents around the world.

ggplot(data = gapminder_cleaned, aes(x = gdpPercap, y = lifeExp)) +
    annotate("text", x = 4000, y = 45, hjust = 0.5,
           size = 85, color = "#999999",
           label = "2007", alpha = .3,
           family = "Helvetica Neue") +
   annotate("text", x = 28200, y = 2, 
           label = "per person (GDP/capita, PPP$ inflation-adjusted)",
           size = 2.8, color = "#999999") +
  geom_point(aes(size = pop, color = continent)) + 
  geom_point(aes(size = pop2), color = "black", shape = 21) +
   scale_x_log10(breaks = c(250, 500, 1000, 2000,
                           4000, 8000, 16000, 32000, 64000, 128000)) +
  scale_y_continuous(breaks = seq(0, 90, by = 10)) +
  scale_color_manual(values = c("#F15772", "#7EEB03",
                                "#FBE700", "#54D5E9")) +
  scale_size_continuous(range = c(1, 20)) +
  labs(
    x = "Income",
    y = "Life expectancy"
  ) +
  theme_minimal() +
  theme(
    panel.grid.minor = element_blank(),
    panel.grid.major = element_line(size = 0.2, 
                                    color = "#e5e5e5"),
    axis.title.y = element_text(margin = margin(r = 15), 
                                size = 11,
                                family = "Helvetica Neue Light"),
    axis.title.x = element_text(margin = margin(t = 15), 
                                size = 11,
                                family = "Helvetica Neue Light"),
    axis.text = element_text(family = "Helvetica Neue Light"),
    axis.line = element_line(color = "#999999", 
                             size = 0.2)
  ) +
  coord_cartesian(ylim = c(4.1, 85))