• The J-PAL MIT Micromasters - 102x

• Creative Commons Attribution-NonCommercial-NoDerivs 3.0 License

• Heavily borrowed from here: R for Data Science

• The complete ggplot2 tutorial

• Data visualization by Kieran Healy

• The World Wide Web

What is the grammar of graphics?

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

• districts grouped by state
• two bars per district-state pair
• bar labels
• all-sample means
• sample size
• confidence intervals

• trends over time

• Built iteratively!

• We are using gapminder dataset from gapminder package
• For scatterplot we are plotting gdpPercap vs lifeExp
• Gives us the unique opportunity to manipulate various elements of the plot

require(ggplot2)
## Loading required package: ggplot2
library(gapminder)
gapminder_sub <- gapminder[gapminder$year == 2007, ]
head(gapminder_sub)
## # A tibble: 6 x 6
##   country     continent  year lifeExp      pop gdpPercap
##   <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
## 1 Afghanistan Asia       2007    43.8 31889923      975.
## 2 Albania     Europe     2007    76.4  3600523     5937.
## 3 Algeria     Africa     2007    72.3 33333216     6223.
## 4 Angola      Africa     2007    42.7 12420476     4797.
## 5 Argentina   Americas   2007    75.3 40301927    12779.
## 6 Australia   Oceania    2007    81.2 20434176    34435.

This should be straighforward

ggplot(gapminder_sub, mapping = aes(x = gdpPercap, y = lifeExp))

We can add points by geom_point()

ggplot(gapminder_sub, mapping = aes(x = gdpPercap, y = lifeExp)) + 
  geom_point() 

We smooth the plot with geom_smooth()

ggplot(gapminder_sub, mapping = aes(x = gdpPercap, y = lifeExp)) + 
  geom_smooth() 
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

geom_smooth() and geom_point() together

ggplot(gapminder_sub, mapping = aes(x = gdpPercap, y = lifeExp)) + 
  geom_point() + 
  geom_smooth() 
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

geom_smooth() with a linear fit

ggplot(gapminder_sub, mapping = aes(x = gdpPercap, y = lifeExp)) + 
  geom_point() + 
  geom_smooth(method = "lm") 

The function scale_x_log10() to scale axis to logs

ggplot(gapminder_sub, mapping = aes(x = gdpPercap, y = lifeExp)) + 
  geom_point() + 
  geom_smooth(method = "gam") + 
  scale_x_log10()

Using xlim() and ylim()

plot_example <- ggplot(gapminder_sub, 
                       mapping = aes(x = gdpPercap, y = lifeExp)) + 
                geom_point() 
plot_example

Let's clip their wings

plot_example + xlim(c(0, 20000)) + ylim(c(50, 70))
## Warning: Removed 102 rows containing missing values (geom_point).

The second method can be by zooming in coord_cartesian()

plot_example <- ggplot(gapminder_sub, 
                       mapping = aes(x = gdpPercap, y = lifeExp)) + 
                geom_point() 
plot_example

Let's zoom in:

plot_example + coord_cartesian(xlim = c(0, 20000) , ylim = c(50, 70))

One method can be to use the ggtitle(), xlab(), and ylab()

plot_example <- ggplot(gapminder_sub, 
                       mapping = aes(x = gdpPercap, y = lifeExp)) + 
                geom_point() +
                ggtitle("GDP per capita Vs Life expectancy", 
                        subtitle="From Gapminder dataset") + 
                xlab("GDP per capita") + 
                ylab("Life expectancy")

plot_example

The other method can be seeping the entire plot with labs()

plot_example + 
  labs(title = "GDP per capita Vs Life expectancy", 
  subtitle = "From Gapminder dataset", 
  y = "Life expectancy", x = "GDP per capita", 
  caption = "Demographics")

Hardcoding col and size arguments within the geom_point()

plot_example <- ggplot(gapminder_sub, 
                       mapping = aes(x = gdpPercap, y = lifeExp)) + 
     geom_point(col = "steelblue", size = 3) +
     labs(title = "GDP per capita Vs Life expectancy", 
          subtitle = "From Gapminder dataset", 
          y = "Life expectancy", x = "GDP per capita", 
          caption = "Demographics")

plot_example

Setting color based on categories by using aes() with col function

plot_example <- ggplot(gapminder_sub, 
                       mapping = aes(x = gdpPercap, y = lifeExp)) + 
     geom_point(aes(col = continent), size = 3) +
     labs(title = "GDP per capita Vs Life expectancy", 
          subtitle = "From Gapminder dataset", 
          y = "Life expectancy", x = "GDP per capita", 
          caption = "Demographics")

plot_example

You can change colors by scale_color_brewer(). RColorBrewer package.

plot_example + scale_colour_brewer(palette = "Set1")

library(RColorBrewer)
head(brewer.pal.info, 10)
##          maxcolors category colorblind
## BrBG            11      div       TRUE
## PiYG            11      div       TRUE
## PRGn            11      div       TRUE
## PuOr            11      div       TRUE
## RdBu            11      div       TRUE
## RdGy            11      div      FALSE
## RdYlBu          11      div       TRUE
## RdYlGn          11      div      FALSE
## Spectral        11      div      FALSE
## Accent           8     qual      FALSE

Change breaks by scale_x_continuous()

options(scipen=999)
plot_example + scale_x_continuous(breaks=seq(0, 30000, 10000))

Change labels by labels in scale_x_continuous()

options(scipen=999)
plot_example + 
  scale_x_continuous(breaks = seq(0, 30000, 10000), 
                     labels = letters[1:4])

sprintf() and custom functions

options(scipen = 999)
plot_example + scale_x_continuous(breaks=seq(0, 30000, 10000), 
                     labels = sprintf("%1.2f%%", 
                                      seq(0, 30000, 10000))) +
  scale_y_continuous(labels = function(x){paste0(x/1000, 'K')})

plot_example <- ggplot(gapminder_sub, 
                       mapping = aes(x = gdpPercap, 
                                     y = lifeExp)) + 
     geom_point(aes(col = continent, size = pop)) +
     labs(title = "GDP per capita Vs Life expectancy", 
          subtitle = "From Gapminder dataset", 
          y ="Life expectancy", 
          x ="GDP per capita", 
          caption ="Demographics")

plot_example

Adding text and labels around the points

library(ggrepel)

gapminder_highgdp <- gapminder_sub[gapminder_sub$gdpPercap > 30000, ]

plot_example + 
  geom_label_repel(aes(label = country), 
                   size = 2, data = gapminder_highgdp) + 
  labs(subtitle = "With ggrepel::geom_label_repel") + 
  theme(legend.position = "None")

plot_example + 
  facet_wrap( ~ continent, nrow=2) + 
  labs(title = "GDP per capita vs Life expectancy", 
       caption = "Source: Gapminder", 
       subtitle = "Ggplot2 - Faceting - Multiple plots in one figure")

plot_example + 
  theme_minimal()

Economist!

library(ggthemes)
plot_example + 
  theme_economist()

plot_example <- ggplot(subset(gapminder, 
                              country == "India"), 
                       mapping = aes(x = as.factor(year), 
                                     y = lifeExp)) + 
  geom_bar(stat = "identity", fill = "#0D82BB", width = 0.5) + 
  labs(title="Change in life expectancy in India", 
       y = "Life Expectancy (in years)", 
       x = "") +
  theme_bw() + 
  coord_flip()

plot_example

stock_amzn <- read_csv("http://sharpsightlabs.com/wp-content/uploads/2017/09/AMZN_stock.csv")
colnames(stock_amzn) <- colnames(stock_amzn) %>% str_to_lower()

ggplot(stock_amzn, aes(x = date, close)) +
  geom_line(color = 'cyan') +
  geom_area(fill = 'cyan', alpha = .1) +
  labs(x = 'Date'
       , y = 'Closing\nPrice'
       , title = "Amazon's stock price has increased dramatically\nover the last 20 years") +
  theme(text = element_text(family = 'Gill Sans', color = "#444444")
        ,panel.background = element_rect(fill = '#444B5A')
        ,panel.grid.minor = element_line(color = '#4d5566')
        ,panel.grid.major = element_line(color = '#586174')
        ,plot.title = element_text(size = 18)
        ,axis.title = element_text(size = 18, color = '#555555')
        ,axis.title.y = element_text(vjust = 1, angle = 0)
        ,axis.title.x = element_text(hjust = 0)
  )

ggsave("amazon.png")

devtools::install_github("UrbanInstitute/urbnmapr")
library(tidyverse)
library(urbnmapr)

household_data <- left_join(countydata, counties, by = "county_fips") 

plot_map <- household_data %>%
  ggplot(aes(long, lat, group = group, fill = medhhincome)) +
  geom_polygon(color = NA) +
  coord_map(projection = "albers", lat0 = 39, lat1 = 45) +
  labs(fill = "Median Household Income")

plot_map

install.packages(c("gganimate", "png", "gifski"))
library(gapminder)
library(ggplot2)
library(gganimate)

plot <- ggplot(gapminder, aes(gdpPercap, lifeExp, 
                              size = pop, 
                              colour = country)) +
  geom_point(alpha = 0.7) +
  scale_colour_manual(values = country_colors) +
  scale_size(range = c(2, 12)) +
  scale_x_log10() +
  facet_wrap(~continent) +
  theme(legend.position = 'none') +
  labs(title = 'Year: {frame_time}', 
       x = 'GDP per capita', 
       y = 'life expectancy') +
  transition_time(year) +
  ease_aes('linear')

animate(plot, 100, 10)

library(ggplot2)
plot_base <- ggplot(data_graph, aes(x=district, y=value)) +
  geom_bar(stat='identity', position = "dodge", 
           aes(fill = state, alpha = round)) +
    facet_grid(state ~ ., scales="free_y", 
               space = "free_y", switch = "y") +
    ggtitle(data_graph$indicator.name[1]) +
    scale_fill_manual(values = colours_hex) +
    scale_alpha_manual(values = c(1, 0.6)) +
    format_bars +
    format_facet

E.g. Define the parameters of the error bars:

plot_ci <- list(
    geom_errorbar(aes(ymin = lower.ci, ymax = upper.ci, 
                      group = round), width = .4, 
                  position = position_dodge(width = dodge_width), 
                  color = "#3f444c"))

Add them to the base plot:

plot_base + plot_ci

• plot.margin()
• plot.bckground()

• coord_flip()
• scale_x_reverse() and scale_y_reverse()

• Either labs()
• Or guides()
• Or scale_aesthetic_vartype()

• Use element_type() and extensions for everything else

library("ggsci")
library("ggplot2")
library("gridExtra")

data("diamonds")

p1 = ggplot(subset(diamonds, carat >= 2.2),
       aes(x = table, y = price, colour = cut)) +
  geom_point(alpha = 0.7) +
  geom_smooth(method = "loess", alpha = 0.05, size = 1, span = 1) +
  theme_bw()

p2 = ggplot(subset(diamonds, carat > 2.2 & depth > 55 & depth < 70),
       aes(x = depth, fill = cut)) +
  geom_histogram(colour = "black", binwidth = 1, position = "dodge") +
  theme_bw()

p1_d3 = p1 + scale_color_d3()
p2_d3 = p2 + scale_fill_d3()
grid.arrange(p1_d3, p2_d3, ncol = 2)