# ggplot2 notes
knitr::opts_chunk$set(echo = TRUE, warning=FALSE, message=FALSE)Packages
library(ggplot2)
library(magrittr)
library(dplyr)
library(tidyr)
library(titanic)
library(faraway)
library(GGally)
library(gridExtra)
library(ggthemes)
library(viridis)
library(dlnm)
library(RColorBrewer)
library(forcats)data("titanic_train", package = "titanic")
titanic <- titanic_train
data("worldcup")Generic code
object <- ggplot(dataframe, aes(x = column_1, y = column_2))
or, if you don’t need to save the object ggplot(dataframe, aes(x = column_1, y = column_2))
Basic histogram
ggplot(data = titanic, aes(x = Fare)) +
geom_histogram()
or
ggplot(data = titanic) +
geom_histogram(aes(x = Fare)) or
ggplot() +
geom_histogram(data = titanic, aes(x = Fare)) or
titanic %>%
ggplot() +
geom_histogram(aes(x = Fare)) or
titanic %>%
ggplot(aes(x = Fare)) +
geom_histogram()
change # of bins
ggplot(titanic, aes(x = Fare)) +
geom_histogram(bins = 15)
basic scatterplot
ggplot(worldcup, aes(x = Time, y = Passes)) +
geom_point()
size and color aesthetics
ggplot(worldcup, aes(x = Time, y = Passes,
color = Position, size = Shots)) +
geom_point()
Aesthetic args
Code Description x Position on x-axis y Position on y-axis shape Shape color Color of border of elements fill Color of inside of elements size Size alpha Transparency (1: opaque; 0: transparent) linetype Type of line (e.g., solid, dashed)
Geoms
Function Common aesthetics Common arguments geom_point() x, y
geom_line() x, y arrow, na.rm geom_segment() x, y, xend, yend arrow, na.rm geom_path() x, y na.rm geom_polygon() x, y
geom_histogram() x bins, binwidth geom_abline() intercept, slope
geom_hline() yintercept
geom_vline() xintercept
geom_smooth() x, y method, se, span geom_text() x, y, label parse, nudge_x, nudge_y
Multiple geoms
noteworthy_players <- worldcup %>% filter(Shots == max(Shots) |
Passes == max(Passes)) %>%
mutate(point_label = paste(Team, Position, sep = ", "))
ggplot(worldcup, aes(x = Passes, y = Shots)) +
geom_point() +
geom_text(data = noteworthy_players, aes(label = point_label),
vjust = "inward", hjust = "inward") 
Verticle lines every 90min
ggplot(worldcup, aes(x = Time)) +
geom_histogram(binwidth = 10) +
geom_vline(xintercept = 90 * 0:6,
color = "blue", alpha = 0.5)
Constant aesthetics
ggplot(worldcup, aes(x = Time, y = Passes)) +
geom_point(color = "darkgreen")
Other useful plot additions
Element Description ggtitle Plot title xlab, ylab x- and y-axis labels xlim, ylim Limits of x- and y-axis
eXAMPLE Plots
data(nepali)
nepali <- nepali %>%
select(id, sex, wt, ht, age) %>%
mutate(id = factor(id),
sex = factor(sex, levels = c(1, 2),
labels = c("Male", "Female"))) %>%
distinct(id, .keep_all = TRUE)Histograms
ggplot(nepali, aes(x = ht)) +
geom_histogram()
ggplot(nepali, aes(x = ht)) +
geom_histogram(fill = "lightblue", color = "black") +
ggtitle("Height of children") +
xlab("Height (cm)") + xlim(c(0, 120))
Scatterplots
ggplot(nepali, aes(x = ht, y = wt)) +
geom_point()
ggplot(nepali, aes(x = ht, y = wt)) +
geom_point(color = "blue", size = 0.5) +
ggtitle("Weight versus Height") +
xlab("Height (cm)") + ylab("Weight (kg)")
ggplot(nepali, aes(x = ht, y = wt, color = sex)) +
geom_point(size = 0.5) +
ggtitle("Weight versus Height") +
xlab("Height (cm)") + ylab("Weight (kg)")
Boxplots
ggplot(nepali, aes(x = 1, y = ht)) +
geom_boxplot() +
xlab("")+ ylab("Height (cm)")
ggplot(nepali, aes(x = sex, y = ht)) +
geom_boxplot() +
xlab("Sex")+ ylab("Height (cm)") 
Common Extensions
More here: Customizing ggplot2 Plots
data(nepali)
data(worldcup)
data(chicagoNMMAPS)
chic <- chicagoNMMAPS
chic_july <- chic %>%
filter(month == 7 & year == 1995)ggplot(worldcup, aes(x = Time, y = Shots)) +
geom_point() +
theme_tufte()
chicago_plot <- ggplot(chic_july, aes(x = date, y = death)) +
xlab("Day in July 1995") +
ylab("All-cause deaths") +
ylim(0, 450)
chicago_plot +
geom_area(fill = "black") +
theme_excel() 
chicago_plot +
geom_line() +
theme_tufte() 
Clean lables
wc_example_data <- worldcup %>%
dplyr::rename(Pos = Position) %>%
mutate(Pos = fct_recode(Pos,
"DC" = "Defender",
"FW" = "Forward",
"GK" = "Goalkeeper",
"MF" = "Midfielder"))
wc_example_data %>%
mutate(Pos = fct_recode(Pos,
"Defender" = "DC",
"Forward" = "FW",
"Goalkeeper" = "GK",
"Midfielder" = "MF")) %>%
ggplot(aes(x = Pos)) +
geom_bar(fill = "lightgray") +
xlab("") +
ylab("Number of players") +
coord_flip() +
theme_tufte()
Smoothed lowess curve
ggplot(filter(worldcup, Position == "Forward"), aes(x = Passes, y = Shots)) +
geom_point(size = 1.5) +
theme_few() +
geom_smooth()
Highlight a couple players
noteworthy_players <- worldcup %>%
filter(Shots == max(Shots) | Passes == max(Passes)) %>%
mutate(point_label = paste0(Team, Position, sep = ", "))
ggplot(worldcup, aes(x = Passes, y = Shots)) +
geom_point(alpha = 0.5) +
geom_text(data = noteworthy_players, aes(label = point_label),
vjust = "inward", hjust = "inward", color = "blue") +
theme_few()
Small multiples
worldcup %>%
ggplot(aes(x = Time, y = Shots, color = Position)) +
geom_point() 
Facets
worldcup %>%
ggplot(aes(x = Time, y = Shots)) +
geom_point() +
facet_grid(. ~ Position) 
Two team facet relationships
worldcup %>%
filter(Team %in% c("Spain", "Netherlands")) %>%
ggplot(aes(x = Time, y = Shots)) +
geom_point() +
facet_grid(Team ~ Position) 
Facet Wrap
worldcup %>%
ggplot(aes(x = Time, y = Shots)) +
geom_point(alpha = 0.25) +
facet_wrap(~ Team, ncol = 6) 
Reorder factors
nepali <- nepali %>%
mutate(sex = factor(sex, levels = c(1, 2),
labels = c("Male", "Female")))
ggplot(nepali, aes(ht, wt)) +
geom_point() +
facet_grid(. ~ sex)
nepali <- nepali %>%
mutate(sex = factor(sex, levels = c("Female", "Male")))
ggplot(nepali, aes(ht, wt)) +
geom_point() +
facet_grid(. ~ sex)
Meaningful ordering
worldcup %>%
group_by(Team) %>%
summarize(mean_time = mean(Time)) %>%
arrange(mean_time) %>% # re-order and re-set
mutate(Team = factor(Team, levels = Team)) %>% # factor levels before plotting
ggplot(aes(x = mean_time, y = Team)) +
geom_point() +
theme_few() +
xlab("Mean time per player (minutes)") + ylab("") 
worldcup %>%
select(Position, Time, Shots) %>%
group_by(Position) %>%
mutate(ave_shots = mean(Shots),
most_shots = Shots == max(Shots)) %>%
ungroup() %>%
arrange(ave_shots) %>%
mutate(Position = factor(Position, levels = unique(Position))) %>%
ggplot(aes(x = Time, y = Shots, color = most_shots)) +
geom_point(alpha = 0.5) +
scale_color_manual(values = c("TRUE" = "red", "FALSE" = "black"),
guide = FALSE) +
facet_grid(. ~ Position) +
theme_few()
worldcup %>%
dplyr::select(Team, Time) %>%
dplyr::group_by(Team) %>%
dplyr::mutate(ave_time = mean(Time),
min_time = min(Time),
max_time = max(Time)) %>%
dplyr::arrange(ave_time) %>%
dplyr::ungroup() %>%
dplyr::mutate(Team = factor(Team, levels = unique(Team))) %>%
ggplot(aes(x = Time, y = Team)) +
geom_segment(aes(x = min_time, xend = max_time, yend = Team),
alpha = 0.5, color = "gray") +
geom_point(alpha = 0.5) +
geom_point(aes(x = ave_time), size = 2, color = "red", alpha = 0.5) +
theme_minimal() +
ylab("")
Scales and Color
ggplot(worldcup, aes(x = Time, y = Passes, color = Position, size = Shots)) +
geom_point(alpha = 0.5)
Continuous Axis
ggplot(worldcup, aes(x = Time, y = Passes, color = Position, size = Shots)) +
geom_point(alpha = 0.5) +
scale_x_continuous(name = "Time played (minutes)",
breaks = 90 * c(2, 4, 6),
minor_breaks = 90 * c(1, 3, 5))
Continuous Scale
ggplot(worldcup, aes(x = Time, y = Passes, color = Position, size = Shots)) +
geom_point(alpha = 0.5) +
scale_x_continuous(name = "Time played (minutes)",
breaks = 90 * c(2, 4, 6),
minor_breaks = 90 * c(1, 3, 5)) +
scale_size_continuous(name = "Shots on goal",
breaks = c(0, 10, 20))
log scale on y-axis
ggplot(chic_july, aes(x = date, y = death)) +
geom_line() +
scale_y_log10(breaks = c(1:4 * 100))
Color palates: http://colorbrewer2.org/
display.brewer.pal(name = "Set1", n = 8)
display.brewer.pal(name = "PRGn", n = 8)
display.brewer.pal(name = "PuBuGn", n = 8)
wc_example <- ggplot(worldcup, aes(x = Time, y = Passes,
color = Position, size = Shots)) +
geom_point(alpha = 0.5)
a <- wc_example +
scale_color_brewer(palette = "Set1") +
ggtitle("Set1")
b <- wc_example +
scale_color_brewer(palette = "Dark2") +
ggtitle("Dark2")
c <- wc_example +
scale_color_brewer(palette = "Pastel2") +
ggtitle("Pastel2") +
theme_dark()
d <- wc_example +
scale_color_brewer(palette = "Accent") +
ggtitle("Accent")
grid.arrange(a, b, c, d, ncol = 2)
worldcup_ex <- worldcup %>%
ggplot(aes(x = Time, y = Shots, color = Passes)) +
geom_point(size = 0.9)
magma_plot <- worldcup_ex +
scale_color_viridis(option = "A") +
ggtitle("magma")
inferno_plot <- worldcup_ex +
scale_color_viridis(option = "B") +
ggtitle("inferno")
plasma_plot <- worldcup_ex +
scale_color_viridis(option = "C") +
ggtitle("plasma")
viridis_plot <- worldcup_ex +
scale_color_viridis(option = "D") +
ggtitle("viridis")
grid.arrange(magma_plot, inferno_plot, plasma_plot, viridis_plot, ncol = 2)