Steps with Tidyverse & ggplot2()
Visualizations in R with ggplot2()
Do It Yourself!
Every ggplot() Function
The Three Essentials
Build in Layers
Aesthetic Mappings, For Example
Adding (Smooth) Lines and Trends Part 1
Adding (Smooth) Lines and Trends Part 2
Adding (Smooth) Lines and Trends Part 3
Linear Regression Lines Part 1
Linear Regression Lines Part 2
Adding Lines and Trends: Smooth Line (LOESS) Part 1
Locally Estimated Scatterplot Smoothing
Adding Lines and Trends: Smooth Line (LOESS) Part 2
Adding Lines and Trends: Smooth Line (LOESS) Part 3
Comprehensive Line Types Guide, Output
Everything you need to know about lines
Customizing Line Appearance
# Available linetypes
df <- data.frame(
x = 1:10,
y = rep(1:6, length.out = 10)
)
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_point(alpha = 0.3) +
geom_smooth(
method = "lm",
linetype = "solid"
)
# Options for linetype:
# "solid" (or 1)
# "dashed" (or 2)
# "dotted" (or 3)
# "dotdash" (or 4)
# "longdash" (or 5)
# "twodash" (or 6)
# Example with multiple lines
ggplot(mpg, aes(x = displ, y = hwy,
color = drv)) +
geom_point() +
geom_smooth(method = "lm",
se = FALSE,
aes(linetype = drv))
Line Customization
# Control line appearance
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_point(alpha = 0.4) +
geom_smooth(
method = "lm",
se = TRUE,
color = "darkred", # Line color
fill = "pink", # CI fill color
linewidth = 1.5, # Line width
linetype = "dashed", # Line type
alpha = 0.3 # CI transparency
)
# Multiple smooths with different methods
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_point(alpha = 0.4) +
geom_smooth(
method = "lm",
se = FALSE,
color = "blue",
aes(fill = "Linear")
) +
geom_smooth(
method = "loess",
se = FALSE,
color = "red",
aes(fill = "LOESS")
)
Faceting: Multiple Plots
Split Your Plot by Groups 📊
Create separate panels for different categories
# Facet by one variable
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_point() +
geom_smooth(method = "lm", se = FALSE) +
facet_wrap(~ class)
# Facet by two variables (grid)
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_point() +
facet_grid(drv ~ cyl)
# Free scales (each panel has own scale)
ggplot(mpg, aes(x = displ, y = hwy)) +
geom_point() +
geom_smooth(method = "lm", se = FALSE) +
facet_wrap(~ class, scales = "free")
# Facet with different rows/columns
ggplot(mpg, aes(x = displ, y = hwy, color = drv)) +
geom_point() +
geom_smooth(method = "lm", se = FALSE) +
facet_wrap(~ class, ncol = 3) +
theme_minimal() +
labs(
title = "Fuel Efficiency by Vehicle Class",
x = "Engine Displacement (L)",
y = "Highway MPG",
color = "Drive Type"
)
Visualizing the Iris Dataset
Multiple visualization approaches
# Scatter Plot with Species
ggplot(iris,
aes(x = Petal.Length,
y = Petal.Width,
color = Species)) +
geom_point(size = 3, alpha = 0.7)
# Add smooth lines per species
ggplot(iris,
aes(x = Petal.Length,
y = Petal.Width,
color = Species)) +
geom_point(size = 2, alpha = 0.6) +
geom_smooth(method = "lm",
se = TRUE) +
theme_minimal() +
labs(
title = "Iris Petal Dimensions",
x = "Petal Length (cm)",
y = "Petal Width (cm)"
)
Multiple Dimensions
# Sepal vs Petal lengths
ggplot(iris,
aes(x = Sepal.Length,
y = Petal.Length,
color = Species,
shape = Species)) +
geom_point(size = 3, alpha = 0.7) +
geom_smooth(method = "lm",
se = FALSE,
linewidth = 1) +
theme_bw()
# All pairwise comparisons
library(GGally) # install.packages('GGally') if needed
iris %>%
select(everything()) %>%
ggpairs(aes(color = Species))
More Plot Types
Beyond Scatter Plots 📊
Common visualization types for different data
# Box plots - Distribution by group
ggplot(mpg, aes(x = class, y = hwy, fill = class)) +
geom_boxplot() +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
labs(title = "Highway MPG by Vehicle Class")
# Violin plots - Similar to boxplot but shows distribution shape
ggplot(mpg, aes(x = class, y = hwy, fill = class)) +
geom_violin() +
geom_jitter(width = 0.2, alpha = 0.3) +
theme_minimal()
# Histogram - Distribution of a single variable
ggplot(mpg, aes(x = hwy)) +
geom_histogram(bins = 30, fill = "steelblue", color = "black") +
theme_minimal() +
labs(title = "Distribution of Highway MPG")
# Density plot - Smooth version of histogram
ggplot(mpg, aes(x = hwy, fill = drv)) +
geom_density(alpha = 0.5) +
theme_minimal() +
labs(title = "Highway MPG Distribution by Drive Type")
# Bar chart - Counts or values
ggplot(mpg, aes(x = class, fill = drv)) +
geom_bar(position = "dodge") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
