Pie Charts

Pie charts show how a whole is divided into parts.

Each slice represents the proportion of a category relative to the total.

They are commonly used when:

there are few categories
proportions are easy to compare

However, pie charts can become difficult to interpret when there are many slices.

We will use the mpg dataset and count the number of vehicles in each class.

library(ggplot2)
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

data("mpg")

class_counts <- mpg %>%
  count(class)

ggplot(class_counts, aes(x = "", y = n, fill = class)) +
  geom_col(width = 1) +
  coord_polar("y") +
  theme_void() +
  labs(title = "Vehicle Class Distribution")

Explanation

geom_col() creates a stacked bar chart
coord_polar(“y”) converts the bar chart into a circular pie chart
theme_void() removes unnecessary axes and grid lines

Prop <- c(3,7,9,1,2)
pie(Prop , labels = c("Gr-A","Gr-B","Gr-C","Gr-D","Gr-E")) #add labels to slices

pie(Prop , labels = c("Gr-A","Gr-B","Gr-C","Gr-D","Gr-E") , density=10 , angle=c(20,90,30,10,0)) # Add dashed lines by using density, and control the angles.

Donut Charts

Donut charts are similar to pie charts but include a hole in the center. This can make labels easier to read and reduce visual clutter.

ggplot(class_counts, aes(x = 2, y = n, fill = class)) +
  geom_col(width = 1) +
  coord_polar("y") +
  xlim(0.5, 2.5) +
  theme_void() +
  labs(title = "Vehicle Class Distribution (Donut Chart)")

Explanation

The donut hole is created by manipulating the x-axis limits.

the bars are drawn away from the center
the middle space becomes empty

To get percentage labels positioned around the donut like in your example, you need to:

Calculate proportions
Compute label positions
Add labels with geom_text()

library(ggplot2)
library(dplyr)
library(scales)

df <- data.frame(
  category = c("A","B","C"),
  value = c(10,60,30)
)

# Compute percentages and label positions
df <- df %>%
  mutate(
    prop = value / sum(value), #calculate proportions
    ymax = cumsum(prop), #calculate slice boundaries to see where they begin and end
    ymin = lag(ymax, default = 0),
    label_pos = (ymax + ymin) / 2, #place text in the center of each slice arc
    label = percent(prop) 
  )

ggplot(df, aes(ymax = ymax, ymin = ymin, xmax = 4, xmin = 3, fill = category)) +
  geom_rect() +
  coord_polar(theta = "y") +
  
  # percentage labels
  geom_text(aes(x = 4.2, y = label_pos, label = label), size = 4) + #add percentage labels
  
  xlim(2, 4.5) +
  theme_void()

data <- data.frame(
  category=c("A", "B", "C"),
  count=c(10, 60, 30)
)
 
# Compute percentages
data$fraction <- data$count / sum(data$count)

# Compute the cumulative percentages (top of each rectangle)
data$ymax <- cumsum(data$fraction)

# Compute the bottom of each rectangle
data$ymin <- c(0, head(data$ymax, n=-1))

# Compute label position
data$labelPosition <- (data$ymax + data$ymin) / 2

# Compute a good label
data$label <- paste0(data$category, "\n value: ", data$count)

# Make the plot
ggplot(data, aes(ymax=ymax, ymin=ymin, xmax=4, xmin=3, fill=category)) +
  geom_rect() +
  geom_label( x=3.5, aes(y=labelPosition, label=label), size=6) +
  scale_fill_brewer(palette=4) +
  coord_polar(theta="y") +
  xlim(c(2, 4)) +
  theme_void() +
  theme(legend.position = "none")

Sunburst Plots

install.packages("sunburstR")

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.5'
## (as 'lib' is unspecified)

## Warning in install.packages("sunburstR"): installation of package 'sunburstR'
## had non-zero exit status

library(sunburstR)
library(dplyr)

sunburst_data <- data.frame(
  sequence = c(
    "Fruit-Apples",
    "Fruit-Bananas",
    "Fruit-Oranges",
    "Vegetable-Carrots",
    "Vegetable-Broccoli",
    "Vegetable-Peppers"
  ),
  value = c(30, 20, 25, 15, 18, 12)
)

sunburst(sunburst_data)

Think of this like a nested dout plot, that can show a category within a category. They are not ideal when:

students need precise comparisons
there are many small slices
labels become crowded

Treemap

library(treemap)
library(dplyr)

sales_data <- data.frame(
  category = c("Fruit", "Fruit", "Fruit", "Vegetable", "Vegetable", "Vegetable"),
  subcategory = c("Apples", "Bananas", "Oranges", "Carrots", "Broccoli", "Peppers"),
  value = c(30, 20, 25, 15, 18, 12)
)

treemap(
  sales_data,
  index = c("category", "subcategory"),
  vSize = "value",
  title = "Treemap of Category and Subcategory Counts"
)

They can become hard to read if:

labels are too long
there are too many tiny categories
viewers need exact comparisons

Circular Packing

Circular packing visualizes nested hierarchical structures.

Large circles represent categories, while smaller circles inside represent subcategories.

This is useful for:

hierarchical datasets
taxonomies
organizational structures

library(packcircles)
library(ggforce)

sizes <- c(50, 30, 20, 10, 5)

circle_data <- circleProgressiveLayout(sizes)

library(ggplot2)

ggplot(circle_data) +
  geom_circle(aes(x0 = x, y0 = y, r = radius),
              fill = "skyblue",
              color = "black") +
  coord_equal() +
  theme_void()

Explanation

each circle size represents a category
circles are packed efficiently to avoid overlap

library(ggraph)
library(igraph)

## 
## Attaching package: 'igraph'

## The following objects are masked from 'package:dplyr':
## 
##     as_data_frame, groups, union

## The following objects are masked from 'package:stats':
## 
##     decompose, spectrum

## The following object is masked from 'package:base':
## 
##     union

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ lubridate 1.9.5     ✔ tibble    3.3.1
## ✔ purrr     1.2.1     ✔ tidyr     1.3.2
## ✔ readr     2.2.0

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ lubridate::%--%()       masks igraph::%--%()
## ✖ tibble::as_data_frame() masks igraph::as_data_frame(), dplyr::as_data_frame()
## ✖ readr::col_factor()     masks scales::col_factor()
## ✖ purrr::compose()        masks igraph::compose()
## ✖ tidyr::crossing()       masks igraph::crossing()
## ✖ purrr::discard()        masks scales::discard()
## ✖ dplyr::filter()         masks stats::filter()
## ✖ dplyr::lag()            masks stats::lag()
## ✖ purrr::simplify()       masks igraph::simplify()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(viridis)

## Loading required package: viridisLite
## 
## Attaching package: 'viridis'
## 
## The following object is masked from 'package:scales':
## 
##     viridis_pal

# We need a data frame giving a hierarchical structure. Let's consider the flare dataset:
edges <- flare$edges
vertices <- flare$vertices
mygraph <- graph_from_data_frame( edges, vertices=vertices )
 
# Control the size of each circle: (use the size column of the vertices data frame)
ggraph(mygraph, layout = 'circlepack', weight=size) + 
  geom_node_circle() +
  theme_void()

ggraph(mygraph, layout = 'circlepack', weight=size) + 
  geom_node_circle(aes(fill = depth)) + #add the fill designation
  theme_void() + 
  theme(legend.position="FALSE") +
   scale_fill_viridis() #choose a color pallette

ggraph(mygraph, layout = 'circlepack', weight=size ) + 
  geom_node_circle(aes(fill = depth)) +
  geom_node_text( aes(label=shortName, filter=leaf, fill=depth, size=size)) +
  theme_void() + 
  theme(legend.position="FALSE") + 
  scale_fill_viridis()

## Warning in geom_node_text(aes(label = shortName, filter = leaf, fill = depth, :
## Ignoring unknown aesthetics: fill

Dendrograms

Dendrograms visualize hierarchical clustering.

They show how observations group together based on similarity.

Common uses include:

gene expression analysis
species similarity
document clustering

# Load packages
library(ggraph)
library(igraph)
library(tidyverse)

# Step 1: Create the top level of the hierarchy
# One starting point called "origin" branches into 5 groups
level1 <- data.frame(
  from = "origin",
  to = paste0("group_", 1:5)
)

# Step 2: Create the second level of the hierarchy
# Each group branches into 5 subgroups
level2 <- data.frame(
  from = rep(level1$to, each = 5),
  to = paste0("subgroup_", 1:25)
)

# Step 3: Combine all connections into one edge list
edges <- bind_rows(level1, level2)

# Step 4: Turn the edge list into a graph object
graph <- graph_from_data_frame(edges)

# Step 5: Plot the hierarchy as a dendrogram
ggraph(graph, layout = "dendrogram", circular = FALSE) +
  geom_edge_diagonal() +
  geom_node_point() +
  theme_void()

# Adding Labels 
ggraph(graph, layout = 'dendrogram') + 
  geom_edge_diagonal() +
  geom_node_text(aes( label=name, filter=leaf) , angle=90 , hjust=1, nudge_y = -0.01) + #add a text label to each of your nodes
  ylim(-.4, NA)

ggraph(graph, layout = 'dendrogram') + 
  geom_edge_diagonal() +
  geom_node_text(aes( label=name, filter=leaf) , angle=90 , hjust=1, nudge_y = -0.04) +
  geom_node_point(aes(filter=leaf) , alpha=0.6) + #add points at the end of each line
  ylim(-.5, NA)

Interpretation

each branch represents a cluster
observations that join earlier are more similar

Circular Dendrograms

ggraph(graph, layout = "dendrogram", circular = TRUE) +
  geom_edge_diagonal() +
  geom_node_point() +
  theme_void()

ggraph(mygraph, layout = "dendrogram", circular = TRUE) +
  geom_edge_link() + #change from curved lines to straight linkages
  geom_node_point() + 
  theme_void()

#adding labels to circular plots is quite difficult.

Word Clouds

Word clouds visualize text frequency.

Words that appear more often are displayed larger.

They are commonly used in:

text analysis
social media analysis
document exploration

library(wordcloud2)

wordcloud2(data=demoFreq, size=1.6)

# Gives a proposed palette
wordcloud2(demoFreq, size=1.6, color='random-dark')

# or a vector of colors. vector must be same length than input data
wordcloud2(demoFreq, size=1.6, color=rep_len( c("green","blue"), nrow(demoFreq) ) )

# Change the background color
wordcloud2(demoFreq, size=1.6, color='random-light', backgroundColor="black")

Explanation

word size reflects frequency
color adds visual variation

You can custom the wordcloud shape using the shape argument. Available shapes are:

circle
cardioid
diamond
triangle-forward
triangle
pentagon
star

# Change the shape:
wordcloud2(demoFreq, size = 0.7, shape = 'star')

Homework

Task 1. Pie chart with ggplot

Use the mpg dataset to create a table counting the number of vehicles in each class. Then create a pie chart showing the distribution of vehicle classes.

Create a simple pie chart in base R using the following values: 3, 7, 9, 1, 2

Label the slices:Gr-A, Gr-B, Gr-C, Gr-D, Gr-E

Requirements:

use count(class) from dplyr
use geom_col()
convert the plot to a pie chart with coord_polar(“y”)
use theme_void()
add a title

library("ggplot2")
library(dplyr)

data("mpg")

class_counts <- mpg %>%
  count(class)

ggplot(class_counts,aes(x = "", y = n, fill = class)) +
  geom_col(width = 2) +
  coord_polar("y") +
  theme_void() +
  labs(title = "Vehicle Class Distribution")

values <- c(3,7,9,1,2)
labels <- c("SUV", "Compact","Midsize","Truck","Van")

pie(values, labels = labels, main = "simple pie chart")

Questions -Which vehicle class appears most common? The midsize car is the most common based on the pie chart. - Why can pie charts become difficult to interpret when there are many categories? Since there is no percentages, if they are close in size it can be hard to inerpret which is each.

Task 2: Create a simple pie chart in base R using the following values:

Create a donut chart using this small dataset:

data <- data.frame(
  category = c("A", "B", "C"),
  count = c(10, 60, 30)
)
ggplot(data, aes(x = 2, y = count, fill = category)) +
  geom_col(width = 1) +
  coord_polar("y") +
  xlim(0.5, 2.5) +
  theme_void() +
  labs(title = "Donut Chart of Categories")

Add labels that show either:

the percentages, or
the category names and values

data <- data.frame(
  category = c("A", "B", "C"),
  count = c(10, 60, 30)
)
data$percent <- data$count / sum(data$count)

ggplot(data, aes(x = 2, y = count, fill = category)) +
  geom_col(width = 1) +
  coord_polar("y") +
  xlim(0.5, 2.5) +
  theme_void() +
  geom_text(aes(label = paste0(round(percent * 100), "%")),
            position = position_stack(vjust = 0.5)) +
  labs(title = "Donut Chart with Percentages")

Questions

Why do we need to calculate label positions manually for this plot? Since the donut plots use polar cordinated, the positioning for the x and y are not the same. This is why we have to manually input informatuion.
Which label type is easier to read: percentages only, or category plus value? the percentage only is usually easier to read.

Task 3: Sunburst Plot

Create the following dataset:

sunburst_data <- data.frame(
  sequence = c(
    "Fruit-Apples",
    "Fruit-Bananas",
    "Fruit-Oranges",
    "Vegetable-Carrots",
    "Vegetable-Broccoli",
    "Vegetable-Peppers"
  ),
  value = c(30, 20, 25, 15, 18, 12)
)
sunburst(sunburst_data)

Use the sunburstR package to create a sunburst plot.

library(sunburstR)

sunburst_data <- data.frame(
  sequence = c(
    "Drinks-Water",
    "Drinks-Soda",
    "Drinks-Juice",
    "Snacks-Chips",
    "Snacks-Cookies",
    "Snacks-Candy"
  ),
  value = c(40, 25, 15, 10, 18, 12)
)
sunburst(sunburst_data)

Task 4: Treemap

Using this dataset:

sales_data <- data.frame(
  category = c("Fruit", "Fruit", "Fruit", "Vegetable", "Vegetable", "Vegetable"),
  subcategory = c("Apples", "Bananas", "Oranges", "Carrots", "Broccoli", "Peppers"),
  value = c(30, 20, 25, 15, 18, 12)
)

Create a treemap.

Requirements

use index = c(“category”, “subcategory”)
use vSize = “value”
include a title

library(treemap)
sales_data <- data.frame(
  category = c("Technology", "Technology", "Technology", "Furniture", "Furniture", "Furniture"),
  subcategory = c("Phones", "Laptops", "Tablets", "Chairs", "Tables", "Desks"),
  value = c(50, 40, 20, 30, 25, 35)
)
treemap(
  sales_data,
  index = c("category", "subcategory"),
  vSize = "value",
  title = "Product Sales Treemap"
)

How is a treemap similar to a sunburst chart? They both display hierarchical data and represent size within an area.
How is it different? they are different because a treemap uses nestedd rectangles to represent cateogires and a suburst uses concentric circles. A treemap is easier to compare sizes and a sunburst chart is good for showing structure and relationships.
Which one do you think is easier to read? I think a treemap is easier to read.

Task 5: Dendrogram

Create a simple hierarchy with:

one origin
four groups
three subgroups per group

Then convert it into a graph and plot it as a dendrogram. Add labels and points to the ends of the branches.

library(igraph)


origin <- "Animals"
groups <- c("Mammals", "Birds", "Fish", "Reptiles")

subgroups <- c(
  "Dog", "Cat", "Elephant",        # Mammals
  "Eagle", "Parrot", "Penguin",    # Birds
  "Shark", "Salmon", "Tuna",       # Fish
  "Snake", "Lizard", "Turtle"      # Reptiles
)


edges <- c()


for (g in groups) {
  edges <- c(edges, origin, g)
}


index <- 1
for (g in groups) {
  for (i in 1:3) {
    edges <- c(edges, g, subgroups[index])
    index <- index + 1
  }
}


g <- graph(edges = edges, directed = TRUE)

## Warning: `graph()` was deprecated in igraph 2.1.0.
## ℹ Please use `make_graph()` instead.
## This warning is displayed once per session.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

plot(
  g,
  layout = layout_as_tree(g),
  vertex.label = V(g)$name,
  vertex.size = 25,
  vertex.color = "lightgreen",
  edge.arrow.size = 0,
  main = "Animal Classification Dendrogram"
)

Task 6: Word Cloud

Run the following code to create a word based dataset from The State of the Union text. Annotate the lines to ensure you know how it was built. This uses a real speech and produces meaningful words.

#running packages already installed
library(janeaustenr) #provides text data from jane austen book
library(tidytext)#tools for text mining
library(dplyr)#data manipulation funtions
library(wordcloud2)#created word cloud visualizations
#load the data set 
text <- austen_books()
#convert the text into individual words and count them
word_counts <- text %>%
  unnest_tokens(word, text) %>%
  count(word, sort = TRUE)
#load common stop words dataset
data("stop_words")

#Pay special attention to this. This is important for word clouds. 
word_counts <- word_counts %>%
  anti_join(stop_words)

## Joining with `by = join_by(word)`

# Create the word cloud
wordcloud2(word_counts[1:100, ], size = 1)

# Uses the top 100 most frequent words

library(wordcloud2)

wordcloud2(data=demoFreq, size=1.6)

# Gives a proposed palette
wordcloud2(demoFreq, size=1.6, color='random-dark')

# or a vector of colors. vector must be same length than input data
wordcloud2(demoFreq, size=1.6, color=rep_len( c("green","blue"), nrow(demoFreq) ) )

# Change the background color
wordcloud2(demoFreq, size=1.6, color='random-light', backgroundColor="black")

Create a word cloud of the most commonly used words in the speech.

library(wordcloud2)

wordcloud2(data=demoFreq, size=1.3)

library(wordcloud2)


# Gives a proposed palette
wordcloud2(demoFreq, size=1.6, color='random-dark')

# or a vector of colors. vector must be same length than input data
wordcloud2(demoFreq, size=1.6, color=rep_len( c("green","blue"), nrow(demoFreq) ) )

# Change the background color
wordcloud2(demoFreq, size=1.6, color='random-light', backgroundColor="black")

# Create the word cloud

Pie and Donut Charts, Dendrograms, Circular Packing, Sunburst, & WordCloud

Pie Charts

Donut Charts

Sunburst Plots

Treemap

Circular Packing

Dendrograms

Circular Dendrograms

Word Clouds

Homework

Task 1. Pie chart with ggplot

Task 2: Create a simple pie chart in base R using the following values:

Task 3: Sunburst Plot

Task 4: Treemap

Task 5: Dendrogram

Task 6: Word Cloud