install.packages("ggplot2")

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

install.packages("dplyr")

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

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(diamonds)

glimpse(diamonds)

## Rows: 53,940
## Columns: 10
## $ carat   <dbl> 0.23, 0.21, 0.23, 0.29, 0.31, 0.24, 0.24, 0.26, 0.22, 0.23, 0.…
## $ cut     <ord> Ideal, Premium, Good, Premium, Good, Very Good, Very Good, Ver…
## $ color   <ord> E, E, E, I, J, J, I, H, E, H, J, J, F, J, E, E, I, J, J, J, I,…
## $ clarity <ord> SI2, SI1, VS1, VS2, SI2, VVS2, VVS1, SI1, VS2, VS1, SI1, VS1, …
## $ depth   <dbl> 61.5, 59.8, 56.9, 62.4, 63.3, 62.8, 62.3, 61.9, 65.1, 59.4, 64…
## $ table   <dbl> 55, 61, 65, 58, 58, 57, 57, 55, 61, 61, 55, 56, 61, 54, 62, 58…
## $ price   <int> 326, 326, 327, 334, 335, 336, 336, 337, 337, 338, 339, 340, 34…
## $ x       <dbl> 3.95, 3.89, 4.05, 4.20, 4.34, 3.94, 3.95, 4.07, 3.87, 4.00, 4.…
## $ y       <dbl> 3.98, 3.84, 4.07, 4.23, 4.35, 3.96, 3.98, 4.11, 3.78, 4.05, 4.…
## $ z       <dbl> 2.43, 2.31, 2.31, 2.63, 2.75, 2.48, 2.47, 2.53, 2.49, 2.39, 2.…

Something I want to add on from last class:

ggplot(mtcars, 
       aes(x = wt, y = mpg, size = hp)) +
  geom_point(alpha = 0.7, color = "steelblue") +
  scale_size(range = c(3, 10)) +
  theme_minimal() +
  labs(
    title = "Fuel Efficiency vs Vehicle Weight",
    subtitle = "Bubble size represents horsepower",
    x = "Weight (1000 lbs)",
    y = "Miles per Gallon",
    size = "Horsepower"
  )

Boxplots

Basic boxplot

Compare diamond price across cut quality.

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot()

#improve readability by rotating axis text
ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot(fill = "steelblue") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

#add transparency
ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot(fill = "steelblue", alpha=0.6) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Violin Plots

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_violin(fill = "skyblue", alpha = 0.6)

# Violin with boxplot overlay 

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_violin(fill = "lightblue", alpha = 0.4, trim = FALSE) +
  geom_boxplot(width = 0.1, alpha = 0.7)

Outlier Formatting

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_violin(fill = "lightblue", alpha = 0.4, trim = FALSE) +
  geom_boxplot(width = 0.1, alpha = 0.7, outlier.size = 0.5, outlier.colour = "red")

ggplot(mpg, aes(x = class, y = hwy)) +
  geom_boxplot(outlier.shape = NA) +  # hide default outliers
  geom_jitter(width = 0.2, height = 0, alpha = 0.6, color = "red", size = 2) +
  theme_minimal() +
  labs(
    title = "Highway MPG by Vehicle Class with Jittered Outliers",
    x = "Vehicle Class",
    y = "Highway MPG"
  )

library(dplyr)

mpg_outliers <- mpg %>%
  group_by(class) %>%
  mutate(q1 = quantile(hwy, 0.25),
         q3 = quantile(hwy, 0.75),
         iqr = q3 - q1,
         is_outlier = hwy < (q1 - 1.5*iqr) | hwy > (q3 + 1.5*iqr)) %>%
  filter(is_outlier)

# Plot
ggplot(mpg, aes(x = class, y = hwy)) +
  geom_boxplot() + #not this is keeping the outliers already.
  geom_jitter(data = mpg_outliers, width = 0.2, color = "red", size = 2, alpha = 0.8) +
  theme_minimal()

ggplot(mpg, aes(x = class, y = hwy)) +
  geom_boxplot(outlier.shape = NA) +  # hide default outliers
  geom_jitter(data = mpg_outliers, width = 0.2, color = "red", size = 2, alpha = 0.8) +
  theme_minimal()

Additional Axis Formatting

#Rounding axis labels 

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot() +
  scale_y_continuous(labels = scales::label_number(accuracy = 100))

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot() +
  coord_cartesian(ylim = c(0, 5000))

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot() +
  scale_y_continuous(limits=c(0, 5000))

## Warning: Removed 14714 rows containing non-finite outside the scale range
## (`stat_boxplot()`).

scale_y_continuous(limits = …) → removes data outside range coord_cartesian() → zooms without removing data

Color Palettes

ggplot(diamonds, aes(x = cut, y = price, fill = cut)) +
  geom_boxplot() +
  scale_fill_brewer(palette = "Set2")

#find color pallets online

#Viridis is colorblind friendly
ggplot(diamonds, aes(x = cut, y = price, fill = cut)) +
  geom_boxplot() +
  scale_fill_viridis_d() #_d = discrete

#when using virdis, make sure you put d because it also works with continuos data so add d to make it sort the colors to categories

Subtitles and Captions

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot(fill = "steelblue") +
  labs(
    title = "Diamond Prices by Cut Quality",
    subtitle = "Boxplots show distribution of price across cut categories",
    x = "Cut Quality",
    y = "Price (USD)",
    caption = "Source: ggplot2 diamonds dataset"
  )

Formatting Titles

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot(fill = "steelblue") +
  labs(
    title = "Diamond Prices by Cut Quality",
    subtitle = "Boxplots show distribution of price across cut categories",
    x = "Cut Quality",
    y = "Price (USD)",
    caption = "Source: ggplot2 diamonds dataset"
  ) + theme(
    plot.title = element_text(face = "bold", size = 14),
    plot.subtitle = element_text(size = 12),
    plot.caption = element_text(size = 8, hjust = 1)
  )

Improving Axis Readability

# Discuss the ordering of themes! 

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot(fill = "steelblue") +
  labs(
    title = "Diamond Prices by Cut Quality",
    subtitle = "Boxplots show distribution of price across cut categories",
    x = "Cut Quality",
    y = "Price (USD)",
    caption = "Source: ggplot2 diamonds dataset"
  ) + theme(
    plot.title = element_text(face = "bold", size = 14),
    plot.subtitle = element_text(size = 12),
    plot.caption = element_text(size = 8, hjust = 1)
  ) +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
theme(axis.text = element_text(size = 12)) +
  theme_minimal () ########## ORDER MATTERS

ggplot(diamonds, aes(x = cut, y = price)) +
  geom_boxplot(fill = "steelblue") +
  labs(
    title = "Diamond Prices by Cut Quality",
    subtitle = "Boxplots show distribution of price across cut categories",
    x = "Cut Quality",
    y = "Price (USD)",
    caption = "Source: ggplot2 diamonds dataset"
  ) +   theme_minimal () +########## ORDER MATTERS
  theme(
    plot.title = element_text(face = "bold", size = 14),
    plot.subtitle = element_text(size = 12),
    plot.caption = element_text(size = 8, hjust = 1)
  ) +
theme(axis.text.x = element_text(angle = 45, hjust = 1)) +
theme(axis.text = element_text(size = 12))

#theme_minimal needs to go before your theme edits because it will ignore what you told it to do and apply the criteria of the theme

Reordering Data

In plain English:

Group the data by cut
Compute the median price within each cut
Reorder the cut categories from lowest median price to highest
Use that new order on the x-axis

#What if you dont link the order that it has set by default?


ggplot(diamonds, aes(x = reorder(cut, price, median), y = price)) + #“Reorder the levels of cut based on the median value of price within each cut.”
  geom_boxplot(fill = "steelblue") +
  coord_cartesian(ylim = c(0, 5000))

ggplot(diamonds, aes(x = reorder(cut, -price, median), y = price)) + #“Reorder the levels of cut based on the median value of price within each cut.”
  geom_boxplot(fill = "steelblue") +
  coord_cartesian(ylim = c(0, 5000))

#what if we add "decr" to reverse the order?
#⚠ desc() does not work inside base reorder().

Combining it all

ggplot(diamonds, aes(x = cut, y = price, fill = cut)) +
  geom_violin(alpha = 0.4, trim = FALSE) +
  geom_boxplot(width = 0.1, alpha = 0.7) +
  scale_fill_viridis_d() +
  coord_cartesian(ylim = c(0, 12000)) +
  labs(
    title = "Distribution of Diamond Prices by Cut",
    subtitle = "Violin + Boxplot Comparison",
    x = "Cut Quality",
    y = "Price (USD)",
    caption = "Source: ggplot2 diamonds dataset"
  ) +
  theme_minimal() +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1),
    plot.title = element_text(face = "bold")
  )

Barplots

mtcars$cyl  <- as.factor(mtcars$cyl)
mtcars$gear <- as.factor(mtcars$gear)

ggplot(mtcars, aes(x = cyl)) +
  geom_bar()

#geom_bar() by default uses stat = "count"
#It counts observations in each category
#No y variable needed

library(dplyr)

#If you want more than counts, you will need a summary table first
avg_mpg <- mtcars %>%
  group_by(cyl) %>%
  summarise(mean_mpg = mean(mpg))

ggplot(avg_mpg, aes(x = cyl, y = mean_mpg)) +
  geom_col()

#geom_bar() → counts, x is needed
#geom_col() → uses provided y values
# This distinction confuses students constantly.

#stacked barplots
ggplot(mtcars, aes(x = cyl, fill = gear)) +
  geom_bar()

#What happens:
#Bars represent total count of cars per cylinder group
#Segments show distribution of gear types

#⚠ Hard to compare middle segments
#⚠ Hard to compare across bars
#⚠ Order of stacking affects readability


# Add proportions instead!
ggplot(mtcars, aes(x = cyl, fill = gear)) +
  geom_bar(position = "fill")

#Each bar = 100%
#Shows composition, not count

#grouped barplots
ggplot(mtcars, aes(x = cyl, y = mpg, fill = gear)) +
  stat_summary(fun = mean,
               geom = "col",
               position = "dodge")

#dodge makes them side by side 
#stat_summary() calculates summary inside ggplot
#Compare with pre-summarized approach

#The additional of error bars
ggplot(mtcars, aes(x = cyl, y = mpg, fill = gear)) +
  stat_summary(fun = mean,
               geom = "col",
               position = position_dodge(width = 0.9)) +
  stat_summary(fun.data = mean_se,
               geom = "errorbar",
               position = position_dodge(width = 0.9),
               width = 0.2)

Homework :

Part 1: Boxplots (20 pts)

Dataset: mpg
Create a boxplot of hwy (highway mpg) for each vehicle class (class).
Rotate the x-axis text 45 degrees for readability.
Add a title, subtitle, and caption to your plot.
Color the boxes by drivetrain (drv).

ggplot(mpg, aes(x = class, y = hwy, color = drv)) +
  geom_boxplot() +
  labs(
    title = "Highway MPG Compared by Drive Type in Each Class",
    subtitle = "created by Abi Wise",
    caption = "Source: ggplot mpg dataset")+
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Questions:

1.Which vehicle class has the highest median highway mpg?

The compact car class seems to have the highest median highway mpg.

2. Which has the largest variability?

The suv class seems to have the largest variability because it has the most outliers.

Create an alteration of this plot where the outliers are shown in a way in which they do not overlap (consider jittering and coloring).

library(dplyr)

boxplot_outliers <- mpg %>%
  group_by(class) %>%
  mutate(q1 = quantile(hwy, 0.25),
         q3 = quantile(hwy, 0.75),
         iqr = q3 - q1,
         is_outlier = hwy < (q1 - 1.5*iqr) | hwy > (q3 + 1.5*iqr)) %>%
  filter(is_outlier)

ggplot(mpg, aes(x = class, y = hwy, color = drv)) +
  geom_boxplot(outlier.shape = NA) +
  geom_jitter(data = boxplot_outliers, width = 0.2, color = "purple", size = 2, alpha = 0.5)+
  labs(
    title = "Highway MPG Compared by Drive Type in Each Class",
    subtitle = "created by Abi Wise",
    caption = "Source: ggplot mpg dataset")+
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Part 2: Violin Plots

Dataset: mpg
Create a violin plot of cty (city mpg) for each vehicle class.
Overlay boxplots on top of the violins. Change as necessary for aesthetics.
Use a transparent fill so that both distributions and boxplots are visible.
Add a descriptive title, subtitle, and labels.

ggplot(mpg, aes(class, cty))+
  geom_violin(fill = "lightpink", alpha = 0.4, trim = FALSE) +
  geom_boxplot(width = 0.05)+
  labs(
    title = "City MPG Distribution by Vehicle Class",
    subtitle = "Violin plots with boxplots overlayed to show distribution and summary statistics",
    x = "Vehicle Class",
    y = "City MPG"
  )

Questions:

1. How does the violin plot help you understand the distribution compared to the boxplot alone?

Violin plots with boxplots help us undertstand where the mean is compared to the ditribution which helps us get a better idea of how the data compares by class.

2. Are there any classes with unusual distributions or outliers?

The subcompact class seems to have a very big unusual distribution with one outlier

Part 3: Barplots

Dataset: diamonds
Create a simple barplot showing the number of diamonds for each cut.
Create a stacked barplot showing the number of diamonds by cut and colored by color.
Create a grouped (side-by-side) barplot showing the same data.

ggplot(diamonds, aes(cut))+ 
  geom_bar()

ggplot(diamonds, aes(cut, fill = color))+ 
  geom_bar()

ggplot(diamonds, aes(cut, fill = color))+ 
  geom_bar(position = "dodge")

Questions:

1. What does the stacked barplot show that the simple barplot does not?

A stakced barplot allows you to see a category within the category while a simple barplot just gived you the count of the category.

2. When is the grouped barplot more useful than the stacked barplot?

In a grouped barplot it is easier to compare and see the exact number of what the data represents. A stacked bar plot is hard to see how the data compares and the amount of each type in a specific category.

Part 4: Barplots Cont.

Dataset: diamonds

Compute the average price of diamonds for each cut using dplyr.
Create a barplot showing the average price for each cut (geom_col()).
Add meaningful axis labels, a title, subtitle, and caption.
Color the bars by color or clarity to show subgroup differences.
Rotate x-axis labels if needed for readability.
Reorder by average price to make comparisons clearer.

avg_price_cut <- diamonds %>%
  group_by(cut) %>%
  summarise(avg_price = mean(price))
avg_price_cut_clarity <- diamonds %>%
  group_by(cut, clarity) %>%
  summarise(avg_price = mean(price), .groups = "drop")

ggplot(avg_price_cut_clarity, aes(x = reorder(cut, avg_price), y = avg_price, fill = clarity)) +
  geom_col(position = "dodge")+
    labs(
    title = "Average Diamond Price Compared to Cut and Clarity",
    subtitle = "Created by Abi Wise",
    x = "Diamond Cut",
    y = "Average Price",
    caption = "Source: ggplot2 diamonds dataset"
  )

Create the same plot using the stat_summary approach. Add error bars to the plot.

ggplot(diamonds, aes(x = cut, y = price, fill = clarity)) +
  stat_summary(fun = mean,
               geom = "col",
               position = "dodge")+
  stat_summary(fun.data = mean_se,
               geom = "errorbar",
               position = position_dodge(width = 0.9),
               width = 0.2)

Boxplots, Histograms, and Categorical Comparisons

2026-03-04