Previously… (1/2)

Chaining dplyr Verbs Using |>

Load Packages

library(tidyverse)

Define Data Frame as a Tibble

iris_tibble <- tibble(iris)

Advanced Example: The goal of this example is to transform the iris dataset by computing the ratio of Petal.Length to Sepal.Length for observations belonging to the “setosa” species.

iris_tibble |>  
  # rule 1: choose only the "setosa" species
  filter(Species == "setosa") |>  
  # rule 2: pick the columns Sepal.Length and Petal.Length
  select(Sepal.Length,Petal.Length) |>  
  # rule 3: create a new column called length_ratio
  mutate(length_ratio = Petal.Length/Sepal.Length)

Previously… (2/2)

The guiding principle of data science is the data science life cycle.

The Data Science Life Cycle

`tidyverse` Core Packages for Data Visualizations

tidyverse is a collection of packages suited for data processing and visualization.

Core packages specifically for data visualizations:

ggplot2 is a system for creating graphics, where you provide the data, specify how to map variables to plots, and it handles the details.

Data Visualization Using `ggplot2`

What is ggplot2?

Overview:
- ggplot2 is a powerful R package designed for data visualizations.
- It is part of the tidyverse ecosystem.
Key Features:
- Intuitive grammar for graphics.
- Intuitive syntax with layering using the operator +.

Why use ggplot2?

Ease of Use: Clear, human-readable code.
Efficiency: Built-in functions optimized for performance.
Consistency: Works seamlessly with other tidyverse packages such as dplyr for data wrangling.
Data Frames and Beyond: Works with data frames, tibbles, and databases.

The Grammar for Graphics

What is the Grammar of Graphics?

The Grammar of Graphics is a systematic approach to building visualizations by breaking down graphs into fundamental components.
The ggplot2 package in R is based on this framework, allowing for a highly customizable and layered approach to data visualization.

Key Components of `ggplot2`

Data: The dataset being visualized in tibble form.
Aesthetics (aes): The mapping of data variables to visual properties like position, color, size, and shape.
Geometries (geom): The type of plot (e.g., points, lines, bars) that represents the data.
Facets: Splitting data into multiple panels for comparison.

Statistics (stat): Computations applied to the data before plotting (e.g., smoothing, binning).
Coordinates (coord): The system defining how data is mapped onto the plot (e.g., Cartesian, polar).
Themes: Controls the overall appearance of the plot, such as background color, grid lines, and fonts.

Example: `iris` Data Set Scatter Plots

Plotting iris lengths

# establish data and variables
ggplot(iris_tibble, 
       aes(x = Sepal.Length, 
           y = Petal.Length)) +
  # draw scatter plot
  geom_point() + 
  # add theme layer
  theme_grey()

Layered Approach

Base layer: ggplot(data, aes(...)) defines the dataset and variables.
Geometric layers: + geom_*() specifies the type of plot.
Other layers: + facet_*(), + coord_*(), + theme_*() enhance the visualization.

\(\dagger\) Try out the above example code sequence with variables Sepal.Width and Petal.Width.

\(\star\) Note that the + operator here is used to “add” a layer, not adding numbers.

Aesthetics

The aes() function maps data variables to visual properties like position, color, size, and shape.

Plotting iris lengths by species

# establish data and variables
ggplot(iris_tibble, 
       aes(x = Sepal.Length, 
           y = Petal.Length,
           color = Species)) +
  # draw scatter plot
  geom_point() + 
  # add theme layer
  theme_grey()

Common Aesthetics Mappings

x and y: Map variables to the horizontal and vertical axes.
color: Assign colors to different categories.
size: Control the size of points or lines based on a variable.
shape: Change the shape of points according to a categorical variable.
fill: Fill color of geometric objects of different categories.

\(\star\) Note that the aes() function is called within the ggplot() function as the second argument.

Layering

Using the + operator allows us to add layers to the plot, which is used for customizing the plot or adding more information.

Plotting iris lengths by species with regression lines

# establish data and variables
ggplot(iris_tibble, 
       aes(x = Sepal.Length, 
           y = Petal.Length,
           color = Species)) +
  # draw scatter plot
  geom_point() + 
  # add regression lines
  geom_smooth(method = 'lm',
              formula = y~x) +
  # add theme layer
  theme_grey()

Layering to add more information

This example used the function geom_smooth()
geom_smooth() fits a regression line to each group, then adds this line as a layer on the plot. We will discuss more on this later.

\(\star\) Key Idea: All subsequent layers will inherit all information of the aes() variables defined in the ggplot() function.

Common Geometries for Numerical Variables

Geom	Function
`geom_point()`	Scatter plot for visualizing relationships between two numerical variables.
`geom_line()`	Line plot for trends over time or continuous sequences.
`geom_histogram()`	Histogram for visualizing the distribution of a single numerical variable.
`geom_boxplot()`	Box plot for showing distributions and detecting outliers.

\(\star\) Be careful when defining variables in aes(). For example, geom_histogram() only requires an x-axis variable, as it plots the distribution of a single numerical variable.

Example: `iris` Data Set Histograms

Plotting the distribution of iris sepal lengths by species

# establish data and variables
ggplot(iris_tibble, 
       aes(x = Sepal.Length, 
           fill = Species)) +
  # draw histogram
  geom_histogram(bins=10) + 
  # add theme layer
  theme_grey()

\(\star\) The geom_histogram() function allows you to adjust the number of bins, affecting how the data is visualized. We will discuss this later.

Activity: Visualize Numerical Data

Log-in to Posit Cloud and open the R Studio assignment MA7: Visualize Numerical Data.
Make sure you are in the current working directory. Rename the .Rmd file by replacing [name] with your name using the format [First name][Last initial]. Then, open the .Rmd file.
Change the author in the YAML header.
Read the provided instructions.
Answer all exercise problems on the designated sections.

Basics of Visualizations

Fundamentals of Data Science

Objectives

Previously… (1/2)

Previously… (2/2)

`tidyverse` Core Packages for Data Visualizations

Data Visualization Using `ggplot2`

The Grammar for Graphics

Key Components of `ggplot2`

Example: `iris` Data Set Scatter Plots

Aesthetics

Layering

Common Geometries for Numerical Variables

Example: `iris` Data Set Histograms

Activity: Visualize Numerical Data

Basics of Visualizations

Fundamentals of Data Science

Objectives

Previously… (1/2)

Previously… (2/2)

tidyverse Core Packages for Data Visualizations

Data Visualization Using ggplot2

The Grammar for Graphics

Key Components of ggplot2

Example: iris Data Set Scatter Plots

Aesthetics

Layering

Common Geometries for Numerical Variables

Example: iris Data Set Histograms

Activity: Visualize Numerical Data

`tidyverse` Core Packages for Data Visualizations

Data Visualization Using `ggplot2`

Key Components of `ggplot2`

Example: `iris` Data Set Scatter Plots

Example: `iris` Data Set Histograms