2.3. Dynamic Visualization

Learning Outcome

Students will be able to compare traditional and dynamic graphing techniques and give reasons for and justify why a dynamic plot may be the appropriate choice (or is the appropriate choice for a specific data set).

Sample Tasks

• Decide the appropriate type of graph or illustrations based on the data set

  • Discuss the similarities and difference between a traditional boxplot and violin plot.

  • Consider advantages and disadvantages of using a map plot versus a heat map

• Tell the story using graphs

  • The goal of the activity is for the student to be able to create a presentation and produce a series of graphs using a large data set.

  • Students brainstorm ideas about what they would like to study.

  • Perform preliminary research and search for available data sets.

  • Generate an informal hypothesis based on their preliminary findings.

  • Gather and clean data.

  • Do trial charting and choose appropriate graphs.

  • Examine outliers and reclean the data if necessary and appropriate.

  • Generate a formal hypothesis based upon what they’ve been seeing in the data set.

  • Explain why the hypothesis fits their “story.”

  • Create a series of charts that verifies your hypothesis

  • Present your findings to tell the story.

  • Include the caveat that generation of a formal hypothesis and confirmation of the hypothesis on the same set of data does not settle the question.

[OhioDoHEducation21]

Warning

The requirements [OhioDoHEducation21] use the terms dynamic graphing techniques and dynamic plot, but these are not standard terms and it is not clear what is meant by them. Possibly, dynamic means interactive, but it might just mean newer. The sample tasks, however, give some guidance on what is required.

Our first readings are from Learning Data Science [LGN23] and are repeated from Section 2.1. These discuss finding the story in a data set.

• 10. Exploratory Data Analysis

  • 10.1. Feature Types

  • 10.2. What to Look For in a Distribution

  • 10.3. What to Look For in a Relationship

  • 10.4. Guidelines for Exploration

  • 10.5. Example: Sale Prices for Houses

Reading Questions

• What is a violin plot and when is it useful?

Our second readings, also from Learning Data Science [LGN23], describe principles for choosing types of graphs and graphing parameters in order to visually tell the story of a data set.

• 11. Data Visualization

  • 11.1. Choosing Scale to Reveal Structure

  • 11.2. Smoothing and Aggregating Data

  • 11.3. Facilitating Meaningful Comparisons

  • 11.4. Incorporating the Data Design

  • 11.5. Adding Context

Reading Questions

• What is over-plotting?

• What is a (topographical) map plot?

• What is a (density) heat map?

Further Resources

See Section 2.1 for information on plotting with Matplotlib and Seaborn.