Data Science · Advanced level

Advanced level · Module 5: Data Governance and Responsible Data Science · Lesson 2 of 4

Documenting Data and Analyses

Document data sets and analyses so others can understand, trust and reuse them.

In this lesson you will

  • Write data dictionaries and datasheets
  • Document methods and decisions in analyses

Key concepts

data dictionarydatasheet for data setsmethods notedecision log

The lesson

A data dictionary describes each variable: name, meaning, type, allowed values and source. A datasheet describes a whole data set: why and how it was collected, who is included, known limits and permitted uses.

Analyses need a methods note and a decision log: which data, which cleaning, which choices and why. Future readers — including you in six months — need them.

Documentation should live with the data and code, in the same repository, and be updated when they change.

Step by step

  1. Complete the data dictionary for one data set.
  2. Write a datasheet for it.
  3. Write the methods note for the analysis.
  4. Start a decision log.

Practice activity

Document the provided project's data and analysis.

Expected result: Complete documentation that lets a new analyst take over the project.

Check your understanding

  1. What is a datasheet for a data set?

    Show answer

    A document describing its purpose, collection, coverage, limits and permitted uses.

  2. Where should documentation live?

    Show answer

    With the data and code, kept up to date.

Taught live by an instructor — online or in person. Free course lessons are for self-study and do not lead to a certificate — see registration options.