Long data

As explained in The Well-Grounded Data Analyst

Long data is a tabular representation in which each row records one measurement or entity-participation observation.

Long data stores one observation per row: a measurement or an entity’s participation in an event. Repeated attributes that would occupy separate columns in a wide table become values in shared columns, while identifiers and context remain alongside each observation. section 3.1.1

Choose the structure for the analytical question, not as a cosmetic cleanup. Long data can make it easier to compare categories, change granularity, and build cross-tabulations; the resulting model should capture transformations that would otherwise be repeated for every analysis. section 3.1.1 section 6.4.2

Representing football results

A wide match record has separate Home team, Away team, Home goals, and Away goals columns. A long version uses two rows per match: one for each team, with a Home or away? value and a Goals scored value. Match details such as date, competition, and round are repeated for both participants. section 3.1.1

For multiple-choice survey responses, first turn selections into indicator columns, then gather each selected option’s counts by response category into a long table. That table can be reshaped into percentage cross-tabs and displayed as a heatmap, making comparisons across use cases easier to inspect. section 6.4.2

Table 3.2 The same football results in a long format, one row per match participant

Match ID	Date	Competition	Round	Team	Home or away?	Goals scored
1	2014-07-04	World Cup 2014	Quarter-final	France	Home	0
1	2014-07-04	World Cup 2014	Quarter-final	Germany	Away	1
2	2014-07-04	World Cup 2014	Quarter-final	Brazil	Home	2
2	2014-07-04	World Cup 2014	Quarter-final	Colombia	Away	1
3	2014-07-05	World Cup 2014	Quarter-final	Argentina	Home	1
3	2014-07-05	World Cup 2014	Quarter-final	Belgium	Away	0

Compare the two participant rows for each match with the single wide match record: team role and goals are values rather than paired home/away columns. section 3.1.1

Figure 6.38 A snapshot of long-format data comparing AI tool use case options with trustworthiness

Inspect a long-form survey artifact in which AI tool-use options are paired with trustworthiness response counts before cross-tabulation. section 6.4.2

How The Well-Grounded Data Analyst covers it

How deep it goes

Defines long versus wide structure and demonstrates reshaping survey indicators into a long table before crosstabs and heatmaps.

Examples

Uses football matches with one row per participant and survey AI-use options grouped by favorability or trustworthiness.

What you can do after

Apply it via pandas to prepare category cross-tabs and heatmaps from repeated survey-option analyses.

How it connects

Connects data modeling, wide data, data cleaning, granularity, categorical data, cross-tabulation, and heatmaps.

liveBookmanning.com

Read The Well-Grounded Data Analyst on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Statistics Slam DunkLong format is a tabular arrangement in which repeated measurements are represented as separate rows with variable-identifying columns.

Compare how 2 books explain long data →

Related concepts

• wide formatalternative to · Wide format is a tabular layout in which each entity occupies a row and distinct measurements, variables, or attributes occupy separate columns.
• pivot_longer() functionproduced by · The pivot_longer() function from tidyr reshapes tabular data from wide format into long format by gathering multiple columns into key-value columns.
• datakind of · Data is represented information, observations, measurements, or other values that can be stored, processed, transmitted, analyzed, or interpreted.

This explainer was generated by Manning's knowledge graph from the text of The Well-Grounded Data Analyst. The section links point to the parts of the book it draws on.