Ordinal data
Ordinal data consists of categorical values with a meaningful order or rank, without necessarily having equal intervals between categories.
Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI
Categorical data whose values have a meaningful order or rank.
- How it is used
- Classifies ordered tabular columns so they receive treatment distinct from purely numeric measurements.
- How deep it goes
- Defines ordinal scales through rankings and unequal intervals, warning against mean and standard-deviation calculations.
- Examples
- Uses product stars, race placements, Likert responses, cylinder counts, and model years as ordered values.
- What you can do after
- Evaluate whether a tabular column represents ordered levels rather than a purely numeric measurement.
Read how Machine Learning for Tabular Data: XGBoost, Deep Learning, and AI explains ordinal data →
The Well-Grounded Data Analyst
Ordinal data consists of categorical values whose categories have a meaningful natural order.
- How it is used
- Frames ordered survey answers and discrete-value columns for categorical-data exploration and relationship analysis.
- How deep it goes
- Defines ordered categories, inspects numeric-looking columns, and applies rank-based tests while deferring broader categorical testing.
- Examples
- Uses clothing sizes, Likert responses, heart-disease test categories, and AI-tool trust ratings as examples.
- What you can do after
- Apply it via pandas and SciPy by ranking ordered responses, filtering invalid entries, and calculating Spearman’s correlation or Kendall’s tau.
Read how The Well-Grounded Data Analyst explains ordinal data →
Effective Data Analysis
Ordinal data consists of observations assigned to categories with a meaningful order but without necessarily equal spacing between categories.
- How it is used
- Uses ordered categories for exploratory features, group comparisons, and modeling decisions.
- How deep it goes
- Distinguishes ordinal from continuous data and lists rank-based tests, but stops short of detailed test calculations.
- Examples
- Uses month number, day of week, weekday indicators, rat-sighting boxplots, and date-derived feature columns.
- What you can do after
- Apply it via grouped distributions, cautious correlation use, and named non-parametric tests for ordinal comparisons.
Starting Data Analytics with Generative AI and Python
An ordinal variable is a categorical variable whose values have a meaningful order but not necessarily equal intervals.
- How it is used
- Uses ordered review scores to investigate how product, transaction, shipping, and payment attributes relate to customer ratings.
- How deep it goes
- Defines ordinal review scores and demonstrates regression preparation, fitting, prediction, evaluation, coefficient inspection, and assumption checking.
- Examples
- Uses 1–5 review scores, merged product and order records, Python predictions, confusion matrices, and named feature coefficients.
- What you can do after
- Diagnose ordinal-score predictions with a fitted model, evaluation metrics, confusion matrices, and coefficient-to-feature mappings.
Read how Starting Data Analytics with Generative AI and Python explains ordinal data →
Ensemble Methods for Machine Learning
An ordinal feature is a categorical input variable whose categories have an inherent ordering.
- How it is used
- Guides categorical-feature encoding by distinguishing meaningful category order from unordered membership.
- How deep it goes
- Explains ordinal-versus-nominal intuition, numeric mappings, scikit-learn usage, and one-hot tradeoffs without covering model-specific effects.
- Examples
- Uses T-shirt sizes S–XL, colors, predicted cost, explicit category lists, and encoded feature matrices.
- What you can do after
- Apply ordinal and one-hot encoders while matching the representation to each feature’s category structure.
Read how Ensemble Methods for Machine Learning explains ordinal data →
Tiny Python Projects: Learn coding and testing with puzzles and games
An ordinal value is a representation that identifies the position of an item in an ordered sequence, such as first or second.
- How it is used
- Uses ordered labels to generate the day wording in a programmatic Twelve Days of Christmas verse.
- How deep it goes
- Explains list and dictionary representations, indexing adjustments, tests, and the distinction from Python's ord() function.
- Examples
- Demonstrates day names, verse generation, pytest assertions, ASCII character values, and character-range exploration.
- What you can do after
- Apply it via Python by mapping positions to labels, handling indexing, testing lookups, and converting characters with ord() and chr().
D3.js in Action, Third Edition
An ordinal value is a categorical value whose labels have a meaningful order or rank.
- How it is used
- Guides data classification, visual encoding, and D3 scale selection for visualization projects.
- How deep it goes
- Defines ordered qualitative categories and connects them to palettes and scales, while deferring detailed scale treatment.
- Examples
- Uses T-shirt sizes and coffee-order sizes to demonstrate meaningful category order.
- What you can do after
- Apply ordinal classifications when organizing attributes and choosing visual encodings or D3 scales.
Read how D3.js in Action, Third Edition explains ordinal data →
Data Without Labels
Ordinal data consists of categories that have an inherent order but not necessarily meaningful numeric spacing.
- How it is used
- Classifies qualitative variables by distinguishing ordered categories from binary and nominal data.
- How deep it goes
- Defines ordinal data and contrasts it with nominal data, stopping before encoding, modeling, or statistical treatment.
- Examples
- Uses fast/medium/slow and positive/neutral/negative as examples of ordered categories.
- What you can do after
- Evaluate/understand whether categorical values possess an inherent order rather than merely distinct labels.
Related concepts
- categorical datakind of · Categorical data consists of values representing membership in a discrete set of named or ordered categories rather than measured numerical magnitudes.
- data typekind of · A data type classifies values and specifies their representation or interpretation and the operations applicable to them.
- qualitative datakind of · Qualitative data is descriptive, nonnumeric information representing characteristics, categories, meanings, experiences, opinions, or context rather than measured quantities.
- Likert scaleproduced by · A Likert scale is an ordered response scale whose labeled categories express degrees of agreement, quality, intensity, preference, or another evaluated property.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.