Categorical data: Difference between revisions

Categorical data is a type of machine learning information that represents qualitative or nominal features rather than numerical or continuous values. It often represents attributes or characteristics of objects or events which cannot be quantified quantitatively. Categorical data plays an essential role in many machine learning tasks such as classification, clustering and regression; this article will give an extensive explanation of categorical data types and applications within machine learning.

Categorical data is commonly represented with one-hot encoding, which transforms each category value into a binary vector of 0s and 1s. Each binary vector has the same length as the number of categories, with 1 being placed at each position corresponding to that category. For instance, if we have categorical variable representing car colors (red, blue, and green), one-hot encoding could read red = [1, 0, 1], blue = [0, 1, 0, 1] and green = [0, 0, 0, 1].