Data sets are made up of data objects. A data object represents an entity such as info on customers, products etc. Data objects are typically described by attributes. The data objects stored in database are called data tuples. The row in database refers data objects and column refers its attributes.
A feature of a data object is called an attribute. The type of attributes are Nominal, Binary, Ordinal and Numeric.
A nominal attribute represents some kind of category, code, or state etc., which are also referred to as categorical. Though a nominal attribute may have integers as values, it is not considered a numeric attribute because the integers are not meant to be used quantitatively.
A binary attribute is a nominal one with only two states: 0 or 1. It is also called as Boolean when the states refer true or false. A binary attribute is symmetric if both of its states are equally valuable.
An ordinal attribute is an attribute with possible values that have a meaningful order or ranking among them.
The nominal, binary, and ordinal attributes describe a feature of an object without giving an actual size or quantity, called as qualitative.
A numeric attribute is a measurable quantity, represented in integer or real values, called as quantitative.
Numeric attributes can be interval-scaled or ratio-scaled. Interval-scaled attributes are measured on a scale of equal-size units. A ratio-scaled attribute is a numeric attribute with an inherent zero-point.
A discrete attribute has a finite or countably infinite set of values, which may or may not be represented as integers. If an attribute is not discrete, it is continuous.