Glossary

Attribute

The name/label of a column of a data set. Often known as variable, sometimes referred to as feature in the literature, but we make specific distinctions between attribute and feature.

Feature

The combination of an attribute and the possible values of the attribute.

Instance

A data instance is a data entry/record/sample of a data set.

Metadata

The information/data that describes the actual data set.

Data sanitisation

A data processing procedure that transforms the data into a format that is compliant with the requirement of the machine learning tool. For example, it includes dealing with missing data.

Nary

A nary function is a function that takes n parameters.

Introspect

Examine a predictive model and obtain a feeling of how it works.