In terms of geovisualization, data classification can be crucial for a satisfying result. In classification, large amounts of data are grouped into smaller amounts that are labeled in some way. There are different types of classification schemes that are more or less suitable for different types of data. Equal steps, quantiles, arithmetic progressions and percentiles are examples of classification schemes. The classification can be done supervised or unsupervised. The classification is often meant to represent the data distribution in its whole. 

Data types

Variables are the subjects used in statistical analyses, for instance in elevation, income or rainfall. Individual observations of the varibles are called values, and they display e.g. a specific height or a specific income. When values are arranged in an order, it's called an array. For instance, an array can arrange values in an ascending or descending order.  

Data kan be qualitative or quantitative. Nominal data is an example of qualitative data, where e.g. land use can be described and different features can be distinguished from each other. Ordinal data, on the other hand, is grouped by rank and based on quantitative data. Ordinal data can be examined in different ways. The median (the value in the middle the rank), for instance, describes a central tendency in the data. 

Data that can be arranged in a standard scale is called interval data. Temperature data is an example of this. Ratio data is similar to interval data, but begins at a zero point where no features are present, e.g. population data and elevation data.

Color schemes