Data Transformation

As discussed earlier, the first step in creating a visualization is data selection. This refers to choosing from the data the attributes needed for the visualization.

Once we select the attributes, the next step is usually to perform aggregation or other transformations in order to be able to create appropriate visualizations, that communicate the required information effectively.

Common aggregation functions include SUM, MAX, MIN, AVERAGE, MEDIAN and STDDEV.

Transformations Related to Temporal Attributes

These involve transformations at different levels/resolutions: seconds, minutes, hours; days, weeks, months, years etc.

Transformations Related to Spatial Attributes

These involve transformations at different levels/resolutions: zip code, county, city, state, country etc.

Geo coding/decoding refers to going from the name of a place to its geo coordinates and vice versa.

Binning

It is the process of transforming a quantitative attribute to an ordinal attribute. Ex. restaurant inspection scores from numbers to letters.

Rescaling/Re-Expression

There are few ways to accomplish this:

- Normalization

This refers to bringing all the values to a scale of say [-1, 1].

- Percentages

This refers to converting quantitative values to percentages, which makes it easier to make comparisons.