Pre-processing of data

Does your NLG system require data processing before development can begin? If any data manipulation is required, then the first step in developing your project is data processing. This involves gathering and cleaning data, and then analyzing it to find interesting patterns and trends that you want to talk about in the narrative.

During the design phase, it is important to identify what kinds of data processing you need to perform and where this will be done. If the processing is simple and if it can be done using existing analytics functions within Studio scripts, then it can be done within Studio. If data processing requires writing complex code, it is usually best to do this in a language designed for data analytics, such as Python.