In recent years, the contemporary data mining community has developed a plethora of algorithms and methods used for different tasks in knowledge discovery within large databases. Furthermore, algorithms become more complex and hybrid as algorithms combining several approaches are suggested, the task of implementing such algorithms from scratch becomes increasingly time consuming. Spatial data sets often contain large amounts of data arranged in multiple layers. These data may contain errors and may not be collected at a common set of coordinates. Therefore, various data pre-processing steps are often necessary to prepare data for further usage. It is important to understand the quality and characteristics of the chosen data. Careful selection, preprocessing, and transformation of the data are needed to ensure meaningful analysis and results.