The selection of an appropriate method of data analysis is a key problem for researchers from various fields of applications. They consider different methods of data classification, often based on the thematic scope of the data at their disposal. However, various data characteristics, such as data set size, data type and quality, gaps, outliers and other anomalies, can make proper selection significantly difficult. Therefore, in this study we propose a method based on a very universal classifier designed on the basis of calculations using information granules. The main objective of the work is to present and comprehensively verify the effectiveness of the classifier. As an example of application, we propose complicated yet currently important data coming from widely understood ecological research. Detailed numerical experiments indicate the high efficiency of the proposed method and the possibility of easy application to data appearing in other fields. In addition, various types of aggregation functions of the classification results are considered in order to obtain the most reliable results for the discussed problems,