Supplementary Data and Code for Discourse vs. Decarbonisation: Tracking the Alignment Between EU Climate Rhetoric and National Energy Patterns

This repository contains the datasets, intermediate calculations, processed indicators, and program code accompanying the article Discourse vs. Decarbonisation: Tracking the Alignment Between EU Climate Rhetoric and National Energy Patterns, published in Energies (MDPI, 2025). The materials include: Processed datasets: time-series features derived from fossil fuel consumption data, recent 5-year trend indicators, feature importance scores, and classification outputs. Machine learning model: a trained Random Forest classifier used for classification of EU Member States as “greening” or “not greening.” Intermediate calculations: transition dynamics (e.g., label flips, slope differentials) and dashboard-ready indicators. Documentation: a README file with guidance on the use of the datasets and model. Data Sources Primary data were obtained from: International Energy Agency (IEA), World Energy Balances (https://www.iea.org/data-and-statistics)