The aim is to analyse any patterns in the CO2 emission of the GCC (Bahrain, Kuwait, Oman, Qatar, Saudi Arabia, United Arab Emirates) from the data on CO2 emissions (metric tons per capaita) by the World Bank using the platform provided by DataBricks Community Edition.
Data cleaning is done and 3 regression models (Linear, LGBM, KNN) are used for predicting the CO2 emission in the gulf in 2025. Regression and result visualization performed using matpltlib.
- Import the DataBricks .ipynb notebook and attach it to a cluster.
- Upload co2e_data.csv on the same cluster.
- Execute and experiment with the notebook!