The main objective of this project is to predict the level of damage to buildings caused by the 2015 Gorkha earthquake in Nepal by using different aspects of the buildings. The data is from the drivendata.org competition: "Richter's Predictor: Modeling Earthquake Damage." The micro-averaged F1 score was the metric used for this project, and I was able to achieve 0.7273 as the best score by fine-tuning a random forest model.
- Python 3
- Scikit-learn 0.22.1
- NumPy 1.17.5
- Pandas 0.25.3
- Matplotlib 3.1.2
- Seaborn 0.9.0
- SciPy 1.4.1