Can you predict the level of damage to buildings caused by the 2015 Gorkha earthquake in Nepal based on aspects of building location and construction?
This is a model to predict the damage for buildings affected by the Nepal earthquake in 2025. The data is from the following competition: https://www.drivendata.org/competitions/57/nepal-earthquake/page/134/
Python version: 3.11.7
pip install -r requirements.txt
In the main.ipynb one can set different Parameters:
PARAMETER_TUNINGMODEL_VALIDATIONSAVE_MODELDO_SUBMISSSION
The streamlit app allows making predictions for example buidlings. Select the properties for a specific building and see its predicted damage grade.
Run the streamlit app from the console with:
streamlit run prediction_app_st.py