https://github.com/nancyhamdan/wids-2022

Predicting building energy consumption as part of the WiDS 2022 Datathon
https://github.com/nancyhamdan/wids-2022

ensemble gradientboostingregressor lgbm lgbmregressor random-forest randomforest-regressor regression

Last synced: 1 day ago
JSON representation

Predicting building energy consumption as part of the WiDS 2022 Datathon

• Host: GitHub
• URL: https://github.com/nancyhamdan/wids-2022
• Owner: nancyhamdan
• Created: 2022-03-28T22:50:12.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2022-03-28T23:29:13.000Z (over 2 years ago)
• Last Synced: 2024-01-31T15:27:42.203Z (9 months ago)
• Topics: ensemble, gradientboostingregressor, lgbm, lgbmregressor, random-forest, randomforest-regressor, regression
• Language: Jupyter Notebook
• Homepage:
• Size: 11.7 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Predicting Building Energy Consumption - WiDS 2022 Datathon

This is my solution for the [WiDS 2022 Datathon](https://www.kaggle.com/competitions/widsdatathon2022)

To help combat climate change, this year's WiDS datathon was to predict building energy consumption using a dataset that details buildings characteristics and weather conditions of the area the buildings are at. My solution included minimal feature enginnering and used a blend of a LightGBM and a Random Forest model to get the final predictions. My solution's RMSE score of 22.573 on private test data ranked 81/829 in the datathon, you can view the leaderboard [here](https://www.kaggle.com/competitions/widsdatathon2022/leaderboard).