https://github.com/maxhalford/kaggle-recruit-restaurant

:trophy: Kaggle 8th place solution
https://github.com/maxhalford/kaggle-recruit-restaurant

kaggle kaggle-recruit-restaurant lightgbm timeseries

Last synced: about 1 hour ago
JSON representation

:trophy: Kaggle 8th place solution

• Host: GitHub
• URL: https://github.com/maxhalford/kaggle-recruit-restaurant
• Owner: MaxHalford
• Created: 2018-02-07T11:50:54.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2023-10-16T15:34:46.000Z (12 months ago)
• Last Synced: 2024-10-03T01:59:14.602Z (about 10 hours ago)
• Topics: kaggle, kaggle-recruit-restaurant, lightgbm, timeseries
• Language: Jupyter Notebook
• Homepage:
• Size: 84 KB
• Stars: 106
• Watchers: 4
• Forks: 57
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Kaggle recruit restaurant solution

My solution ranked 8th out of 2216 on the [Recruit Restaurant Visitor Forecasting Kaggle competition](https://www.kaggle.com/c/recruit-restaurant-visitor-forecasting). The solution focuses on targeted feature engineering and LightGBM cross-validation.

1. Have Python 3 installed

2. Download the Kaggle data from [here](https://www.kaggle.com/c/recruit-restaurant-visitor-forecasting/data)

3. Download the weather data from [here](https://www.kaggle.com/huntermcgushion/rrv-weather-data)

4. Run `pip install -r requirements.txt` (using a [virtual environment](http://docs.python-guide.org/en/latest/dev/virtualenvs/) is good practice)

5. [Install LightGBM](http://lightgbm.readthedocs.io/en/latest/Installation-Guide.html)

6. Run `jupyter notebook`

7. Open the `Solution.ipynb` notebook