Python project to predict the sales of retail stores with machine learning. This project is based on the data provided in Kaggle Competition.
Kaggle Link : https://www.kaggle.com/c/favorita-grocery-sales-forecasting/
- Free software: MIT license
- Documentation: https://retail-sales-prediction.readthedocs.io.
We create the project environment using below command.
conda env create -f environment.yml -p ./venv
Update the existing conda environment
conda env update -f environment.yml -p ./venv
Activate the environment
conda activate ./venv
Machine learning pipeline to predict the sale forecasting. This project is the sand box and needs a bit of work to complete it.
Currently it supports below features
- Running the Light GBM Model with fixed training, validation and test sets.
- Two variants of how unit_sales are filled NA. More can be added
- Notebooks with Exploratory data analysis
- Notebooks with Feature engineering and Model Training
- Documentation using Sphnix
You can view the project slides of my project at using this link
This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.