Coffee Recommender - Marcelino Mayorga Quesada
This is a simple machine learning exercise with the objective to recommend coffee leveraging Coffee Quality Institute's data and applying Content-Based Filtering
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.
Conda and requirements.txt
streamlit
streamlit-pandas-profiling
pandas
scikit-learn
conda
1 - Creating and Activating conda local "coffeerec" environment on Terminal: use "rc.bat"
rc.bat
2 - on Terminal and under root folder, run streamlit
streamlit run app/streamlit-app.py
2.1 - OR Docker on root folder and with Docker Desktop running
docker-compose up --build
3 - Upload to cloud
1 - data_preprocess.ipynb: Analysis and data preprocess. 2 - recommender.ipynb: Recommender using the preprocessed data.