Simple Recommender System Using Scikit Surprise

Prequisites

• Ensure you have Python v3.6 or later
• Install the required dependencies present in the requirements.txt

How To Setup Project

• Download the Digital_Software_V1 Dataset
• Place the dataset amazon_reviews_us_Digital_Software_v1_00.tsv in the resources > dataset directory
• Navigate inside therecommenders directory.
• Run the svd_trainer.py & knn_trainer.py files to train the required Models. (This process will be improved later).
• The models should be present in the resources > models directory.
• Once the model has been generated, return to the root of the Project.
• Execute the following command to run the web application:

$ streamlit run main.py 

• The application should be accessible via the url http://localhost:8501

References

• https://surprise.readthedocs.io/en/stable/index.html
• https://www.youtube.com/watch?v=fEd1p8-3S7w&t=1176s
• https://hackernoon.com/introduction-to-recommender-system-part-1-collaborative-filtering-singular-value-decomposition-44c9659c5e75