25M Movielens recommendation system with the use of Pearson Correlation
You can download the MovieLens 25M dataset (https://grouplens.org/datasets/movielens/)
- creating_database.ipynb: handles the creation of database for all necessary data.
- preprocessing.ipynb: Manipulates, calculates, extracts, and combines important features to make it easy and quick to access.
- Recommendation_detailed.ipynb: Handles the recommendation part using Pearson similarity to find similar user tastes.
- movie_time_analysis.ipynb: General visualizations of data.
Run the following command in the project terminal:
streamlit run main.py