This is another example of code used for recommending films, based on distance algorithm, and can be used for cheating in your Data Science homeworks
Thanks again to a Kaggle dataset: https://www.kaggle.com/c/movie/data,
Before starting: get the training_ratings_for_kaggle_comp.csv and the movies.dat files and paste them on your local environment
For practising you have some parameters you can modify on the constant.py file:
- NUM_OF_ROWS_RATING = 1000 -> don't overstress your computer getting so much values from the rating file
- USER = int(2788) -> User Id we want to recommend to
- RECOMMENDER_TYPE = 'D' -> By Now it is D: distance, and C: cosaine
- ELEVATED = 2 -> Elevation factor for distance calculation -> 1 Manhattan, 2 Euclidian, ....
Code description will appear soon on www.blog.dataontheroad.com For doubts about the code you can write me at jimenezict@gmail.com
Enjoy!
Pearson will be available soon. Don't worry for dirty code, also will be refactor