Load the movielens 1m dataset ratings file.

incremental_recommender_1.py

# load the data
col_names = ['user_id', 'movie_id', 'rating', 'timestamp']
ratings_df = pd.read_csv('/tmp/ratings.dat', delimiter='::', names=col_names, engine='python')

# transform users and movies to categorical features
ratings_df['user_id'] = ratings_df['user_id'].astype('category')
ratings_df['movie_id'] = ratings_df['movie_id'].astype('category')

# use the category codes to avoid creating separate vocabularies
ratings_df['user_code'] = ratings_df['user_id'].cat.codes.astype(int)
ratings_df['movie_code'] = ratings_df['movie_id'].cat.codes.astype(int)

ratings_df.head()