Building and Testing Recommender Systems With Surprise, Step-By-Step

The book was rated by 47 users, user “26544” rated 10, our BaselineOnly algorithm predicts this user would rate 0.import matplotlib.pyplot as plt%matplotlib notebookdf_new.loc[df_new['ISBN'] == '055358264X']['bookRating'].hist()plt.xlabel('rating')plt.ylabel('Number of ratings')plt.title('Number of ratings book ISBN 055358264X has received');Figure 13It turns out, most of the ratings this book received was 0, in another word, most of the users in the data rated this book 0, only very few users rated 10..Same with the other predictions in “worst predictions” list..It seems that for each prediction, the users are some kind of outsiders.That was it!.I hope you enjoyed the recommendation (or rather, a rating prediction) journey with Surprise..Jupyter notebook can be found on Github..Happy Holidays!Reference: Surprise’ documentation. More details

Leave a Reply