| import numpy as np | |
| import pandas as pd | |
| class ContentBasedRecommender: | |
| def __init__(self, train_data): | |
| self.train_data = train_data | |
| def predict(self, user_id, k=10): | |
| user_books = set(self.train_data[self.train_data['user_id'] == user_id]['book_id']) | |
| similar_books = set().union(*(self.train_data[self.train_data['book_id'] == book_id]['similar_books'].iloc[0] for book_id in user_books)) | |
| recommended_books = list(similar_books - user_books) | |
| return np.random.choice(recommended_books, size=min(k, len(recommended_books)), replace=False).tolist() | |