Update handler.py

handler.py

@@ -4,6 +4,35 @@ import numpy as np
 import pandas as pd
 import os
 
+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=k, replace=False) if len(recommended_books) >= k else recommended_books
+
+    def evaluate(self, test_data, k=10):
+        user_ids = test_data['user_id'].unique()
+        hit_rate, ndcg_scores = [], []
+
+        for user_id in user_ids[:100]:
+            true_books = set(test_data[test_data['user_id'] == user_id]['book_id'])
+            pred_books = set(self.predict(user_id, k))
+
+            hits = len(true_books & pred_books)
+            hit_rate.append(hits / min(k, len(true_books)))
+
+            dcg = sum(1 / math.log2(rank + 2) for rank, book in enumerate(pred_books) if book in true_books)
+            idcg = sum(1 / math.log2(i + 2) for i in range(min(k, len(true_books))))
+            ndcg = dcg / idcg if idcg > 0 else 0
+            ndcg_scores.append(ndcg)
+
+        return np.mean(hit_rate), np.mean(ndcg_scores)
+
 class EndpointHandler:
     def __init__(self, path=""):
         model_path = os.path.join(path, "model.pkl")