File size: 2,401 Bytes
8b64cdc 0448345 97be00a 2b8cf41 8b64cdc 97be00a 8b64cdc 97be00a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
from typing import Dict, List, Any
import pickle
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")
with open(model_path, 'rb') as f:
self.model = pickle.load(f)
def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
"""
data args:
user_id (:obj: `str` or `int`)
k (:obj: `int`, optional)
Return:
A :obj:`list` of :obj:`dict`: will be serialized and returned
"""
user_id = data.pop("user_id", None)
k = data.pop("k", 10) # Default to 10 if not provided
if user_id is None:
return [{"error": "user_id is required"}]
try:
recommended_books = self.model.predict(user_id, k=k)
return [{"recommended_books": recommended_books.tolist()}]
except Exception as e:
return [{"error": str(e)}]
def load_model(model_path):
handler = EndpointHandler(model_path)
return handler |