#匯入相關的庫檔案
import os
from surprise import Dataset
from surprise import Reader
from surprise import SVD
from surprise import accuracy
from surprise.model_selection import train_test_split
from surprise import evaluate, print_perf

##讀取資料
#指定檔案的路徑
file_path = os.path.expanduser('ml-100k/u.data')
#告訴文字閱讀器，文字的格式是什麼樣子的
 

reader = Reader(line_format='user item rating timestamp', sep='\t')
#載入資料
data = Dataset.load_from_file(file_path, reader=reader)

# testset佔比25%.
#trainset, testset = train_test_split(data, test_size=.25)
trainset = data.build_full_trainset()
#這裡使用SVD演算法,也可以使用其他的演算法
algo = SVD()
# 在trainset上進行模型的訓練, 在testset進行預測
 

algo.fit(trainset)
#進行預測
testset = trainset.build_anti_testset()  #這裡的testset是trainset中 rui為0的（user, item， 0）
predictions = algo.test(testset)
# Then compute RMSE
accuracy.rmse(predictions)

RMSE: 0.6043
0.6042835704959628

from collections import defaultdict       #defaultdict是一個字典，當key不存在時，會返回預設值
#從一個prediction集合中返回每個 user Top-N推薦
 

def get_top_n(predictions, n = 10):
    '''從一個prediction集合中返回每個 user Top-N推薦
    Args:
        predictions(list of Prediction objects): The list of predictions, as
            returned by the test method of an algorithm.
        n(int): The number of recommendation to output for each user. Default
            is 10.
    Returns:
    A dict where keys are user (raw) ids and values are lists of tuples:
        [(raw item id, rating estimation), ...] of size n.
    '''
    #首先將prediction對映到每個user上
    top_n = defaultdict(list)
    for uid, iid, true_r, est, _ in predictions:
        top_n[uid].append((iid, est))
    #再對每個user的item按照評分進行排序
    for uid, user_ratings in top_n.items():
        user_ratings.sort(key = lambda x : x[1], reverse = True)
        top_n[uid] = user_ratings[:n]   #取前n個
    return top_n

get_top_n(predictions, n = 10)

#計算查準率 [email protected] and 和查全率 [email protected]