我有一个关于在推荐系统中使用皮尔森相关系数的问题 .
我目前在我的数据库中有3个集合 . 1表示用户,1表示餐馆,1表示评论 .
我编写了一个函数,它接受2个用户ID及其提交的评论列表,并返回一个double,这是两个用户之间基于他们提交的评论的皮尔森相关系数 .
因此,该功能的作用是制作用户提交的所有评论的2个列表 . 然后for循环检查他们是否有评论留在同一家餐馆,并将这些评论放在一个列表中 . 该列表用于计算系数 .
我只是想知道我是否正确使用这个系数 . 我想向第一个用户提供建议 . 我可以使用此系数作为适合其他用户的人的良好指标吗?
如果它不是匹配用户的好方法,那么更好的方法是什么?
如果有人想知道,这是我计算系数的函数 .
public static double CalculatePearsonCorrelation(Guid userId1, List<Review> user1Reviews,
Guid userId2, List<Review> user2Reviews)
{
//Resetting the dictionary
restaurantRecommendations = new Dictionary<Guid, List<Review>>();
//Matching the reviews with the corresponding user
restaurantRecommendations.Add(userId1, user1Reviews);
restaurantRecommendations.Add(userId2, user2Reviews);
//Check if users have enough reviews to get a correct correlation
if (restaurantRecommendations[userId1].Count < 4)
throw new NotEnoughReviewsException("UserId " + userId1 + " doesn't contain enough reviews for this correlation");
if (restaurantRecommendations[userId2].Count < 4)
throw new NotEnoughReviewsException("UserId " + userId2 + " doesn't contain enough reviews for this correlation");
//This will be the list of reviews that are the same per subject for the two users.
List<Review> shared_items = new List<Review>();
//Loops through the list of reviews of the selected user (userId1)
foreach (var item in restaurantRecommendations[userId1])
{
//Checks if they have any reviews on subjects in common
if (restaurantRecommendations[userId2].Where(x => x.subj.Id == item.subj.Id).Count() != 0)
{
//Adds these reviews to a list on which the correlation will be based
shared_items.Add(item);
}
}
//If they don't have anything in common, the correlation will be 0
if (shared_items.Count() == 0)
return 0;
//I decided users need at least 4 subjects in common, else there won't be an accurate correlation
if (shared_items.Count() < 4)
throw new NotEnoughReviewsException("UserId " + userId1 + " and UserId " + userId2 + " don't have enough reviews in common for a correlation");
////////////////////////// Calculating the pearson correlation //////////////////////////
double product1_review_sum = 0.00f;
double product2_review_sum = 0.00f;
double product1_rating = 0f;
double product2_rating = 0f;
double critics_sum = 0f;
foreach (Review item in shared_items)
{
product1_review_sum += restaurantRecommendations[userId1].Where(x => x.subj.Id == item.subj.Id).FirstOrDefault().rating;
product2_review_sum += restaurantRecommendations[userId2].Where(x => x.subj.Id == item.subj.Id).FirstOrDefault().rating;
product1_rating += Math.Pow(restaurantRecommendations[userId1].Where(x => x.subj.Id == item.subj.Id).FirstOrDefault().rating, 2);
product2_rating += Math.Pow(restaurantRecommendations[userId2].Where(x => x.subj.Id == item.subj.Id).FirstOrDefault().rating, 2);
critics_sum += restaurantRecommendations[userId1].Where(x => x.subj.Id == item.subj.Id).FirstOrDefault().rating *
restaurantRecommendations[userId2].Where(x => x.subj.Id == item.subj.Id).FirstOrDefault().rating;
}
//Calculate pearson correlation
double num = critics_sum - (product1_review_sum * product2_review_sum / shared_items.Count);
double density = Math.Sqrt((product1_rating - Math.Pow(product1_review_sum, 2) / shared_items.Count) *
((product2_rating - Math.Pow(product2_review_sum, 2) / shared_items.Count)));
if (density == 0)
return 0;
return num / density;
}
}