我在尝试使用Django框架实现一个群体推荐系统，并使用LensKit的Python工具（具体来说是使用UserUser算法的Recommender对象）。然而，它只在某些情况下（对于特定用户）返回个性化推荐，但对于用户组总是能返回推荐（我创建了一个混合用户，其评分是组内成员评分的平均值，并为其请求推荐）。下面是我请求个别用户和用户组推荐的实现代码：

from rest_framework import viewsets, statusfrom .models import Movie, Rating, Customer, Recommendationfrom .serializers import MovieSerializer, RatingSerializer, UserSerializer, GroupSerializer, CustomerSerializer, RecommendationSerializerfrom rest_framework.response import Responsefrom rest_framework.decorators import actionfrom django.contrib.auth.models import User, Groupfrom rest_framework.authentication import TokenAuthenticationfrom rest_framework.permissions import IsAuthenticated, AllowAnyfrom pandas import Seriesfrom lenskit.algorithms import Recommenderfrom lenskit.algorithms.user_knn import UserUserimport lenskit.datasets as dsclass CustomerViewSet(viewsets.ModelViewSet):    queryset = Customer.objects.all()    serializer_class = CustomerSerializer    authentication_classes = (TokenAuthentication,)    permission_classes = (IsAuthenticated,)@action(methods=['GET'], detail=False)    def recommendations(self, request):        if 'genre' in request.data:            genre = request.data['genre']        else:            genre = 'All'        user = request.user        ratings = Rating.objects.filter(user=user.id)        user_dict = {} #用户评分字典        name = user.username        #print('name', name)        #删除之前请求生成的推荐结果，然后生成新的        Recommendation.objects.filter(name=name).delete()        for rating in ratings:            stars = rating.stars            movieId = int(rating.movie.movieId)            user_dict[movieId] = stars        #print(user_dict)        data = ds.MovieLens('datasets/')        user_user = UserUser(15, min_nbrs=3)        algo = Recommender.adapt(user_user)        algo.fit(data.ratings)        #print(algo)        #print(data.ratings)        """        基于不在训练集中的用户（因此，他们的id为-1），以及从评分字典中获取的pandas.Series来生成推荐。        """        recs = algo.recommend(user=-1, ratings=Series(user_dict))        #print(recs)        #解析结果DataFrame，并将推荐保存为对象        for index, row in recs.iterrows():            #print(row['item'])            movieId = row['item']            stars = row['score']            if genre == 'All':                Recommendation.objects.create(name=name, movieId=movieId, pred_stars=stars)            if genre != 'All' and genre in movie.genres:                Recommendation.objects.create(name=name, movieId=movieId, pred_stars=stars)            #在推荐20个项目时停止            count = Recommendation.objects.filter(name=name).count()            #print('count', count)            if count >= 20:                break        #返回按预测评分排序的电影        recs = Recommendation.objects.filter(name=name).order_by('-pred_stars')        rec_movies = []        for rec in recs:            mov = Movie.objects.get(movieId=rec.movieId)            rec_movies.append(mov)        serializer = MovieSerializer(rec_movies, many=True)        return Response(serializer.data, status=status.HTTP_200_OK)class GroupViewSet(viewsets.ModelViewSet):    queryset = Group.objects.all()    serializer_class = GroupSerializer    authentication_classes = (TokenAuthentication,)    permission_classes = (IsAuthenticated, )    @action(methods=['GET'], detail=True)    def recommendations(self, request, pk=None):        if 'genre' in request.data:            genre = request.data['genre']        else:            genre = 'All'        #检查用户是否属于该组        group = Group.objects.get(id=pk)        users = group.user_set.all()        #print(users)        user = request.user        #print(user)        if user in users:            #删除之前请求生成的推荐结果，然后生成新的            Recommendation.objects.filter(name=group.name).delete()            rating_dict = {} #组平均评分字典            for user in users:                ratings = Rating.objects.filter(user=user.id)                for rating in ratings:                    stars = rating.stars                    movieId = int(rating.movie.movieId)                    """                    如果电影已被其他成员评分（即字典中存在该电影的评分），则计算平均评分                    """                    if movieId in rating_dict:                        x = rating_dict[movieId][0]                        y = rating_dict[movieId][1]                        x = (x * y + stars) / (y+1)                        y += 1                        rating_dict[movieId][0] = x                        rating_dict[movieId][1] = y                    #如果没有，则直接将个人评分插入字典                    else:                        rating_dict[movieId] = [stars, 1]            #训练机器学习算法            data = ds.MovieLens('datasets/')            user_user = UserUser(15, min_nbrs=3)            algo = Recommender.adapt(user_user)            algo.fit(data.ratings)            for key in rating_dict.keys():                x = rating_dict[key][0]                rating_dict[key] = x            #print(rating_dict)            #请求混合用户的推荐            recs = algo.recommend(user=-1, ratings=Series(rating_dict))            #print(recs)            genre = request.data['genre']            name = group.name            #解析结果DataFrame，并将推荐保存为对象            for index, row in recs.iterrows():                print(row['item'])                movie = Movie.objects.get(movieId=str(int(row['item'])))                stars = row['score']                name = group.name                if genre == 'All':                    Recommendation.objects.create(name=name, movieId=movie.movieId, pred_stars=stars)                if genre != 'All' and genre in movie.genres:                    Recommendation.objects.create(name=name, movieId=movie.movieId, pred_stars=stars)                #在推荐20个项目时停止                count = Recommendation.objects.filter(name=name).count()                print('count', count)                if count >= 20:                    break            #返回按预测评分排序的组电影            recs = Recommendation.objects.filter(name=name).order_by('-pred_stars')            rec_movies = []            for rec in recs:                mov = Movie.objects.get(movieId=rec.movieId)                rec_movies.append(mov)            serializer = MovieSerializer(rec_movies, many=True)            return Response(serializer.data, status=status.HTTP_200_OK)        else:            response = {'message': '您不是该组的成员'}            return Response(response, status=status.HTTP_400_BAD_REQUEST)

这里是一个工作响应的示例：

[    {        "id": 17521,        "movieId": "318",        "title": "肖申克的救赎 (1994)",        "genres": "犯罪|戏剧",        "link": "https://www.imdb.com/title/tt0111161/",        "average_rating": 4.487138263665595,        "no_ratings": 311,        "poster": "/default-movie.jpg"    },    {        "id": 17503,        "movieId": "296",        "title": "低俗小说 (1994)",        "genres": "喜剧|犯罪|戏剧|惊悚",        "link": "https://www.imdb.com/title/tt0110912/",        "average_rating": 4.256172839506172,        "no_ratings": 324,        "poster": "/default-movie.jpg"    },    ...]

一个不工作的响应：

[]

在后一种情况下，打印Recommender返回的DataFrame显示如下：

空DataFrame列: [item, score]索引: []

我不确定我做错了什么。谁能帮帮我？

回答：

这个问题最可能的原因是用户-用户推荐系统无法构建足够的可行邻域来提供推荐。这是基于邻域的推荐的一个缺点。

解决方案是切换到一种总是能为有某些评分的用户推荐的算法（例如，矩阵分解算法中的一种），和/或使用一个后备算法，如Popular，在个性化协同过滤无法推荐时使用。

（另一种解决方案是为LensKit实现各种冷启动推荐器或基于内容的推荐器之一，但目前项目中没有提供这些。）