使用模型

通過以下步驟在Controller中使用訓練的模型。

1. 建立ML.NET環境並載入已經訓練過的模型

   // 1. Create the ML.NET environment and load the MoviesRecommendation Model
   var ctx = new MLContext();
            
   ITransformer loadedModel;
   using (var stream = new FileStream(_movieService.GetModelPath(), FileMode.Open, FileAccess.Read, FileShare.Read))
   {
   loadedModel = ctx.Model.Load(stream);
   }

2. 建立預測函式以預測一組電影推薦

   //3. Create a prediction function
   var predictionfunction = loadedModel.MakePredictionFunction<RatingData, RatingPrediction>(ctx);
            
   List<Tuple<int, float>> ratings = new List<Tuple<int, float>>();
   List<Tuple<int, int>> MovieRatings = _profileService.GetProfileWatchedMovies(id);
   List<Movie> WatchedMovies = new List<Movie>();

   foreach (Tuple<int, int> tuple in MovieRatings)
   {
   WatchedMovies.Add(_movieService.Get(tuple.Item1));
   }
   
   RatingPrediction prediction = null;
   
   foreach (var movie in _movieService._trendingMovies)
   {
   // Call the Rating Prediction for each movie prediction
      prediction = predictionfunction.Predict(new RatingData { userId = id.ToString(), movieId = movie.MovieID.ToString()});
              
   // Normalize the prediction scores for the "ratings" b/w 0 - 100
      var normalizedscore = Sigmoid(prediction.Score);

   // Add the score for recommendation of each movie in the trending movie list
      ratings.Add(Tuple.Create(movie.MovieID, normalizedscore));
   }

3. 為要顯示的檢視提供評分預測

   ViewData["watchedmovies"] = WatchedMovies;
   ViewData["ratings"] = ratings;
   ViewData["trendingmovies"] = _movieService._trendingMovies;
   return View(activeprofile);

替代方法

這個示例顯示了許多可以用於ML.NET的推薦方法之一。根據您的特定場景，您可以選擇以下任何最適合您的用例的方法。