public void ScorePropertyOk()
{
MovieRatingPrediction aMovieRatingPrediction = new MovieRatingPrediction();
float score = 4.5f;
aMovieRatingPrediction.Score = score;
Assert.AreEqual(aMovieRatingPrediction.Score, score);
}
public void LabelPropertyOk()
{
MovieRatingPrediction aMovieRatingPrediction = new MovieRatingPrediction();
float label = 1;
aMovieRatingPrediction.Label = label;
Assert.AreEqual(aMovieRatingPrediction.Label, label);
}
public float PredictScore(int userId, int movieId)
{
MovieRating movieRating = new MovieRating
{
userId = userId,
movieId = movieId
};
MovieRatingPrediction prediction = _predictionEnginePool.Predict(modelName: "MovieRatingAnalysisModel", example: movieRating);
return(prediction.Score);
}
public static void DisplayPrediction(MovieRating example, MovieRatingPrediction prediction)
{
if (prediction == null)
{
Console.WriteLine("Task 5 \"Predict\" not completed.\n");
}
else
{
Console.WriteLine("The predicted score of user " + example.userId + " for the movie " + example.movieId + " is: " + Math.Round(prediction.Score, 1) + "\n");
}
}
public ActionResult Recommend(int id)
{
var activeprofile = _profileService.GetProfileByID(id);
// 1. Create the ML.NET environment and load the already trained model
MLContext mlContext = new MLContext();
ITransformer trainedModel;
using (FileStream stream = new FileStream(_movieService.GetModelPath(), FileMode.Open, FileAccess.Read, FileShare.Read))
{
trainedModel = mlContext.Model.Load(stream);
}
//2. Create a prediction function
var predictionEngine = trainedModel.CreatePredictionEngine <MovieRating, MovieRatingPrediction>(mlContext);
List <(int movieId, float normalizedScore)> ratings = new List <(int movieId, float normalizedScore)>();
var MovieRatings = _profileService.GetProfileWatchedMovies(id);
List <Movie> WatchedMovies = new List <Movie>();
foreach ((int movieId, int movieRating) in MovieRatings)
{
WatchedMovies.Add(_movieService.Get(movieId));
}
MovieRatingPrediction prediction = null;
foreach (var movie in _movieService.GetTrendingMovies)
{
// Call the Rating Prediction for each movie prediction
prediction = predictionEngine.Predict(new MovieRating
{
userId = id.ToString(),
movieId = movie.MovieID.ToString()
});
// Normalize the prediction scores for the "ratings" b/w 0 - 100
float normalizedscore = Sigmoid(prediction.Score);
// Add the score for recommendation of each movie in the trending movie list
ratings.Add((movie.MovieID, normalizedscore));
}
//3. Provide rating predictions to the view to be displayed
ViewData["watchedmovies"] = WatchedMovies;
ViewData["ratings"] = ratings;
ViewData["trendingmovies"] = _movieService.GetTrendingMovies;
return(View(activeprofile));
}
public async Task <ActionResult <IEnumerable <MovieVM> > > RecommendMovies(int userId)
{
var reviews = await _context.Reviews.ToListAsync();
// Lấy id của những phim mà user đã đánh giá
var ratedIds = reviews.Where(r => r.AccountId == userId).Select(r => r.MovieId).ToList();
if (ratedIds.Count == 0)
{
return(NoContent());
}
// Sử dụng model để dự đoán rating của userId lên một số phim
var recommendedMovies = new List <Movie>();
MovieRatingPrediction prediction = null;
foreach (var movie in _context.Movies.OrderBy(x => Guid.NewGuid()).ToList())
{
movie.Reviews = null;
if (ratedIds.Contains(movie.Id))
{
continue;
}
prediction = _model.Predict(new MovieRating
{
userId = userId,
movieId = movie.Id
});
if (prediction.Score >= 7)
{
recommendedMovies.Add(movie);
}
// Chỉ recommend 6 phim
if (recommendedMovies.Count == 6)
{
break;
}
}
return(recommendedMovies.Select(m => new MovieVM()
{
Movie = m, Ratings = AvgRatingsAsync(reviews.Where(r => r.MovieId == m.Id).ToList())
}).ToList());
}
public ActionResult Recommend(int id)
{
var activeprofile = _profileService.GetProfileByID(id);
// 1. Create the ML.NET environment and load the already trained model
MLContext mlContext = new MLContext();
List <(int movieId, float normalizedScore)> ratings = new List <(int movieId, float normalizedScore)>();
var MovieRatings = _profileService.GetProfileWatchedMovies(id);
List <Movie> WatchedMovies = new List <Movie>();
foreach ((int movieId, int movieRating) in MovieRatings)
{
WatchedMovies.Add(_movieService.Get(movieId));
}
MovieRatingPrediction prediction = null;
foreach (var movie in _movieService.GetTrendingMovies)
{
// Call the Rating Prediction for each movie prediction
prediction = _model.Predict(new MovieRating
{
userId = id.ToString(),
movieId = movie.MovieID.ToString()
});
// Normalize the prediction scores for the "ratings" b/w 0 - 100
float normalizedscore = Sigmoid(prediction.Score);
// Add the score for recommendation of each movie in the trending movie list
ratings.Add((movie.MovieID, normalizedscore));
}
//3. Provide rating predictions to the view to be displayed
ViewData["watchedmovies"] = WatchedMovies;
ViewData["ratings"] = ratings;
ViewData["trendingmovies"] = _movieService.GetTrendingMovies;
return(View(activeprofile));
}
public void InstanceOk()
{
MovieRatingPrediction aMovieRatingPrediction = new MovieRatingPrediction();
Assert.IsNotNull(aMovieRatingPrediction);
}
