/// <summary>
/// Runs the module.
/// </summary>
/// <param name="args">The command line arguments for the module.</param>
/// <param name="usagePrefix">The prefix to print before the usage string.</param>
/// <returns>True if the run was successful, false otherwise.</returns>
public override bool Run(string[] args, string usagePrefix)
{
string datasetFile = string.Empty;
string trainedModelFile = string.Empty;
string predictionsFile = string.Empty;
int maxRelatedItemCount = 5;
int minCommonRatingCount = 5;
int minRelatedItemPoolSize = 5;
var parser = new CommandLineParser();
parser.RegisterParameterHandler("--data", "FILE", "Dataset to make predictions for", v => datasetFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--model", "FILE", "File with trained model", v => trainedModelFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--predictions", "FILE", "File with generated predictions", v => predictionsFile = v, CommandLineParameterType.Required);
parser.RegisterParameterHandler("--max-items", "NUM", "Maximum number of related items for a single item; defaults to 5", v => maxRelatedItemCount = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--min-common-users", "NUM", "Minimum number of users that the query item and the related item should have been rated by in common; defaults to 5", v => minCommonRatingCount = v, CommandLineParameterType.Optional);
parser.RegisterParameterHandler("--min-pool-size", "NUM", "Minimum size of the related item pool for a single item; defaults to 5", v => minRelatedItemPoolSize = v, CommandLineParameterType.Optional);
if (!parser.TryParse(args, usagePrefix))
{
return(false);
}
RecommenderDataset testDataset = RecommenderDataset.Load(datasetFile);
var trainedModel = MatchboxRecommender.Load <RecommenderDataset, User, Item, RatingDistribution, DummyFeatureSource>(trainedModelFile);
var evaluator = new RecommenderEvaluator <RecommenderDataset, User, Item, int, int, RatingDistribution>(
Mappings.StarRatingRecommender.ForEvaluation());
IDictionary <Item, IEnumerable <Item> > relatedItems = evaluator.FindRelatedItemsRatedBySameUsers(
trainedModel, testDataset, maxRelatedItemCount, minCommonRatingCount, minRelatedItemPoolSize);
RecommenderPersistenceUtils.SaveRelatedItems(predictionsFile, relatedItems);
return(true);
}
/// <summary>
/// Predictions based on 10-star rating input data and features
/// </summary>
/// <param name="traitsCounts"> Number of item traits </param>
/// <returns> Metrics </returns>
public MetricValues PredictionsOnDataWithFeatures(IList <int> traitsCounts)
{
var starRatingTrainTestSplittingMapping = RecommenderMappingFactory.GetStarsMapping(true);
var binaryRatingTrainTestSplittingMapping = RecommenderMappingFactory.BinarizeMapping(starRatingTrainTestSplittingMapping);
var trainSource = SplitInstanceSource.Training(RatingsPath);
var testSource = SplitInstanceSource.Test(RatingsPath);
var binaryRatingEvaluator = new RecommenderEvaluator <SplitInstanceSource <string>, string, Movie, int, int, IDictionary <int, double> >(binaryRatingTrainTestSplittingMapping.ForEvaluation());
var starsRatingEvaluator = new RecommenderEvaluator <SplitInstanceSource <string>, string, Movie, int, int, IDictionary <int, double> >(starRatingTrainTestSplittingMapping.ForEvaluation());
var correctFractions = new Dictionary <string, double>();
var ndcgs = new Dictionary <string, double>();
var maes = new Dictionary <string, double>();
foreach (var traitCount in traitsCounts)
{
Console.WriteLine($"Running metrics calculation for data with features and a model with {traitCount} traits.");
Rand.Restart(RandomSeed);
var recommender = GetRecommender(starRatingTrainTestSplittingMapping, traitCount);
recommender.Settings.Training.UseItemFeatures = true;
recommender.Settings.Training.UseSharedUserThresholds = true;
recommender.Settings.Training.Advanced.UserThresholdPriorVariance = 10;
recommender.Train(trainSource);
var distribution = recommender.PredictDistribution(testSource);
var binarizedPredictions = BinarizePredictions(distribution);
var predictions = recommender.Predict(testSource);
var correctFraction = 1.0 - binaryRatingEvaluator.RatingPredictionMetric(testSource, binarizedPredictions, Metrics.ZeroOneError);
correctFractions.Add(traitCount.ToString(), correctFraction);
var itemRecommendationsForEvaluation = starsRatingEvaluator.RecommendRatedItems(recommender, testSource, 5, 5);
var ndcg = starsRatingEvaluator.ItemRecommendationMetric(testSource, itemRecommendationsForEvaluation, Metrics.Ndcg);
ndcgs.Add(traitCount.ToString(), ndcg);
var mae = starsRatingEvaluator.RatingPredictionMetric(testSource, predictions, Metrics.AbsoluteError);
//Divide maes by 2 to convert 10-star rating to 5-star rating
maes.Add(traitCount.ToString(), mae / 2.0);
}
return(new MetricValues(correctFractions, ndcgs, maes));
}
/// <summary>
/// Predictions based on like/dislike input data
/// </summary>
/// <param name="traitsCounts"> Number of item traits </param>
/// <returns>A tuple of probability of like and metrics </returns>
public (Dictionary <string, double[][]> likeProbability, MetricValues metricValues) PredictionsOnBinaryData(
IList <int> traitsCounts
)
{
var starRatingTrainTestSplittingMapping = RecommenderMappingFactory.GetStarsMapping(true);
var binaryRatingTrainTestSplittingMapping = RecommenderMappingFactory.BinarizeMapping(starRatingTrainTestSplittingMapping);
var trainSource = SplitInstanceSource.Training(RatingsPath);
var testSource = SplitInstanceSource.Test(RatingsPath);
var binaryRatingEvaluator = new RecommenderEvaluator <SplitInstanceSource <string>, string, Movie, int, int, IDictionary <int, double> >(binaryRatingTrainTestSplittingMapping.ForEvaluation());
var starsRatingEvaluator = new RecommenderEvaluator <SplitInstanceSource <string>, string, Movie, int, int, IDictionary <int, double> >(starRatingTrainTestSplittingMapping.ForEvaluation());
var correctFractions = new Dictionary <string, double>();
var ndcgs = new Dictionary <string, double>();
var likeProbability = new Dictionary <string, double[][]>();
foreach (var traitCount in traitsCounts)
{
Console.WriteLine($"Running metrics calculation for binarized data and a model with {traitCount} traits.");
Rand.Restart(RandomSeed);
var recommender = GetRecommender(binaryRatingTrainTestSplittingMapping, traitCount);
recommender.Settings.Training.Advanced.UserThresholdPriorVariance = EpsilonPriorVariance;
recommender.Train(trainSource);
var predictions = recommender.Predict(testSource);
likeProbability.Add(traitCount.ToString(), GetLikeProbability(recommender.PredictDistribution(testSource)));
var correctFraction = 1.0 - binaryRatingEvaluator.RatingPredictionMetric(testSource, predictions, Metrics.ZeroOneError);
correctFractions.Add(traitCount.ToString(), correctFraction);
var itemRecommendationsForEvaluation = starsRatingEvaluator.RecommendRatedItems(recommender, testSource, 5, 5);
var ndcg = starsRatingEvaluator.ItemRecommendationMetric(testSource, itemRecommendationsForEvaluation, Metrics.Ndcg);
ndcgs.Add(traitCount.ToString(), ndcg);
}
return(likeProbability, new MetricValues(correctFractions, ndcgs));
}
/// <summary>
/// Predictions based on 10-star rating input data
/// </summary>
/// <param name="traitsCounts"> Number of item traits </param>
/// <returns>A tuple of probability of thresholds posterior distributions, most probable ratings and metrics </returns>
public (Dictionary <string, IDictionary <string, Gaussian> > posteriorDistributionsOfThresholds, Dictionary <string, double[][]> mostProbableRatings, MetricValues metricValues) PredictionsOnStarRatings(
IList <int> traitsCounts
)
{
var starRatingTrainTestSplittingMapping = RecommenderMappingFactory.GetStarsMapping(true);
var binaryRatingTrainTestSplittingMapping = RecommenderMappingFactory.BinarizeMapping(starRatingTrainTestSplittingMapping);
var trainSource = SplitInstanceSource.Training(RatingsPath);
var testSource = SplitInstanceSource.Test(RatingsPath);
var binaryRatingEvaluator = new RecommenderEvaluator <SplitInstanceSource <string>, string, Movie, int, int, IDictionary <int, double> >(binaryRatingTrainTestSplittingMapping.ForEvaluation());
var starsRatingEvaluator = new RecommenderEvaluator <SplitInstanceSource <string>, string, Movie, int, int, IDictionary <int, double> >(starRatingTrainTestSplittingMapping.ForEvaluation());
var correctFractions = new Dictionary <string, double>();
var ndcgs = new Dictionary <string, double>();
var maes = new Dictionary <string, double>();
var mostProbableRatings = new Dictionary <string, double[][]>();
var posteriorDistributionsOfThresholds = new Dictionary <string, IDictionary <string, Gaussian> >();
foreach (var traitCount in traitsCounts)
{
Console.WriteLine($"Running metrics calculation for 10-star data and a model with {traitCount} traits.");
Rand.Restart(RandomSeed);
var recommender = GetRecommender(starRatingTrainTestSplittingMapping, traitCount);
recommender.Settings.Training.UseSharedUserThresholds = true;
recommender.Settings.Training.Advanced.UserThresholdPriorVariance = 10;
recommender.Train(trainSource);
var distributions = recommender.PredictDistribution(testSource);
var predictions = recommender.Predict(testSource);
mostProbableRatings.Add(traitCount.ToString(),
GetJaggedDoubles(predictions.Select(userRating =>
userRating.Value.Select(movieRating => (double)movieRating.Value))));
var posteriorDistributionOfThresholds = recommender.GetPosteriorDistributions().Users.First().Value.Thresholds.ToList();
var posteriorDistributionOfThresholdsDict = BeautifyPosteriorDistribution(posteriorDistributionOfThresholds);
posteriorDistributionsOfThresholds.Add(traitCount.ToString(), posteriorDistributionOfThresholdsDict);
var binarizedPredictions = BinarizePredictions(distributions);
var correctFraction = 1.0 - binaryRatingEvaluator.RatingPredictionMetric(testSource, binarizedPredictions, Metrics.ZeroOneError);
correctFractions.Add(traitCount.ToString(), correctFraction);
var itemRecommendationsForEvaluation = starsRatingEvaluator.RecommendRatedItems(recommender, testSource, 5, 5);
var ndcg = starsRatingEvaluator.ItemRecommendationMetric(testSource, itemRecommendationsForEvaluation, Metrics.Ndcg);
ndcgs.Add(traitCount.ToString(), ndcg);
var mae = starsRatingEvaluator.RatingPredictionMetric(testSource, predictions, Metrics.AbsoluteError);
//Divide maes by 2 to convert 10-star rating to 5-star rating
maes.Add(traitCount.ToString(), mae / 2.0);
}
return(posteriorDistributionsOfThresholds, mostProbableRatings,
new MetricValues(correctFractions, ndcgs, maes));
}