static void Main(string[] args)
{
Console.WriteLine("Restaurants recommender");
MLContext mlContext = new MLContext(0);
var trainingDataFile = "Data\\trainingData.tsv";
DataPreparer.PreprocessData(trainingDataFile);
IDataView trainingDataView = mlContext
.Data
.LoadFromTextFile <ModelInput>
(trainingDataFile, hasHeader: true);
var dataProcessingPipeline =
mlContext
.Transforms
.Conversion
.MapValueToKey(outputColumnName: "UserIdEncoded",
inputColumnName: nameof(ModelInput.UserId))
.Append(mlContext
.Transforms
.Conversion
.MapValueToKey(outputColumnName: "RestaurantNameEncoded",
inputColumnName: nameof(ModelInput.RestaurantName)));
var finalOptions = new MatrixFactorizationTrainer.Options
{
MatrixColumnIndexColumnName = "UserIdEncoded",
MatrixRowIndexColumnName = "RestaurantNameEncoded",
LabelColumnName = "TotalRating",
NumberOfIterations = 10,
ApproximationRank = 200,
Quiet = true
};
var trainer = mlContext.Recommendation().Trainers.MatrixFactorization(finalOptions);
var trainingPipeLine = dataProcessingPipeline.Append(trainer);
Console.WriteLine("Training model");
var model = trainingPipeLine.Fit(trainingDataView);
// View results
var testUserId = "U1134";
var predictionEngine = mlContext
.Model
.CreatePredictionEngine <ModelInput, ModelOutput>(model);
var alreadyRatedRestaurants =
mlContext
.Data
.CreateEnumerable <ModelInput>(trainingDataView, false)
.Where(i => i.UserId == testUserId)
.Select(r => r.RestaurantName)
.Distinct();
var allRestaurantNames = trainingDataView
.GetColumn <string>("RestaurantName")
.Distinct()
.Where(r => !alreadyRatedRestaurants.Contains(r));
var scoredRestaurants =
allRestaurantNames.Select(restName =>
{
var prediction = predictionEngine.Predict(
new ModelInput()
{
RestaurantName = restName,
UserId = testUserId
});
return(RestaurantName: restName, PredictedRating: prediction.Score);
});
var top10Restaurants = scoredRestaurants
.OrderByDescending(s => s.PredictedRating)
.Take(10);
Console.WriteLine();
Console.WriteLine($"Top 10 restaurants for {testUserId}");
Console.WriteLine($"----------------------------");
foreach (var input in top10Restaurants)
{
Console.WriteLine($"Predicted rating [{input.PredictedRating:#.0}] for restaurant: '{input.RestaurantName}'");
}
}
static void Main(string[] args)
{
Console.WriteLine("Restaurants recommender");
MLContext mlContext = new MLContext(0);
var trainingDataFile = "Data\\trainingData.tsv";
DataPreparer.PreprocessData(trainingDataFile);
IDataView trainingDataView = mlContext
.Data
.LoadFromTextFile <ModelInput>
(trainingDataFile, hasHeader: true);
var dataProcessingPipeline =
mlContext
.Transforms
.Conversion
.MapValueToKey(outputColumnName: "UserIdEncoded",
inputColumnName: nameof(ModelInput.UserId))
.Append(mlContext
.Transforms
.Conversion
.MapValueToKey(outputColumnName: "RestaurantNameEncoded",
inputColumnName: nameof(ModelInput.RestaurantName)));
var finalOptions = new MatrixFactorizationTrainer.Options
{
MatrixColumnIndexColumnName = "UserIdEncoded",
MatrixRowIndexColumnName = "RestaurantNameEncoded",
LabelColumnName = "TotalRating",
NumberOfIterations = 10,
ApproximationRank = 200,
Quiet = true
};
var trainer = mlContext.Recommendation().Trainers.MatrixFactorization(finalOptions);
var trainingPipeLine = dataProcessingPipeline.Append(trainer);
Console.WriteLine("Training model");
var model = trainingPipeLine.Fit(trainingDataView);
//// View results
//var testUserId = "U1134";
var predictionEngine = mlContext
.Model
.CreatePredictionEngine <ModelInput, ModelOutput>(model);
//var alreadyRatedRestaurants =
// mlContext
// .Data
// .CreateEnumerable<ModelInput>(trainingDataView, false)
// .Where(i => i.UserId == testUserId)
// .Select(r => r.RestaurantName)
// .Distinct();
//var allRestaurantNames = trainingDataView
// .GetColumn<string>("RestaurantName")
// .Distinct()
// .Where(r => !alreadyRatedRestaurants.Contains(r));
//var scoredRestaurants =
// allRestaurantNames.Select(restName =>
// {
// var prediction = predictionEngine.Predict(
// new ModelInput()
// {
// RestaurantName = restName,
// UserId = testUserId
// });
// return (RestaurantName: restName, PredictedRating: prediction.Score);
// });
//var top10Restaurants = scoredRestaurants
// .OrderByDescending(s => s.PredictedRating)
// .Take(10);
//Console.WriteLine();
//Console.WriteLine($"Top 10 restaurants for {testUserId}");
//Console.WriteLine($"----------------------------");
//foreach (var input in top10Restaurants)
//{
// Console.WriteLine($"Predicted rating [{input.PredictedRating:#.0}] for restaurant: '{input.RestaurantName}'");
//}
var crossValMetrics = mlContext.Recommendation()
.CrossValidate(data: trainingDataView,
estimator: trainingPipeLine,
labelColumnName: "TotalRating"
);
var averageRMSE = crossValMetrics.Average(m => m.Metrics.RootMeanSquaredError);
var averageRSquared = crossValMetrics.Average(m => m.Metrics.RSquared);
Console.WriteLine();
Console.WriteLine($"--- Metrics before tuning hyper parameters ---");
Console.WriteLine($"Cross validated root mean square error: {averageRMSE:#.000}");
Console.WriteLine($"Cross validated RSquared: {averageRSquared:#.000}");
Console.WriteLine();
//HyperParameterExploration(mlContext, dataProcessingPipeline, trainingDataView);
var prediction = predictionEngine.Predict(
new ModelInput()
{
UserId = "CLONED",
RestaurantName = "Restaurant Wu Zhuo Yi"
});
Console.WriteLine($"Predicted: {prediction.Score:#.0} for 'Restaurant Wu Zhuo Yi'");
}