public void CreateSubsetEpinions()
{
int numDomains = 4;
var epinionsReader = new EpinionsCrossDomainReader(Paths.EpinionRoot + "Epinions RED");
var container = new EpinionsCrossDomainDataContainer(numDomains + 1);
epinionsReader.LoadData(container);
var output = container.Users.Values.Where(u =>
{
var counts = u.Ratings.Where(r => r.Domain.Id != "ep0").GroupBy(r => r.Domain).Select(g => g.Count());
return counts.All(c => c >= 1 && c <= 20) && (counts.Count() > 3);
})
//.Select(u => new { UserId = u.Id, Counts = u.Ratings.GroupBy(r => r.Domain.Id).Select(g => g.Count().ToString()).Aggregate((a,b) => a + " " + b) })
//.Select(a => a.UserId + "," + a.Counts);
.SelectMany(u => u.Ratings)
.GroupBy(r => r.Domain.Id)
.Select(g => g.Select(r => r.ToString())).ToList();
//.SelectMany(u => u.Ratings.GroupBy(r => r.Item.Id).Select(g => g.Take(1).Single()))
//.Select(r => r.ToString());
Console.WriteLine("Writing...");
var header = new string[] { "UserId,ItemId,Rating" };
int i = 1;
foreach (var domain in output)
{
// Format of the file: Domains{Number of Domains}-{Domain Number}
File.WriteAllLines(string.Format("{0}Epinions RED\\Domains{1}-{2}.csv", Paths.EpinionRoot, numDomains, i++), header.Concat(domain));
}
}
public void ExploreEpinionDataset()
{
var epinionReader = new EpinionsCrossDomainReader(Paths.EpinionRoot + "Epinions RED");
var container = new EpinionsCrossDomainDataContainer(2);
epinionReader.LoadData(container);
container.SpecifyTargetDomain("ep0");
//container.PrintCategoryStatistics();
container.PrintStatistics();
}
private void DomainsLoad(EpinionsCrossDomainDataContainer container)
{
int i = 0;
foreach (var file in DomainFiles)
{
container.CurrentDomain = container.Domains["ep" + i++];
foreach (string line in File.ReadAllLines(file).Skip(1))
{
var parts = line.Split(',');
container.AddRating(parts[0], parts[1], float.Parse(parts[2]), false);
}
}
}
private void NormalRead(EpinionsCrossDomainDataContainer container)
{
string reviewsPath = FolderPath + "\\Reviews.csv";
// add products
foreach (string line in File.ReadAllLines(FolderPath + "\\Products.csv").Skip(1))
{
var parts = line.Split(',');
var item = container.AddItem(parts[0]);
item.Properties["Category"] = parts[1];
}
// add reviews
foreach (string line in File.ReadAllLines(FolderPath + "\\Reviews.csv").Skip(1))
{
var parts = line.Split(',');
container.AddRating(parts[1], parts[4], float.Parse(parts[2]), false);
}
}
public void TestEpinionAllDomains(int numDomains = 3)
{
var numAuxRatings = new List<int> { 0, 1, 2, 3, 4 };
var epinionsReader = new EpinionsCrossDomainReader(Paths.EpinionRoot + "Epinions RED");
//var domainPaths = Enumerable.Range(1, numDomains)
// .Select(i => string.Format("{0}Epinions RED\\Domains{1}-{2}.csv", Paths.EpinionRoot, numDomains, i)).ToArray();
//var epinionsReader = new EpinionsCrossDomainReader(domainPaths);
var container = new EpinionsCrossDomainDataContainer(numDomains);
epinionsReader.LoadData(container);
container.Domains.Remove("ep0");
double[,] rmseMatrix = new double[numAuxRatings.Count, numDomains];
int[,] durationsMatrix = new int[numAuxRatings.Count, numDomains];
int[] numUsers = new int[numDomains];
int[] numItems = new int[numDomains];
int[] numRatings = new int[numDomains];
int domainIndex = 0;
foreach (Domain d in container.Domains.Values)
{
var targetDomain = container.SpecifyTargetDomain(d.Id);
Console.WriteLine("Target domain: {0}", d.ToString());
var splitter = new CrossDomainSimpleSplitter(container, 0.25f);
int numAuxIndex = 0;
foreach (var num in numAuxRatings)
{
var startTime = DateTime.Now;
LibFmTrainTester recommender;
CrossDomainLibFmFeatureBuilder featureBuilder = null;
if (num == 0)
{
recommender = new LibFmTrainTester(experimentId: num.ToString());
}
else
{
featureBuilder = new CrossDomainLibFmFeatureBuilder(targetDomain, num);
recommender = new LibFmTrainTester(experimentId: num.ToString(), featureBuilder: featureBuilder);
}
var ctx = new EvalutationContext<ItemRating>(recommender, splitter);
var ep = new EvaluationPipeline<ItemRating>(ctx);
ep.Evaluators.Add(new RMSE());
ep.Run();
var duration = DateTime.Now.Subtract(startTime);
rmseMatrix[numAuxIndex, domainIndex] = recommender.RMSE;
durationsMatrix[numAuxIndex, domainIndex] = (int)duration.TotalMilliseconds;
numAuxIndex++;
}
numUsers[domainIndex] = d.Ratings.Select(r => r.User.Id).Distinct().Count();
numItems[domainIndex] = d.Ratings.Select(r => r.Item.Id).Distinct().Count();
numRatings[domainIndex] = d.Ratings.Count;
domainIndex++;
}
// Write RMSEs
Console.WriteLine("\nRMSEs:\n");
string header = Enumerable.Range(1, numDomains).Select(i => "D" + i).Aggregate((a, b) => a + "\t" + b);
Console.WriteLine("Num aux. ratings\t" + header);
for (int i = 0; i < numAuxRatings.Count; i++)
{
Console.Write(numAuxRatings[i]);
for (int j = 0; j < numDomains; j++)
{
Console.Write("\t" + rmseMatrix[i, j]);
}
Console.WriteLine();
}
// Write domain statistics
string users = numUsers.Select(c => c.ToString()).Aggregate((a, b) => a + "\t" + b);
string items = numItems.Select(c => c.ToString()).Aggregate((a, b) => a + "\t" + b);
string ratings = numRatings.Select(c => c.ToString()).Aggregate((a, b) => a + "\t" + b);
Console.WriteLine();
Console.WriteLine("Num Users\t" + users);
Console.WriteLine("Num Items\t" + items);
Console.WriteLine("Num Ratings\t" + ratings);
// Write times
Console.WriteLine("\nTimes:\n");
header = Enumerable.Range(1, numDomains).Select(i => "T" + i).Aggregate((a, b) => a + "\t" + b);
Console.WriteLine("Num aux. ratings\t" + header);
for (int i = 0; i < numAuxRatings.Count; i++)
{
Console.Write(numAuxRatings[i]);
for (int j = 0; j < numDomains; j++)
{
Console.Write("\t" + durationsMatrix[i, j]);
}
Console.WriteLine();
}
Console.WriteLine("\n");
}