public static AffiliateReaderBase GetAppropriateReader(AffiliateFile file)
{
AffiliateReaderBase reader;
switch (file.Name)
{
case "Bol": reader = new BolReader(); break;
case "Affilinet": reader = new AffilinetReader(); break;
case "Belboon": reader = new BelboonReader(); break;
case "CommissionJunction": reader = new CommissionJunctionReader(); break;
case "Daisycon": reader = new DaisyconReader(); break;
case "TradeDoubler": reader = new TradeDoublerReader(); break;
case "TradeTracker": reader = new TradeTrackerReader(); break;
case "Webgains": reader = new WebgainsReader(); break;
case "Zanox": reader = new ZanoxReader(); break;
case "BorderBot": reader = new BorderBotReader(); break;
case "Wehkamp": reader = new WehkampReader(); break;
case "AffiliateWindow": reader = new AffiliateWindowReader(); break;
case "Effiliation": reader = new EffiliationLecteur(); break;
case "LDLC": reader = new LDLCReader(); break;
case "Linkshare": reader = new LinkshareReader(); break;
case "Rene\'s Toppertjes": reader = new RenesToppertjesReader(); break;
case "JacobElektronik": reader = new JacobElektronikReader(); break;
case "PepperjamNetwork": reader = new PepperjamNetworkReader(); break;
case "Amazon": reader = new AmazonReader(); break;
default: reader = null; break;
}
return reader;
}
public void TestNmfClusting()
{
var reader = new AmazonReader(Paths.AmazonBooksRatings);
var dataset = new Dataset <ItemRating>(reader);
var clusterer = new Clusterer(dataset);
clusterer.ClusterNmf(5, Paths.AmazonBooksUsersCluster);
}
public void CreateClustersAmazon()
{
var reader = new AmazonReader(Paths.AmazonMusicRatings);
var dataset = new Dataset <ItemRating>(reader);
var clusterer = new Clusterer(dataset);
for (int i = 14; i < 15; i += 2)
{
clusterer.WriteUsersCluster(Paths.AmazonMusicUsersCluster + i + ".csv", i, 5);
clusterer.WriteItemsCluster(Paths.AmazonMusicItemsCluster + i + ".csv", i, 5);
}
}
public void CreateClustersAmazon()
{
var reader = new AmazonReader(Paths.AmazonMusicRatings);
var dataset = new Dataset<ItemRating>(reader);
var clusterer = new Clusterer(dataset);
for (int i = 14; i < 15; i += 2)
{
clusterer.WriteUsersCluster(Paths.AmazonMusicUsersCluster + i + ".csv", i, 5);
clusterer.WriteItemsCluster(Paths.AmazonMusicItemsCluster + i + ".csv", i, 5);
}
}
public void TestAmazonWithClusters()
{
// Todo: instead of loading the dataset every time add a updateCluster method to the Dataset<ItemRatingWithCluster>
List <string> rmses = new List <string>();
List <string> maes = new List <string>();
for (int i = 2; i < 13; i += 2)
{
string usersClusterFile = Paths.AmazonMusicUsersCluster + i + ".csv";
string itemsClusterFile = Paths.AmazonMusicItemsCluster + i + ".csv";
AmazonReader trainReader, testReader;
if (i == 0)
{
trainReader = new AmazonReader(Paths.AmazonMusicTrain75);
testReader = new AmazonReader(Paths.AmazonMusicTest25);
}
else
{
trainReader = new AmazonReader(Paths.AmazonMusicTrain75, usersClusterFile, itemsClusterFile, "b", true);
testReader = new AmazonReader(Paths.AmazonMusicTest25, usersClusterFile, itemsClusterFile, "b", true);
}
var dataset = new Dataset <ItemRatingWithClusters>(trainReader, testReader);
var recommender = new LibFmTrainTester(i.ToString());
var context = new EvalutationContext <ItemRating>(recommender, dataset);
var ep = new EvaluationPipeline <ItemRating>(context);
ep.Evaluators.Add(new RMSE());
ep.Evaluators.Add(new MAE());
ep.Run();
rmses.Add(context["RMSE"].ToString());
maes.Add(context["MAE"].ToString());
}
Console.WriteLine("RMSEs--------------");
rmses.ForEach(Console.WriteLine);
Console.WriteLine("MAEs-------------");
maes.ForEach(Console.WriteLine);
}
public void TestAmazonWithNmfCluster()
{
var trainReader = new AmazonReader(Paths.AmazonBooksTrain75, Paths.AmazonBooksUsersCluster + ".nmf.u", Paths.AmazonBooksUsersCluster + ".nmf.i");
var testReader = new AmazonReader(Paths.AmazonBooksTest25, Paths.AmazonBooksUsersCluster + ".nmf.u", Paths.AmazonBooksUsersCluster + ".nmf.i");
var dataset = new Dataset <ItemRatingWithClusters>(trainReader, testReader);
var recommender = new LibFmTrainTester();
var context = new EvalutationContext <ItemRating>(recommender, dataset);
var ep = new EvaluationPipeline <ItemRating>(context);
ep.Evaluators.Add(new RMSE());
ep.Evaluators.Add(new MAE());
ep.Run();
}
public void CreateNmfClustersAmazon()
{
var reader = new AmazonReader(Paths.AmazonBooksRatings);
var dataset = new Dataset <ItemRating>(reader);
var userMapping = new Mapping();
var itemMapping = new Mapping();
var data = dataset.AllSamples.Select(ir => new
{
UserId = userMapping.ToInternalID(ir.User.Id),
ItemId = itemMapping.ToInternalID(ir.Item.Id),
Rating = Convert.ToDouble(ir.Rating)
}).ToList();
// users
int i = 0;
var uOut = File.ReadAllLines(Paths.AmazonBooksUsersCluster + ".lf").Select(l =>
{
var values = l.Split(new string[] { " " }, StringSplitOptions.RemoveEmptyEntries)
.Select(v => Convert.ToDouble(v)).ToList();
var maxIndex = values.IndexOf(values.Max());
return(new { UserId = userMapping.ToOriginalID(i++), ClusterId = maxIndex });
}).Select(uc => string.Format("{0},{1}", uc.UserId, uc.ClusterId));
File.WriteAllLines(Paths.AmazonBooksUsersCluster + ".nmf.u", uOut);
// items
int j = 0;
var iOut = File.ReadAllLines(Paths.AmazonBooksUsersCluster + ".rf").Select(l =>
{
var values = l.Split(new string[] { " " }, StringSplitOptions.RemoveEmptyEntries)
.Select(v => Convert.ToDouble(v)).ToList();
var maxIndex = values.IndexOf(values.Max());
return(new { ItemId = itemMapping.ToOriginalID(j++), ClusterId = maxIndex });
}).Select(ic => string.Format("{0},{1}", ic.ItemId, ic.ClusterId));
File.WriteAllLines(Paths.AmazonBooksUsersCluster + ".nmf.i", iOut);
}
public void CreateNmfClustersAmazon()
{
var reader = new AmazonReader(Paths.AmazonBooksRatings);
var dataset = new Dataset<ItemRating>(reader);
var userMapping = new Mapping();
var itemMapping = new Mapping();
var data = dataset.AllSamples.Select(ir => new
{
UserId = userMapping.ToInternalID(ir.User.Id),
ItemId = itemMapping.ToInternalID(ir.Item.Id),
Rating = Convert.ToDouble(ir.Rating)
}).ToList();
// users
int i = 0;
var uOut = File.ReadAllLines(Paths.AmazonBooksUsersCluster + ".lf").Select(l =>
{
var values = l.Split(new string[] { " " }, StringSplitOptions.RemoveEmptyEntries)
.Select(v => Convert.ToDouble(v)).ToList();
var maxIndex = values.IndexOf(values.Max());
return new { UserId = userMapping.ToOriginalID(i++), ClusterId = maxIndex };
}).Select(uc => string.Format("{0},{1}", uc.UserId, uc.ClusterId));
File.WriteAllLines(Paths.AmazonBooksUsersCluster + ".nmf.u", uOut);
// items
int j = 0;
var iOut = File.ReadAllLines(Paths.AmazonBooksUsersCluster + ".rf").Select(l =>
{
var values = l.Split(new string[] { " " }, StringSplitOptions.RemoveEmptyEntries)
.Select(v => Convert.ToDouble(v)).ToList();
var maxIndex = values.IndexOf(values.Max());
return new { ItemId = itemMapping.ToOriginalID(j++), ClusterId = maxIndex };
}).Select(ic => string.Format("{0},{1}", ic.ItemId, ic.ClusterId));
File.WriteAllLines(Paths.AmazonBooksUsersCluster + ".nmf.i", iOut);
}
public void TestNmfClusting()
{
var reader = new AmazonReader(Paths.AmazonBooksRatings);
var dataset = new Dataset<ItemRating>(reader);
var clusterer = new Clusterer(dataset);
clusterer.ClusterNmf(5, Paths.AmazonBooksUsersCluster);
}
public void TestAmazonWithNmfCluster()
{
var trainReader = new AmazonReader(Paths.AmazonBooksTrain75, Paths.AmazonBooksUsersCluster + ".nmf.u", Paths.AmazonBooksUsersCluster + ".nmf.i");
var testReader = new AmazonReader(Paths.AmazonBooksTest25, Paths.AmazonBooksUsersCluster + ".nmf.u", Paths.AmazonBooksUsersCluster + ".nmf.i");
var dataset = new Dataset<ItemRatingWithClusters>(trainReader, testReader);
var recommender = new LibFmTrainTester();
var context = new EvalutationContext<ItemRating>(recommender, dataset);
var ep = new EvaluationPipeline<ItemRating>(context);
ep.Evaluators.Add(new RMSE());
ep.Evaluators.Add(new MAE());
ep.Run();
}
public void TestAmazonWithClusters()
{
// Todo: instead of loading the dataset every time add a updateCluster method to the Dataset<ItemRatingWithCluster>
List<string> rmses = new List<string>();
List<string> maes = new List<string>();
for (int i = 2; i < 13; i += 2)
{
string usersClusterFile = Paths.AmazonMusicUsersCluster + i + ".csv";
string itemsClusterFile = Paths.AmazonMusicItemsCluster + i + ".csv";
AmazonReader trainReader, testReader;
if (i == 0)
{
trainReader = new AmazonReader(Paths.AmazonMusicTrain75);
testReader = new AmazonReader(Paths.AmazonMusicTest25);
}
else
{
trainReader = new AmazonReader(Paths.AmazonMusicTrain75, usersClusterFile, itemsClusterFile, "b", true);
testReader = new AmazonReader(Paths.AmazonMusicTest25, usersClusterFile, itemsClusterFile, "b", true);
}
var dataset = new Dataset<ItemRatingWithClusters>(trainReader, testReader);
var recommender = new LibFmTrainTester(i.ToString());
var context = new EvalutationContext<ItemRating>(recommender, dataset);
var ep = new EvaluationPipeline<ItemRating>(context);
ep.Evaluators.Add(new RMSE());
ep.Evaluators.Add(new MAE());
ep.Run();
rmses.Add(context["RMSE"].ToString());
maes.Add(context["MAE"].ToString());
}
Console.WriteLine("RMSEs--------------");
rmses.ForEach(Console.WriteLine);
Console.WriteLine("MAEs-------------");
maes.ForEach(Console.WriteLine);
}
