private static void Print(string newName, AllResults loadedFile)
{
using (var sw = new StreamWriter(newName.Replace(".bin", ".html"), append: false))
{
loadedFile.Render(sw);
}
}
public static void AgglomerativeClustering(AllResults loaded)
{
var imgName = "241666.jpg"; //"159161.jpg";
var imgId = loaded.ImageEncoding[imgName];
var relevantRows = loaded.Rows
//.Where(r => r.Query.ImageId == imgId)
.ToList();
// cluster all of them together? Include query into dissimilarity function then
// Or product by product, filter down to big elements, and offer to transitively load more and more?
var metric = new ResultsRowSetBasedDistance();
var linkage = new AverageLinkage <ResultsRow>(metric);
var algorithm = new AgglomerativeClusteringAlgorithm <ResultsRow>(linkage);
var clusters = algorithm.GetClustering(new HashSet <ResultsRow>(relevantRows));
clusters.SaveToCsv(@"G:\siret\zoot\protobuf\clustertest.csv");
//RenderData();
var dummyResults = new AllResults {
ImageEncoding = loaded.ImageEncoding, PatchEncoding = loaded.PatchEncoding
};
var clusterQueue = new Queue <Cluster <ResultsRow> >(new[] { clusters.SingleCluster });
while (clusterQueue.Count > 0)
{
var item = clusterQueue.Dequeue();
if (item.Dissimilarity <= 0.70 && item.Count < 50)
{
dummyResults.Rows.Add(new ResultsRow
{
Query = item.First().Query,
Hits = item.SelectMany(x => x.Hits)
.GroupBy(x => x.Hit)
.Select(x => new SearchHit {
Hit = x.Key, Distance = x.Min(y => y.Distance)
})
.Concat(item.Select(i => new SearchHit {
Hit = i.Query, Distance = -1
}))
.ToArray()
});
}
else
{
clusterQueue.Enqueue(item.Parent1);
clusterQueue.Enqueue(item.Parent2);
}
}
loaded.RefreshReferenceMap();
foreach (var k in AllResults.ReferenceMap.Keys)
{
AllResults.ReferenceMap[k][k] = 1;
}
using (var sw = new StreamWriter(@"G:\siret\zoot\protobuf\clusteringTestMega.html", append: false))
{
dummyResults.Render(sw);
}
}