/// <summary>
/// Build the index
/// </summary>
public virtual void Build(MetricDB db, int num_centers, Random rand)
{
this.DB = db;
var n = this.DB.Count;
// randomized has very good performance, even compared with more "intelligent" strategies
this.node_list = new List<Node> (num_centers);
var subset = RandomSets.GetRandomSubSet (num_centers, this.DB.Count, rand);
var H = new HashSet<int> (subset);
for (int centerID = 0; centerID < num_centers; ++centerID) {
this.node_list.Add (new Node (subset [centerID]));
}
var IDX = new SAT_Distal ();
IDX.Build (new SampleSpace("", db, subset), rand);
for (int docID = 0; docID < n; ++docID) {
if (docID % 1000 == 0) {
Console.WriteLine ("== Vor {0}/{1}, num_centers: {2}, db: {3}", docID + 1, n, num_centers, db.Name);
}
if (H.Contains(docID)) {
continue;
}
// var near = new Result(1);
// for (var centerID = 0; centerID < num_centers; ++centerID) {
// var node = this.node_list[centerID];
// var d = this.DB.Dist(this.DB[node.refID], this.DB[docID]);
// near.Push(centerID, d);
// }
// var _near = near.First;
var _near = IDX.SearchKNN (this.DB[docID], 1, new Result (1)).First;
this.node_list[_near.ObjID].Add(docID, _near.Dist);
}
}
public void Build(MetricDB db, Random rand, int num_refs, int K=7, int maxcand=1024, SequenceBuilder seq_builder=null)
{
var sample = new SampleSpace ("", db, num_refs, rand);
var sat = new SAT_Distal ();
sat.Build (sample, RandomSets.GetRandom());
this.Build (db, sat, K, maxcand, seq_builder);
}
public void Build(MetricDB db, int k, int num_refs, Random rand)
{
var sample = new SampleSpace("", db, num_refs, rand);
var I = new SAT_Distal();
I.Build(sample, rand);
this.Build(db, k, I);
}
public void Build(MetricDB db, int symbolsPerHash, int neighborhoodExpansion, Random rand)
{
this.DB = db;
int n = db.Count;
this.SymbolsPerHash = symbolsPerHash; // very small values, i.e., 2, 3, 4
this.NeighborhoodExpansion = neighborhoodExpansion; // neighborhoodExpansion >= symbolsPerHash
var numrefs = (int)(Math.Pow(n, 1.0 / this.SymbolsPerHash));
this.CountSymbolBits = countBits(numrefs);
var refs = new SampleSpace("", db, numrefs, rand);
var sat = new SAT_Distal ();
sat.Build (refs, new Random ());
this.R = sat;
var G = new KnrFP ();
G.Build (db, this.R, this.SymbolsPerHash);
var knrcopy = new int[this.SymbolsPerHash];
this.hashTable = new Dictionary<long, List<int>> ();
for (int objID = 0; objID < n; ++objID) {
var knr = G [objID] as int[];
knr.CopyTo (knrcopy, 0);
var hash = this.EncodeKnr (knrcopy); // EncodeKnr destroys the reference order
List<int> L;
if (!this.hashTable.TryGetValue(hash, out L)) {
L = new List<int>();
this.hashTable.Add(hash, L);
}
L.Add (objID);
}
double avg_len = 0;
double avg_len_sq = 0;
foreach (var list in this.hashTable.Values) {
avg_len += list.Count;
avg_len_sq += list.Count * list.Count;
}
avg_len /= this.hashTable.Count;
avg_len_sq /= this.hashTable.Count;
Console.WriteLine ("=== created hash table with {0} keys, items: {1}, popcount mean: {2}, popcount stddev: {3}",
this.hashTable.Count, n, avg_len, Math.Sqrt(avg_len_sq - avg_len * avg_len));
}
public static string ExecuteSATDistal(IndexArgumentSetup setup, string nick)
{
var idxname = String.Format ("{0}/Index.SAT-Distal", nick);
return Execute (setup, nick, idxname, (db) => {
var sat = new SAT_Distal ();
sat.Build (db, RandomSets.GetRandom());
return sat;
});
}