public IActionResult Partition2(int partitionCount)
{
using (var db = new FusekiContext())
{
var articles = db.Articles.Where(el => el.Published == true)
.Include(el => el.Tags).Take(20).ToList();
//get a tag vector for each article.
var allTags = new HashSet <string>();
//TODO: What happens if we remove all tags which only occur once.
foreach (var article in articles)
{
foreach (var tag in article.Tags)
{
allTags.Add(tag.Name);
}
}
var newAllTags = new HashSet <string>();
foreach (var t in allTags)
{
var relatedArticles = db.Articles.Where(el => el.Tags.Select(tag => tag.Name).Contains(t));
if (relatedArticles.Count() > 1)
{
newAllTags.Add(t);
}
}
allTags = newAllTags;
var allTagsOrdered = allTags.OrderBy(el => el);
var obs = new List <List <double> >();
var dict = new Dictionary <string, object>();
foreach (var article in articles)
{
var articleTags = article.Tags.Select(el => el.Name);
var vector = new List <double>();
foreach (var tag in allTagsOrdered)
{
if (articleTags.Contains(tag))
{
vector.Add(1);
}
else
{
vector.Add(0);
}
}
obs.Add(vector);
}
var vecvec = obs.Select(el => el.ToArray()).ToArray();
var kmeans = new KMeans(k: partitionCount);
var clusters = kmeans.Learn(vecvec);
dict["Kmeans Error"] = kmeans.Error;
dict["dimensionality"] = kmeans.Dimension;
dict["Iterations"] = kmeans.Iterations;
dict["MaxIterations"] = kmeans.MaxIterations;
dict["Tolerance"] = kmeans.Tolerance;
int[] labels = clusters.Decide(vecvec);
//labels is array[articleId] => partitionNumber
var ii = 0;
var psets = new List <PartitionSet <Article> >();
//this is totally fake. TODO: refactor these to be dumber - no need to have comparators etc.
var dm = new DistanceMetrics <Article>((a, b) => Comparators.GetTagCommonality(a, b), (a, b) => Comparators.ArticleKeyLookup(a, b));
while (ii < partitionCount)
{
//TODO: is accord zero indexed?
psets.Add(new PartitionSet <Article>(dm, ii));
ii++;
}
var index = 0;
foreach (var l in labels)
{
var article = articles[index];
index++;
psets[l].Add(article);
}
var partitiondata = new PartitionData <Article>(psets, dict);
var model = new ArticlePartitionModel(partitiondata);
return(View("ArticlePartitions", model));
}
}
///obviously impossible to test every possibility.
///Might be possible to iterate or do local hill climbing? order matters for all that.
///title length has weird transitivity; don't use that because it won't apply for other metrics.
///I could just do it 100 times with random starts, iterating adding members to the set which they are closest to.
///Then as a final step test each element to see if it belongs better in another set.
public PartitionData <T> GetPartitions(int partitionCount, List <T> Elements)
{
if (partitionCount < 2 || partitionCount > 100)
{
throw new Exception("Are you sure you want to generate that many partitions?");
}
var sets = new List <PartitionSet <T> >();
var ii = 0;
while (ii < partitionCount)
{
var px = new PartitionSet <T>(metrics, ii);
sets.Add(px);
ii++;
}
using (var db = new FusekiContext())
{
foreach (var el in Elements)
{
var targetSet = FindBestPartition(el, sets);
targetSet.Add(el);
}
}
//initial assignment done.
//now iterate over each item, removing it and then readding it where it belongs til we reach stability or N iterations.
var loopCt = 0;
var moveCt = 100;
var stats = new Dictionary <string, object>();
stats["InitialQuality"] = FindQuality(sets);
while (loopCt < 200)
{
moveCt = 0;
var PlannedMoves = new Dictionary <T, Tuple <PartitionSet <T>, PartitionSet <T> > >();
foreach (var set in sets)
{
foreach (var el in set.Items)
{
//remove it first so it has a free choice
var targetSet = FindBestPartition(el, sets);
if (targetSet != set)
{
moveCt++;
var data = new Tuple <PartitionSet <T>, PartitionSet <T> >(set, targetSet);
PlannedMoves[el] = data;
}
if (moveCt > 0)
{
break;
}
}
if (moveCt > 0)
{
break;
}
}
//problem: I am moving to favor the article, not to favor the overall quality of matches. i.e. if there is a linking article who is happier in a dedicated node, but removing him hurts the parent, how to do it?
foreach (var article in PlannedMoves.Keys)
{
var tup = PlannedMoves[article];
var old = tup.Item1;
var newset = tup.Item2;
old.Remove(article);
newset.Add(article);
}
loopCt++;
stats[$"quality:{loopCt} moved:{moveCt}"] = FindQuality(sets);
if (moveCt == 0)
{
break;
}
}
stats["moveCt"] = moveCt;
stats["loopCt"] = loopCt;
stats["Final quality"] = FindQuality(sets);
var pdata = new PartitionData <T>(sets, stats);
return(pdata);
}
