public IActionResult Partition(int partitionCount)
{
//var partitioner = new Partitioner<Article>((a, b) => Comparators.GetLengthDistance(a, b), (a, b) => Comparators.ArticleKeyLookup(a, b));
var partitioner = new Partitioner <Article>((a, b) => Comparators.GetTagCommonality(a, b), (a, b) => Comparators.ArticleKeyLookup(a, b));
using (var db = new FusekiContext())
{
var articles = db.Articles.Where(el => el.Published == true)
.Include(el => el.Tags).ToList();
var r = new Random();
articles = articles.OrderBy(el => r.NextDouble()).ToList();
var partitiondata = partitioner.GetPartitions(partitionCount, articles);
var model = new ArticlePartitionModel(partitiondata);
return(View("ArticlePartitions", model));
}
}
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));
}
}
