private static void BuildTitleMinHashes(List <Listing> listings, string job_id)
{
var universe = new Dictionary <string, int>();
var wordId = 0;
var mh = new MinHash(200000, minHashCount);
var singleItemProgress = ProgressManager.CalculateLoopIncrement(listings.Count(), 0.2M);
// Build ngrams for each listing (if not done already) and save to universe of ngrams
foreach (var listing in listings.ToList())
{
if (!listing.ngrams_description.Any())
{
listing.ngrams_description = mh.GetProfile(listing.description, nGramLength);
}
foreach (var ngram in listing.ngrams_description.Keys)
{
if (!universe.ContainsKey(ngram))
{
universe[ngram] = wordId++;
}
}
ProgressManager.IncrementJobPercentBy(job_id, singleItemProgress);
}
singleItemProgress = ProgressManager.CalculateLoopIncrement(listings.Count(), 0.2M);
mh = new MinHash(universe.Count, minHashCount);
foreach (var listing in listings)
{
if (listing.minhash_description.Any())
{
continue;
}
// Set word ID in each document
foreach (var ngram in listing.ngrams_description.Keys)
{
listing.word_ids_description.Add(universe[ngram]);
}
// Calculate min hash for each listing
listing.minhash_description = mh.GetMinHash(listing.word_ids_description);
ProgressManager.IncrementJobPercentBy(job_id, singleItemProgress);
}
}