private static async Task Main()
{
Console.WriteLine("Reading posts from GitHub repo..");
var posts = await GetBlogPosts();
Console.WriteLine("Parsing documents..");
Storage.Current = new OnlineRepositoryStorage(new DiskStorage("catalyst-models"));
var language = Language.English;
var pipeline = Pipeline.For(language);
var postsWithDocuments = posts
.Select(post =>
{
var document = new Document(NormaliseSomeCommonTerms(post.PlainTextContent), language)
{
UID = post.Title.Hash128()
};
pipeline.ProcessSingle(document);
return(Post: post, Document: document);
})
.ToArray(); // Call ToArray to force evaluation of the document processing now
Console.WriteLine("Training FastText model..");
var fastText = new FastText(language, version: 0, tag: "");
fastText.Data.Type = FastText.ModelType.PVDM;
fastText.Data.Loss = FastText.LossType.NegativeSampling;
fastText.Data.IgnoreCase = true;
fastText.Data.Epoch = 50;
fastText.Data.Dimensions = 512;
fastText.Data.MinimumCount = 1;
fastText.Data.ContextWindow = 10;
fastText.Data.NegativeSamplingCount = 20;
fastText.Train(
postsWithDocuments.Select(postsWithDocument => postsWithDocument.Document),
trainingStatus: update => Console.WriteLine($" Progress: {update.Progress}, Epoch: {update.Epoch}")
);
Console.WriteLine("Building recommendations..");
// Combine the blog post data with the FastText-generated vectors
var results = fastText
.GetDocumentVectors()
.Select(result =>
{
// Each document vector instance will include a "token" string that may be mapped back to the
// UID of the document for each blog post. If there were a large number of posts to deal with
// then a dictionary to match UIDs to blog posts would be sensible for performance but I only
// have a 100+ and so a LINQ "First" scan over the list will suffice.
var uid = UID128.Parse(result.Token);
var postForResult = postsWithDocuments.First(
postWithDocument => postWithDocument.Document.UID == uid
);
return(UID: uid, result.Vector, postForResult.Post);
})
.ToArray(); // ToArray since we enumerate multiple times below
// Construct a graph to search over, as described at
// https://github.com/curiosity-ai/hnsw-sharp#how-to-build-a-graph
var graph = new SmallWorld <(UID128 UID, float[] Vector, BlogPost Post), float>(
distance: (to, from) => CosineDistance.NonOptimized(from.Vector, to.Vector),
DefaultRandomGenerator.Instance,
new() { M = 15, LevelLambda = 1 / Math.Log(15) }
);
graph.AddItems(results);
// For every post, use the "KNNSearch" method on the graph to find the three most similar posts
const int maximumNumberOfResultsToReturn = 3;
var postsWithSimilarResults = results
.Select(result =>
{
// Request one result too many from the KNNSearch call because it's expected that the original
// post will come back as the best match and we'll want to exclude that
var similarResults = graph
.KNNSearch(result, maximumNumberOfResultsToReturn + 1)
.Where(similarResult => similarResult.Item.UID != result.UID)
.Take(maximumNumberOfResultsToReturn); // Just in case the original post wasn't included
return(new
{
result.Post,
Similar = similarResults
.Select(similarResult => new
{
similarResult.Item.Post,
similarResult.Distance
})
.ToArray()
});
})
.OrderBy(result => result.Post.Title, StringComparer.OrdinalIgnoreCase)
.ToArray();
foreach (var postWithSimilarResults in postsWithSimilarResults)
{
Console.WriteLine();
Console.WriteLine(postWithSimilarResults.Post.Title);
foreach (var similarResult in postWithSimilarResults.Similar.OrderBy(other => other.Distance))
{
Console.WriteLine($"{similarResult.Distance:0.000} {similarResult.Post.Title}");
}
}
Console.WriteLine();
Console.WriteLine("Done! Press [Enter] to terminate..");
Console.ReadLine();
}
private static async Task Main()
{
Console.WriteLine("Reading posts from GitHub repo..");
var posts = await GetBlogPosts();
Console.WriteLine("Parsing documents..");
Storage.Current = new OnlineRepositoryStorage(new DiskStorage("catalyst-models"));
var language = Language.English;
var pipeline = Pipeline.For(language);
var postsWithDocuments = posts
.Select(post =>
{
var document = new Document(NormaliseSomeCommonTerms(post.PlainTextContent), language)
{
UID = post.Title.Hash128()
};
pipeline.ProcessSingle(document);
return(Post: post, Document: document);
})
.ToArray(); // Call ToArray to force evaluation of the document processing now
Console.WriteLine("Training FastText model..");
var fastText = new FastText(language, version: 0, tag: "");
fastText.Data.Type = FastText.ModelType.PVDM;
fastText.Data.Loss = FastText.LossType.NegativeSampling;
fastText.Data.IgnoreCase = true;
fastText.Data.Epoch = 50;
fastText.Data.Dimensions = 512;
fastText.Data.MinimumCount = 1;
fastText.Data.ContextWindow = 10;
fastText.Data.NegativeSamplingCount = 20;
fastText.Train(
postsWithDocuments.Select(postsWithDocument => postsWithDocument.Document),
trainingStatus: update => Console.WriteLine($" Progress: {update.Progress}, Epoch: {update.Epoch}")
);
Console.WriteLine("Training TF-IDF model..");
var tfidf = new TFIDF(pipeline.Language, version: 0, tag: "");
await tfidf.Train(postsWithDocuments.Select(postWithDocument => postWithDocument.Document));
Console.WriteLine("Getting average TF-IDF weights per word..");
var tokenValueTFIDF = new Dictionary <string, List <float> >(StringComparer.OrdinalIgnoreCase);
foreach (var doc in postsWithDocuments.Select(postWithDocument => postWithDocument.Document))
{
tfidf.Process(doc);
foreach (var sentence in doc)
{
foreach (var token in sentence)
{
if (!tokenValueTFIDF.TryGetValue(token.Value, out var freqs))
{
freqs = new();
tokenValueTFIDF.Add(token.Value, freqs);
}
freqs.Add(token.Frequency);
}
}
}
var averagedTokenValueTFIDF = tokenValueTFIDF.ToDictionary(
entry => entry.Key,
entry => entry.Value.Average(), StringComparer.OrdinalIgnoreCase
);
Console.WriteLine("Building recommendations..");
// Combine the blog post data with the FastText-generated vectors
var results = fastText
.GetDocumentVectors()
.Select(result =>
{
// Each document vector instance will include a "token" string that may be mapped back to the
// UID of the document for each blog post. If there were a large number of posts to deal with
// then a dictionary to match UIDs to blog posts would be sensible for performance but I only
// have a 100+ and so a LINQ "First" scan over the list will suffice.
var uid = UID128.Parse(result.Token);
var postForResult = postsWithDocuments.First(
postWithDocument => postWithDocument.Document.UID == uid
);
return(UID: uid, result.Vector, postForResult.Post);
})
.ToArray(); // ToArray since we enumerate multiple times below
// Construct a graph to search over, as described at
// https://github.com/curiosity-ai/hnsw-sharp#how-to-build-a-graph
var graph = new SmallWorld <(UID128 UID, float[] Vector, BlogPost Post), float>(
distance: (to, from) => CosineDistance.NonOptimized(from.Vector, to.Vector),
DefaultRandomGenerator.Instance,
new() { M = 15, LevelLambda = 1 / Math.Log(15) }
);
graph.AddItems(results);
const int maximumNumberOfResultsToReturn = 3;
var postsWithSimilarResults = results
.Select(result =>
{
// Request that the KNNSearch operate over all documents because we can't take the top {n}
// until we've combined the ordering with the title TFIDF proximity values
var similarResults = graph
.KNNSearch(result, postsWithDocuments.Length)
.Where(similarResult => similarResult.Item.UID != result.UID);
var tokenValuesInTitle =
GetAllTokensForText(NormaliseSomeCommonTerms(result.Post.Title), pipeline)
.Select(token => token.Value)
.ToHashSet(StringComparer.OrdinalIgnoreCase);
return(new
{
result.Post,
Similar = similarResults
.Select(similarResult => new
{
similarResult.Item.Post,
similarResult.Distance,
ProximityByTitleTFIDF = GetProximityByTitleTFIDF(
NormaliseSomeCommonTerms(similarResult.Item.Post.Title),
tokenValuesInTitle,
averagedTokenValueTFIDF,
pipeline
)
})
.OrderByDescending(similarResult => similarResult.ProximityByTitleTFIDF)
.ThenBy(similarResult => similarResult.Distance)
.Take(maximumNumberOfResultsToReturn)
.ToArray()
});
})
.OrderBy(result => result.Post.Title, StringComparer.OrdinalIgnoreCase)
.ToArray();
foreach (var postWithSimilarResults in postsWithSimilarResults)
{
Console.WriteLine();
Console.WriteLine(postWithSimilarResults.Post.Title);
foreach (var similarResult in postWithSimilarResults.Similar.OrderBy(other => other.Distance))
{
Console.WriteLine($"{similarResult.ProximityByTitleTFIDF:0.000} {similarResult.Distance:0.000} {similarResult.Post.Title}");
}
}
Console.WriteLine();
Console.WriteLine("Done! Press [Enter] to terminate..");
Console.ReadLine();
}