public static void Run()
{
var spacy = new Spacy();
var nlp = spacy.Load("en_core_web_sm");
var doc = nlp.GetDocument("Apple is looking at buying U.K. startup for $1 billion");
var displacy = new Displacy();
displacy.Serve(doc, "dep");
}
public static async Task Main(string[] args)
{
using (await Spacy.Initialize(Spacy.ModelSize.Small, Language.Any, Language.English))
{
var nlp = Spacy.For(Spacy.ModelSize.Small, Language.English);
var doc = new Document("This is a test of integrating Spacy and Catalyst", Language.English);
nlp.ProcessSingle(doc);
Console.WriteLine(doc.ToJson());
}
}
public static void Run()
{
var spacy = new Spacy();
var nlp = spacy.Load("en_core_web_sm");
var doc = nlp.GetDocument("Apple is looking at buying U.K. startup for $1 billion");
foreach (Token token in doc.Tokens)
{
Console.WriteLine($"{token.Text} {token.Lemma} {token.PoS} {token.Tag} {token.Dep} {token.Shape} {token.IsAlpha} {token.IsStop}");
}
Console.WriteLine("");
foreach (Span ent in doc.Ents)
{
Console.WriteLine($"{ent.Text} {ent.StartChar} {ent.EndChar} {ent.Label}");
}
nlp = spacy.Load("en_core_web_md");
var tokens = nlp.GetDocument("dog cat banana afskfsd");
Console.WriteLine("");
foreach (Token token in tokens.Tokens)
{
Console.WriteLine($"{token.Text} {token.HasVector} {token.VectorNorm}, {token.IsOov}");
}
tokens = nlp.GetDocument("dog cat banana");
Console.WriteLine("");
foreach (Token token1 in tokens.Tokens)
{
foreach (Token token2 in tokens.Tokens)
{
Console.WriteLine($"{token1.Text} {token2.Text} {token1.Similarity(token2) }");
}
}
doc = nlp.GetDocument("I love coffee");
Console.WriteLine("");
Console.WriteLine(doc.Vocab.Strings["coffee"]);
Console.WriteLine(doc.Vocab.Strings[3197928453018144401]);
Console.WriteLine("");
foreach (Token word in doc.Tokens)
{
var lexeme = doc.Vocab[word.Text];
Console.WriteLine($@"{lexeme.Text} {lexeme.Orth} {lexeme.Shape} {lexeme.Prefix} {lexeme.Suffix} {lexeme.IsAlpha} {lexeme.IsDigit} {lexeme.IsTitle} {lexeme.Lang}");
}
}
public static void Run()
{
var spacy = new Spacy();
var nlp = spacy.Load("en_core_web_sm");
var text = "Autonomous cars shift insurance liability toward manufacturers";
var doc = nlp.GetDocument(text);
foreach (var token in doc.Tokens)
{
var childs = new List <string>();
token.Children.ForEach(c => childs.Add(c.Text));
Console.WriteLine($"{token.Text} {token.Dep} {token.Head.Text} [{string.Join(", ", childs)}]");
}
}
public static void Run()
{
var spacy = new Spacy();
var text = "I love coffee";
// Load base document
var nlp = spacy.Load("en_core_web_sm");
var docBase = nlp.GetDocument(text);
Console.WriteLine("");
PrintDoc(docBase);
// Serialize document to disk and bytes
docBase.ToDisk("doc.spacy");
var docBaseBytes = docBase.ToBytes();
// Serialize using DocBin
var docBinBase = new DocBin(attrs: new string[] { "ENT_IOB", "POS", "HEAD", "DEP", "ENT_TYPE" }, storeUserData: true);
docBinBase.Add(docBase);
var docBinBaseBytes = docBinBase.ToBytes();
// Restore document from disk
var doc = new Doc(new Vocab());
doc.FromDisk("doc.spacy");
Console.WriteLine("");
PrintDoc(doc);
// Restore document from bytes
doc = new Doc(new Vocab());
doc.FromBytes(docBaseBytes);
Console.WriteLine("");
PrintDoc(doc);
// Restore using DocBin
var docBin = new DocBin();
docBin.FromBytes(docBinBaseBytes);
var docs = docBin.GetDocs(nlp.Vocab);
Console.WriteLine("");
PrintDoc(docs[0]);
}
public static void Run()
{
var spacy = new Spacy();
var nlp = spacy.Load("es_core_news_sm");
var separator = "____________________________________________________________________________";
var text = @"Cuando Sebastian Thrun empezó a trabajar en coches de conducción autónoma, en 2007, para ";
text += "Google, muy poca gente fuera de la empresa le tomó en serio. “Podría contaros como CEOs muy ";
text += "veteranos de las empresas automotrices más grandes de América me daban la mano para después ";
text += "ignorarme porque no merecía la pena hablar conmigo”, comentaba Thrun, en una entrevista a Recode ";
text += "a principios de semana";
var doc = nlp.GetDocument(text);
Console.WriteLine("Pipeline:");
Console.WriteLine(string.Join(",", nlp.PipeNames));
Console.WriteLine(separator);
Console.WriteLine("Tokenization");
Console.Write("[");
foreach (var token in doc.Tokens)
{
Console.Write("'" + token.Text + "', ");
}
Console.WriteLine("\b\b]");
Console.WriteLine(separator);
Console.WriteLine("Pos");
Console.Write("[");
foreach (var token in doc.Tokens)
{
Console.Write("'" + token.PoS + "', ");
}
Console.WriteLine("\b\b]");
Console.WriteLine(separator);
Console.WriteLine("PoS[0]:");
var token0 = doc.Tokens[0];
Console.WriteLine("Fine-grained POS tag " + token0.PoS);
Console.WriteLine("Coarse-grained POS tag " + token0.Tag);
Console.WriteLine("Word shape " + token0.Shape);
Console.WriteLine("Alphabetic characters? " + token0.IsAlpha);
Console.WriteLine("Punctuation mark? " + token0.IsPunct);
Console.WriteLine("Digit? " + token0.IsDigit);
Console.WriteLine("Like a number? " + token0.LikeNum);
Console.WriteLine("Like an email address? " + token0.LikeEMail);
Console.WriteLine(separator);
Console.WriteLine("Lemmatization:");
Console.Write("[");
foreach (var token in doc.Tokens)
{
Console.Write("'" + token.Lemma + "', ");
}
Console.WriteLine("\b\b]");
Console.WriteLine(separator);
Console.WriteLine("Sentences:");
Console.Write("[");
foreach (var sentence in doc.Sents)
{
Console.Write("'" + sentence.Text + "', ");
}
Console.WriteLine("\b\b]");
Console.WriteLine(separator);
Console.WriteLine("Noun Phrases:");
Console.Write("[");
foreach (var nounChunk in doc.NounChunks)
{
Console.Write("'" + nounChunk.Text + "', ");
}
Console.WriteLine("\b\b]");
Console.WriteLine(separator);
Console.WriteLine("Entities (Named entities, phrases and concepts):");
foreach (var entity in doc.Ents)
{
Console.WriteLine("Entity: " + entity.Text + "\tLabel: " + entity.Label);
}
Console.WriteLine(separator);
}