import java.util.Collection;

import org.deeplearning4j.models.embeddings.loader.WordVectorSerializer;
import org.deeplearning4j.models.word2vec.Word2Vec;
import org.deeplearning4j.text.sentenceiterator.BasicLineIterator;
import org.deeplearning4j.text.sentenceiterator.SentenceIterator;
import org.deeplearning4j.text.tokenization.tokenizer.preprocessor.CommonPreprocessor;
import org.deeplearning4j.text.tokenization.tokenizerfactory.DefaultTokenizerFactory;
import org.deeplearning4j.text.tokenization.tokenizerfactory.TokenizerFactory;

public class main {

    public static void main(String[] args) throws Exception {
    	//Path du document pour apprentissage
    	String filePath = "C:/Users/lucas/Desktop/M2/Web Semantique/Projet/web-semantique/src/main/resources/raw_sentences.txt";

    	//Ouverture et tokenization du document
        System.out.println("Load & Vectorize Sentences....");
        SentenceIterator iter = new BasicLineIterator(filePath);
        TokenizerFactory t = new DefaultTokenizerFactory();
        t.setTokenPreProcessor(new CommonPreprocessor());

        //Build du model
        System.out.println("Building model....");
        Word2Vec vec = new Word2Vec.Builder()
                .minWordFrequency(5)
                .layerSize(100)
                .seed(42)
                .windowSize(5)
                .iterate(iter)
                .tokenizerFactory(t)
                .build();

        //Entrainement du model
        System.out.println("Fitting Word2Vec model....");
        vec.fit();

        //Affichage des mots les plus proches de "le"
        System.out.println("Closest Words:");
        Collection<String> lst = vec.wordsNearest("le", 3);
        System.out.println(lst);

        //Sauvegarde du model buildé pour pouvoir le recharger ultérieurement
        WordVectorSerializer.writeWord2VecModel(vec, "C:/Users/lucas/Desktop/M2/Web Semantique/Projet/web-semantique/src/main/resources/model.txt");
    }
}