Main.java

import net.bbridge.core.extractor.TopicsFeatureExtractor;
import net.bbridge.core.text.processing.TextProcessor;
import net.bbridge.feature.extractor.text.TextTopicsFeatureExtractor;

import java.io.File;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;

public class Main {
    public static void main(String[] args) {
        String booksPath = "/Users/ksburaya/Documents/NUS/lda-librusec/books/";
        int documentSize = 500;

        TextTopicsFeatureExtractor extractor = new TextTopicsFeatureExtractor(100, 0.5, 0.1,
                10, 1000,
                "/Users/ksburaya/Documents/NUS/lda-librusec/librusec.lda", 2);


        // read each book and generate documents with N symbols size
        List<TextProcessor.Result> trainData = new ArrayList<>();
        File folder = new File(booksPath);
        File[] listOfFiles = folder.listFiles();

        for (File file : listOfFiles) {
            if (file.isFile()) {
                try {
                    String[] text = new String(Files.readAllBytes(Paths.get(file.getPath()))).split("\\s+");
                    int charCounter = 0;
                    List<String> words = new ArrayList<>();
                    for (String word: text) {
                        words.add(word);
                        charCounter += word.length();

                        if (charCounter > documentSize) {
                            charCounter = 0;
                            TextProcessor.Result result = new TextProcessor.Result(words, new HashMap<>());
                            trainData.add(result);
                            words.clear();
                        }
                    }

                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }

        extractor.train(trainData);

        List<String> testList = new ArrayList<>();
        testList.add("привет");
        testList.add("как");
        testList.add("дела");
        TextProcessor.Result test = new TextProcessor.Result(testList, new HashMap<>());
        HashMap <String, Double> ldaResult = (HashMap<String, Double>) extractor.extractFeatures(test);

        int i = 0;
    }
}