public void Initialize() { NBFactory = new NaiveBayesLanguageIdentifierFactory(); RLFactory = new RankedLanguageIdentifierFactory(); NBIdentifier = NBFactory.Load(Path.Combine(ModelFolder, SelectedModel)); RLIdentifier = RLFactory.Load(Path.Combine(ModelFolder, SelectedModel)); }
private async Task MainAsync() { var credentials = JsonConvert.DeserializeObject <Credentials>(File.ReadAllText("Keys/Credentials.json")); if (credentials.BotToken == null) { throw new NullReferenceException("Invalid Credentials file"); } var factory = new RankedLanguageIdentifierFactory(); _identifier = factory.Load("Keys/Core14.profile.xml"); foreach (var file in Directory.GetFiles("Dictionaries")) { FileInfo fi = new FileInfo(file); if (fi.Name.Split('.')[1] == "dic") { _dictionaries.Add(fi.Name.Split('.')[0], WordList.CreateFromFiles(file)); } } await _commands.AddModuleAsync <Communication>(null); Client.MessageReceived += HandleCommandAsync; StartTime = DateTime.Now; await Client.LoginAsync(TokenType.Bot, credentials.BotToken); await Client.StartAsync(); await Task.Delay(-1); }
static LanguageDetector() { var factory = new RankedLanguageIdentifierFactory(); var currentDirectory = AppDomain.CurrentDomain.BaseDirectory; var coreProfileFile = Path.Combine(currentDirectory, "Core14.profile.xml"); _identifier = factory.Load(coreProfileFile); }
public NoticeParserFactory() { _tedLabelDictionary = new TedLabelDictionary(); var factory = new RankedLanguageIdentifierFactory(); _rankedLanguageIdentifier = factory.Load("Core14.profile.xml"); }
public static void DetectLanguage(RankedLanguageIdentifier identifier, string sequence, int index) { var languages = identifier.Identify(sequence.ToLower()); var mostCertainLanguage = languages.FirstOrDefault(); if (mostCertainLanguage != null && mostCertainLanguage.Item1.Iso639_3 == "eng" && mostCertainLanguage.Item2 <= CONFIDENCE_THRESHOLD) { SaveToFile(sequence, mostCertainLanguage.Item2, index); } }
string getLanguage(string text) { if (isEnglishCharacters(text)) { return("eng"); } if (isJapaneseCharacters(text)) { return("jpn"); } if (ncIdentifier_ == null) { var file = Path.Combine(Path.GetDirectoryName(Application.ExecutablePath), @"Core14.profile.xml"); if (!File.Exists(file)) { MessageBox.Show("Profile file of NTextCat not found."); return(string.Empty); } var fac = new RankedLanguageIdentifierFactory(); ncIdentifier_ = fac.Load(file); } var languages = ncIdentifier_.Identify(text); var mostCertainLanguage = languages.FirstOrDefault(); string lang; if (mostCertainLanguage == null) { lang = string.Empty; } else { lang = mostCertainLanguage.Item1.Iso639_3; } //if (string.IsNullOrEmpty(lang) || // (lang != "eng" && lang != "jpn")) //{ // if (isEnglish_obsolete(text)) // lang = "eng"; // else if (isJapanese_obsolete(text)) // lang = "jpn"; //} return(lang); }
public async Task Initialize(Configuration configuration) { this.configuration = configuration; minDate = configuration.MediaMinDate; dateLimitReached = false; var factory = new RankedLanguageIdentifierFactory(); languageIdentifier = factory.Load(Utils.GetPath(@"packages\NTextCat.0.2.1.30\Core14.profile.xml")); instaApi = InstaApiBuilder.CreateBuilder() .SetUser(new UserSessionData() { UserName = configuration.InstagramUserName, Password = configuration.InstagramPassword, CsrfToken = configuration.InstagramCsrfToken }) .SetRequestDelay(RequestDelay.FromSeconds(0, 0)) .Build(); await instaApi.LoginAsync(); }
private static string PrepareWord(RankedLanguageIdentifier identifier, string or) { var languages = identifier.Identify(or).ToArray(); var myLanguages = languages.Where(x => x.Item1.Iso639_3 == "eng" || x.Item1.Iso639_3 == "rus").ToArray(); if (!myLanguages.Any()) { throw new NotSupportedException(); } var max = myLanguages.Min(x => x.Item2); var lang = myLanguages.First(x => x.Item2 == max); var langCode = lang?.Item1.Iso639_3; IStemmer stemmer = langCode switch { "eng" => new EnglishStemmer(), "rus" => new RussianStemmer(), _ => throw new Exception() }; var stemmed = stemmer.Stem(or); return(stemmed); } }
public LanguageDetection() { string basepath = Path.GetDirectoryName(System.Reflection.Assembly.GetEntryAssembly().Location); identifier = factory.Load(basepath + "\\LanguageModels\\Core14.profile.xml"); }
static LanguageDetector() { var factory = new RankedLanguageIdentifierFactory(); _identifier = factory.Load("Core14.profile.xml"); }
public LanguageDetector(INTextCatMatchingProfileLoader profileLoader, DetectedLanguageBuilder builder) { _profileLoader = profileLoader; _builder = builder; _identifier = new RankedLanguageIdentifierFactory().Load(_profileLoader.MatchingProfileFile); }
public LanguageIdentifier() { var stream = Assembly.GetExecutingAssembly().GetManifestResourceStream(LanguageModelProfile); _identifier = new RankedLanguageIdentifierFactory().Load(stream); }