Lexer lexer = Lexers.coreBuilder()      //core分词构建器
                     .withPos()         //开启词性
                     .withPersonName()  //开启人名
                     .build();          // 创建定制词法分析对象
                     
Sentence sentence = lexer.scan("mynlp是mayabot开源的中文NLP工具包。");

System.out.println(sentence.toList());

Lexer lexer = Lexers
                .perceptronBuilder()
                .withPos()
                .withPersonName()
                .withNer()
                .build();

// or Lexer lexer = Lexers.perceptron(); 返回一个默认的分析器

System.out.println(lexer.scan("2001年，他还在纽约医学院工作时，在英国学术刊物《自然》上发表一篇论文"));

MemCustomDictionary dictionary = new MemCustomDictionary();
dictionary.addWord("逛吃");

//词典生效
dictionary.rebuild();

FluentLexerBuilder builder = Lexers.coreBuilder()
        .withPos()
        .withPersonName();
        
builder.with(new CustomDictionaryPlugin(dictionary));

Lexer lexer = builder.build();

System.out.println(lexer.scan("逛吃行动小组成立"));

PinyinResult result = Pinyins.convert("招商银行,推出朝朝盈理财产品");

System.out.println(result.asString());
System.out.println(result.asHeadString(","));

// 输出模糊拼音
result.fuzzy(true);
System.out.println(result.fuzzy(true).asString());

//保留标点
result.keepPunctuation(true);
//result.keepAlpha(true);
//result.keepNum(true);
//result.keepOthers(true);

System.out.println(result.asString());

System.out.println(PinyinSplits.split("nizhidaowozaishuoshenmema"));

File trainFile = new File("data/agnews/ag.train");
InputArgs inputArgs = new InputArgs();
inputArgs.setLoss(LossName.softmax);
inputArgs.setLr(0.1);
inputArgs.setDim(100);
inputArgs.setEpoch(20);

FastText model = FastText.trainSupervised(trainFile, inputArgs);

// 训练参数
InputArgs trainArgs = new InputArgs();
trainArgs.setLoss(LossName.hs);
trainArgs.setEpoch(10);
trainArgs.setDim(100);
trainArgs.setLr(0.2);

//训练一个分类模型
FastText fastText = FastText.trainSupervised(trainFile, trainArgs);

//使用乘积量化压缩模型
FastText qFastText = fastText.quantize();

//fastText.saveModel("example.data/hotel.model");

//使用测试数据评估模型
fastText.test(testFile,1,0.0f,true);
System.out.println("--------------");
qFastText.test(testFile,1,0.0f,true);

Simplified2Traditional s2t = TransformService.simplified2Traditional();
System.out.println(s2t.transform("软件和体育的艺术"));

Traditional2Simplified t2s = TransformService.traditional2Simplified();
System.out.println(t2s.transform("軟件和體育的藝術"));

KeywordSummary keywordSummary = new KeywordSummary();
keywordSummary.keyword("text",10);

SentenceSummary sentenceSummary = new SentenceSummary();
List<String> result = sentenceSummary.summarySentences(document, 10);