public static String PKU199801_TRAIN = "src/data/test/pku98/199801-train.txt"; // 训练集
public static String PKU199801_TEST = "src/data/test/pku98/199801-test.txt"; // 测试集
public static String pos_model = "src/main/resources/model/pku199801_pos.bin"; // posTagger 模型保存位置
public static String NER_MODEL = "src/main/resources/model/pku199801_ner.bin"; // ner 模型保存位置

public static String perceptronModelPath = "src/data/model/perceptronModel_pos.bin";


// 训练并保存模型
@Test
public void tstPosTagger1() throws IOException {
    PerceptronTrainer posTrainer = new POSTrainer();
    //同态的train方法可以指定压缩率
    LinearModel posModel = posTrainer.train(PKU199801_TRAIN, pos_model).getModel();
}



// 读取、评估模型和使用模型
@Test
public void tstPosTagger2() throws IOException {
    LinearModel posModel = new LinearModel(pos_model);
    PerceptronPOSTagger postTagger = new PerceptronPOSTagger(posModel);

    //评估模型
    System.out.printf("感知机 ACC = %.2f%%\n",PosTagUtil.evaluate(postTagger,PKU199801_TEST));

    //使用模型做标注
    System.out.println(Arrays.toString(postTagger.tag("多吃", "苹果", "有益", "健康")));

}


// 用规则调整pos
@Test
public void tstPosTagger3() throws IOException {
    PerceptronLexicalAnalyzer perceptronLexicalAnalyzer = new PerceptronLexicalAnalyzer(
            new PerceptronSegmenter("src/main/resources/model/cws.bin"),
            new PerceptronPOSTagger("src/main/resources/model/pku199801_pos.bin"),
            new PerceptronNERecognizer("src/main/resources/model/ner.bin")
    );

    CustomDictionary.insert("希望小学", "学校 1");
    perceptronLexicalAnalyzer.enableCustomDictionaryForcing(true);

    //仅标注
    System.out.println(Arrays.toString(perceptronLexicalAnalyzer.tag("多吃", "苹果", "有益", "健康")));
    //分词+标注
    System.out.println(perceptronLexicalAnalyzer.analyze("他的希望是希望上希望小学"));
    // 他/r 的/u 希望/n 是/v 希望/v 上/v 希望小学/学校
}

// 使用在线训练来调整模型。原本苹果为 n（名词），希望标注为nr（专有名词）
@Test
public void tstPosTagger4() throws IOException {
    PerceptronLexicalAnalyzer perceptronLexicalAnalyzer = new PerceptronLexicalAnalyzer(
            new PerceptronSegmenter("src/main/resources/model/cws.bin"),
            new PerceptronPOSTagger("src/main/resources/model/pku199801_pos.bin"),
            new PerceptronNERecognizer("src/main/resources/model/ner.bin")
    );

    //训练前
    System.out.println(perceptronLexicalAnalyzer.analyze("他想买苹果手机"));
    //他/r 想/v 买/v 苹果/n 手机/n

    for (int i = 0; i < 100; i++) {
        perceptronLexicalAnalyzer.learn("他/r 的/u 希望/n 是/v 买/v 苹果/nr 手机/n");
    }

    System.out.println(perceptronLexicalAnalyzer.analyze("他想买苹果手机"));
    //他/r 想/v 买/v 苹果/nr 手机/n
}

// 训练并保存模型
@Test
public void tstNER1() throws IOException {

    NERTrainer nerTrainer = new NERTrainer();
    LinearModel nerModel = nerTrainer.train("src/data/test/pku98/199801.txt",
            "src/main/resources/model/pku_198801_ner.bin").getModel();
}

// 读取、使用模型
@Test
public void tstNER2() throws IOException {

    LinearModel nerModel = new LinearModel("src/main/resources/model/pku_198801_ner.bin");
    PerceptronNERecognizer perceptronNERecognizer = new PerceptronNERecognizer(nerModel);

    String[] wordArray = {"华北", "电力", "公司"}; // 构造单词序列
    String[] posArray = {"ns", "n", "n"}; // 构造词性序列
    String[] nerTagArray = perceptronNERecognizer.recognize(wordArray, posArray); // 序列标注
    for (int i = 0; i < wordArray.length; i++)
        System.out.printf("%s\t%s\t%s\t\n", wordArray[i], posArray[i], nerTagArray[i]);
    //华北	ns	B-nt
    //电力	n	M-nt
    //公司	n	E-nt
}

//    在线学习
@Test
public void tstNER3() throws IOException {
    PerceptronLexicalAnalyzer perceptronLexicalAnalyzer = new PerceptronLexicalAnalyzer(
            new PerceptronSegmenter("src/main/resources/model/cws.bin"),
            new PerceptronPOSTagger("src/main/resources/model/pku199801_pos.bin"),
            new PerceptronNERecognizer("src/main/resources/model/pku_198801_ner.bin")
    );

    //使用模型
    perceptronLexicalAnalyzer.enableCustomDictionary(false);
    System.out.println(perceptronLexicalAnalyzer.analyze("华北电力公司董事长谭旭光和秘书胡花蕊来到美国纽约现代艺术博物馆参观"));
    //[华北/ns 电力/n 公司/n]/nt 董事长/n 谭旭光/nr 和/c 秘书/n 胡花蕊/nr 来到/v [美国/ns 纽约/ns 现代/t 艺术/n 博物馆/n]/ns 参观/v


    //在线学习
    System.out.println(perceptronLexicalAnalyzer.analyze("与特朗普通电话讨论太空探索技术公司"));

    Sentence sentence = Sentence.create("与/c 特朗普/nr 通/v 电话/n 讨论/v [太空/s 探索/vn 技术/n 公司/n]/nt");
    for (int i = 0; i < 20; i++) {
        if (perceptronLexicalAnalyzer.analyze(sentence.text()).equals(sentence)) break;
        perceptronLexicalAnalyzer.learn(sentence);
    }
    System.out.println(perceptronLexicalAnalyzer.analyze("与特朗普通电话讨论太空探索技术公司"));
}