知识图谱入门pdf

知识图谱入门pdf

import java.io.*;
import java.util.HashMap;
import java.util.HashSet;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * Created by Dell on 2017/11/3.
 */
public class Assignment4Class3 {

    //任务2中过滤实体用的可选属性
    enum CleanAttr {
        ABSTRACT（“摘要“0） CATEGORY（“类别“1） NAME（“名字“2） SECTION（“宗派“3）;

        private String name ;
        private int index ;

        private CleanAttr（ String name  int index ）{
            this.name = name ;
            this.index = index ;
        }

        public String getName（） {
            return name;
        }
        public int getIndex（） {
            return index;
        }
    }

    /**********************************************************************
     * 给定字符串与正则表达式，打印所有匹配的子串
     * String str : 带匹配的字符串
     * String regex : 模板（正则表达式）
     **********************************************************************/
    public void extract（String str String regex） {
        Pattern pattern = Pattern.compile（regex）;
        Matcher matcher = pattern.matcher（str）;
        while （matcher.find（）） {
            System.out.println（matcher.group（））;
        }
    }

    /**********************************************************************
     * 给定知识库的abstract文件与正则表达式，使用正则从abstract中抽取属性值，每抽出一条属性值打印一行abstract一行属性的主语、宾语对
     * String input : 实体abstract属性文件的完整路径
     * String regex : 模板
     **********************************************************************/
    public void extractFromFile（String input String regex） throws IOException {
        Pattern pattern = Pattern.compile（regex）;
        BufferedReader br = new BufferedReader（new InputStreamReader（new FileInputStream（input） “utf-8“））;
        String line = ““;
        while （（line=br.readLine（））!=null） {
            String subject = line.split（“/resource/“）[1].split（“> <“）[0];
            String sentence = line.split（“> \““）[1].split（“\““）[0];
            Matcher matcher = pattern.matcher（sentence）;
            while （matcher.find（）） {
                System.out.println（“sentence: “+sentence）;
                System.out.println（“relation: “+subject+“\t:\t“+matcher.group（））;
            }
        }
        br.close（）;
    }

    /**********************************************************************
     * 给定人工标注文件路径和阈值，被标注为正确实体的次数不小于阈值则被视为正确实体返回，否则被视为错误实体打印出来
     * String path : 人工标注结果文件的路径
     * int threshold : 阈值
     **********************************************************************/
    public HashSet clean（String path int threshold） throws IOException {
        HashSet result = new HashSet<>（）;
        HashMap countMap = new HashMap<>（）;
        File[] fileList = new File（path）.listFiles（）;
        for （File file:fileList）{
            BufferedReader br = new BufferedReader（new InputStreamReader（new FileInputStream（path+file.getName（））“utf-8“））;
            String line = ““;
            while （（li

 属性            大小     日期    时间   名称
----------- ---------  ---------- -----  ----

     文件        273  2017-11-03 18:41  资料\Assignment\Assignment\.idea\misc.xml

     文件        260  2017-11-03 18:40  资料\Assignment\Assignment\.idea\modules.xml

     文件      31996  2017-11-03 22:51  资料\Assignment\Assignment\.idea\workspace.xml

     文件        502  2017-11-03 18:42  资料\Assignment\Assignment\Assignment.iml

     文件     632610  2017-11-03 20:23  资料\Assignment\Assignment\out\production\Assignment\Assignment1\abstracts.ttl

     文件    1773471  2017-11-03 20:23  资料\Assignment\Assignment\out\production\Assignment\Assignment2\abstracts.ttl

     文件     152910  2017-11-03 20:23  资料\Assignment\Assignment\out\production\Assignment\Assignment2\aliases.ttl

     文件    2292411  2017-11-03 20:23  资料\Assignment\Assignment\out\production\Assignment\Assignment2\categories.ttl

     文件     199701  2017-11-03 20:23  资料\Assignment\Assignment\out\production\Assignment\Assignment2\entities.txt

     文件      86476  2017-11-03 20:23  资料\Assignment\Assignment\out\production\Assignment\Assignment2\entities_labeled\1.txt

     文件     142152  2017-11-03 20:23  资料\Assignment\Assignment\out\production\Assignment\Assignment2\entities_labeled\2.txt

     文件      69384  2017-11-03 20:23  资料\Assignment\Assignment\out\production\Assignment\Assignment2\entities_labeled\3.txt

     文件     101518  2017-11-03 20:23  资料\Assignment\Assignment\out\production\Assignment\Assignment2\entities_labeled\4.txt

     文件     101740  2017-11-03 20:23  资料\Assignment\Assignment\out\production\Assignment\Assignment2\sections.ttl

     文件       1524  2017-11-03 22:51  资料\Assignment\Assignment\out\production\Assignment\Assignment4Class3$CleanAttr.class

     文件       6349  2017-11-03 22:51  资料\Assignment\Assignment\out\production\Assignment\Assignment4Class3.class

     文件       3073  2017-11-03 22:48  资料\Assignment\Assignment\readme.md

     文件     632610  2017-08-09 19:16  资料\Assignment\Assignment\resource\Assignment1\abstracts.ttl

     文件    1773471  2017-08-14 10:56  资料\Assignment\Assignment\resource\Assignment2\abstracts.ttl

     文件     152910  2017-10-31 18:07  资料\Assignment\Assignment\resource\Assignment2\aliases.ttl

     文件    2292411  2017-08-14 10:58  资料\Assignment\Assignment\resource\Assignment2\categories.ttl

     文件     199701  2017-08-14 10:37  资料\Assignment\Assignment\resource\Assignment2\entities.txt

     文件      86476  2017-08-14 10:38  资料\Assignment\Assignment\resource\Assignment2\entities_labeled\1.txt

     文件     142152  2017-08-14 10:39  资料\Assignment\Assignment\resource\Assignment2\entities_labeled\2.txt

     文件      69384  2017-08-14 10:39  资料\Assignment\Assignment\resource\Assignment2\entities_labeled\3.txt

     文件     101518  2017-08-14 10:39  资料\Assignment\Assignment\resource\Assignment2\entities_labeled\4.txt

     文件     101740  2017-10-31 18:56  资料\Assignment\Assignment\resource\Assignment2\sections.ttl

     文件       8455  2017-11-03 22:50  资料\Assignment\Assignment\src\Assignment4Class3.java

     文件        182  2017-11-03 20:25  资料\Assignment\__MACOSX\._Assignment

     文件        182  2017-11-03 18:41  资料\Assignment\__MACOSX\Assignment\.idea\._misc.xml

............此处省略405个文件信息