Menu
▾
▴
[DL-Learner SVN] SF.net SVN: dl-learner:[1735] trunk/src/dl-learner/org/dllearner/scripts/ matching
|
From: <ku...@us...> - 2009-05-05 11:52:41
|
Revision: 1735
http://dl-learner.svn.sourceforge.net/dl-learner/?rev=1735&view=rev
Author: kurzum
Date: 2009-05-05 11:52:27 +0000 (Tue, 05 May 2009)
Log Message:
-----------
code for testing existing matching
Added Paths:
-----------
trunk/src/dl-learner/org/dllearner/scripts/matching/LearnCriteria.java
trunk/src/dl-learner/org/dllearner/scripts/matching/Mcollect.java
trunk/src/dl-learner/org/dllearner/scripts/matching/Pcollect.java
trunk/src/dl-learner/org/dllearner/scripts/matching/SameCollect.java
Added: trunk/src/dl-learner/org/dllearner/scripts/matching/LearnCriteria.java
===================================================================
--- trunk/src/dl-learner/org/dllearner/scripts/matching/LearnCriteria.java (rev 0)
+++ trunk/src/dl-learner/org/dllearner/scripts/matching/LearnCriteria.java 2009-05-05 11:52:27 UTC (rev 1735)
@@ -0,0 +1,120 @@
+package org.dllearner.scripts.matching;
+
+import java.io.BufferedReader;
+import java.io.InputStreamReader;
+import java.net.URL;
+import java.net.URLConnection;
+import java.util.ArrayList;
+import java.util.SortedSet;
+import java.util.TreeSet;
+
+import org.dllearner.kb.sparql.Cache;
+import org.dllearner.kb.sparql.SPARQLTasks;
+import org.dllearner.kb.sparql.SparqlEndpoint;
+import org.dllearner.utilities.CSVFileToArray;
+import org.dllearner.utilities.datastructures.StringTuple;
+
+import com.wcohen.ss.Jaro;
+import com.wcohen.ss.api.StringDistance;
+
+public class LearnCriteria {
+ ArrayList<SameCollect>sameAs =new ArrayList<SameCollect>() ;
+ Mcollect m ;
+ /**
+ * @param args
+ */
+ public static void main(String[] args) {
+ LearnCriteria lc = new LearnCriteria();
+ @SuppressWarnings("unused")
+ StringDistance distance = new Jaro();
+ try{
+ CSVFileToArray csv = new CSVFileToArray("osmdata/owlsameas_en.csv");
+ ArrayList<String> al =null ;
+
+ while ((al = csv.next()) != null){
+ //System.out.println(al);
+ if(al.size()!=2)continue;
+ //if(distance.score(al.get(0), al.get(1))>=0.7){
+ //System.out.println(distance.score(al.get(0), al.get(1)));
+ //System.out.println(al);
+ //}
+ //String dbpedia = al.get(1).replace("%25", "%");
+ String dbpedia = al.get(1);
+ lc.sameAs.add(new SameCollect(al.get(0), dbpedia));
+ }
+ }catch (Exception e) {
+ e.printStackTrace();
+ }
+
+ Mcollect m = new Mcollect();
+ SPARQLTasks dbpedia = new SPARQLTasks(new Cache("matching"), SparqlEndpoint.getEndpointLOCALDBpedia());
+ int countzerold = 0;
+ int countzerodb = 0;
+ for (int x = 0; x<lc.sameAs.size();x++) {
+ SameCollect s = lc.sameAs.get(x);
+ String query = "SELECT * WHERE {<"+s.db+"> ?p ?o}";
+ s.dbdata = dbpedia.queryAsRDFNodeTuple(query, "?p", "?o");
+ s.lddata = lc.getLinkedData(s.ld);
+// System.exit(0);
+// System.out.println(s.lddata);
+// for (StringTuple string : s.lddata ) {
+// System.out.println(string);
+// }
+ m.add(s);
+ if(s.dbdata.size() == 0){
+ System.out.println(s.db);
+ countzerodb+=1;
+ }
+ //if( s.lddata.size() == 0)countzerold+=1;
+// if(x>110) break;
+ System.out.println(x);
+ }
+
+ System.out.println(countzerodb);
+ System.out.println(countzerold);
+ // System.exit(0);
+
+ System.out.println(m);
+ //System.out.println(lc.sameAs);
+ //System.out.println(lc.sameAs.size());
+
+
+ }
+
+ public SortedSet<StringTuple> getLinkedData(String url){
+ SortedSet<StringTuple> result = new TreeSet<StringTuple>();
+ try{
+ URL linkedGeoDataURL = new URL(url);
+
+ URLConnection conn = linkedGeoDataURL.openConnection();
+ BufferedReader rd = new BufferedReader(new InputStreamReader(conn.getInputStream()));
+ String line="";
+ @SuppressWarnings("unused")
+ boolean oneLine = false;
+ while ((line = rd.readLine()) != null)
+
+ { oneLine = true;
+// System.out.println(line);continue;
+ line = line.replace("<"+url+"#id>", "");
+ line = line.replace("<"+url+">", "");
+
+
+ String p = line.substring(line.indexOf("<")+1,line.indexOf(">") );
+ line = line.substring(line.indexOf(">")+1);
+ line = line.substring(0,line.lastIndexOf("."));
+ line = line.trim();
+ line = line.substring(1);
+ String o = line.substring(0,line.length()-1);
+// System.out.println(new StringTuple(p,o));
+ result.add(new StringTuple(p,o));
+ }
+
+ rd.close();
+
+ }catch (Exception e) {
+ e.printStackTrace();
+ }
+ return result;
+ }
+
+}
Added: trunk/src/dl-learner/org/dllearner/scripts/matching/Mcollect.java
===================================================================
--- trunk/src/dl-learner/org/dllearner/scripts/matching/Mcollect.java (rev 0)
+++ trunk/src/dl-learner/org/dllearner/scripts/matching/Mcollect.java 2009-05-05 11:52:27 UTC (rev 1735)
@@ -0,0 +1,63 @@
+package org.dllearner.scripts.matching;
+
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+
+import org.dllearner.utilities.datastructures.RDFNodeTuple;
+import org.dllearner.utilities.datastructures.StringTuple;
+
+import com.wcohen.ss.Jaro;
+import com.wcohen.ss.api.StringDistance;
+
+public class Mcollect {
+ String name;
+ List<Pcollect> props = new ArrayList<Pcollect>();
+
+
+ public void add(SameCollect s){
+ StringDistance distance = new Jaro();
+
+ for (RDFNodeTuple db : s.dbdata) {
+ for (StringTuple ld : s.lddata) {
+// System.out.println(ld.b);
+// System.out.println(db.b.toString());
+// System.out.println(istance.score(ld.b,db.b.toString()));
+ if ( distance.score(ld.b,db.b.toString())>=0.90){
+ boolean found = false;
+ for (Pcollect p : props){
+
+ if(p.ldp.equals(ld.a) && p.dbp.equals( db.a.toString())){
+ p.count +=1;
+ found = true;
+ }
+ }
+ if(found==false){
+ props.add(new Pcollect(ld.a, db.a.toString()));
+ }
+
+
+ };
+
+ }
+ }
+ }
+
+ @SuppressWarnings("unchecked")
+ @Override
+ public String toString(){
+ //SortedSet<Pcollect> s = new TreeSet<Pcollect>();
+// for(Pcollect one : s){
+// s.add(one);
+//
+// }
+ String ret = "";
+ Collections.sort(props );
+ for(int a=0; a<props.size();a++){
+
+ ret+= props.get(a).toString()+"\n";
+
+ }
+ return ret;
+ }
+}
Added: trunk/src/dl-learner/org/dllearner/scripts/matching/Pcollect.java
===================================================================
--- trunk/src/dl-learner/org/dllearner/scripts/matching/Pcollect.java (rev 0)
+++ trunk/src/dl-learner/org/dllearner/scripts/matching/Pcollect.java 2009-05-05 11:52:27 UTC (rev 1735)
@@ -0,0 +1,34 @@
+package org.dllearner.scripts.matching;
+
+public class Pcollect implements Comparable<Pcollect>{
+
+ String ldp;
+ String dbp;
+ int count=1;
+
+
+
+
+ public Pcollect(String ldp, String dbp) {
+ super();
+ this.ldp = ldp.trim();
+ this.dbp = dbp.trim();
+ }
+
+
+ @Override
+ public String toString(){
+ String ret = "count : "+count+" : "+ldp+ " = "+dbp;
+
+ return ret;
+ }
+
+ public int compareTo(Pcollect in){
+
+ Pcollect other = (Pcollect) in;
+ if(this.count==other.count)return 0;
+ if( this.count>other.count){
+ return -1;
+ }else {return 1;}
+ }
+}
Added: trunk/src/dl-learner/org/dllearner/scripts/matching/SameCollect.java
===================================================================
--- trunk/src/dl-learner/org/dllearner/scripts/matching/SameCollect.java (rev 0)
+++ trunk/src/dl-learner/org/dllearner/scripts/matching/SameCollect.java 2009-05-05 11:52:27 UTC (rev 1735)
@@ -0,0 +1,23 @@
+package org.dllearner.scripts.matching;
+
+import java.util.SortedSet;
+
+import org.dllearner.utilities.datastructures.RDFNodeTuple;
+import org.dllearner.utilities.datastructures.StringTuple;
+
+public class SameCollect {
+
+ String ld;
+ String db;
+
+ SortedSet<RDFNodeTuple> dbdata;
+ SortedSet<StringTuple> lddata;
+
+ public SameCollect(String ld, String db) {
+ super();
+ this.ld = ld;
+ this.db = db;
+ }
+
+
+}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
