Examples of opennlp.tools.namefind.NameSampleDataStream

opennlp.tools.namefind.NameSampleDataStream
The {@link NameSampleDataStream} class converts tagged {@link String}s provided by a {@link DataStream} to {@link NameSample} objects.It uses text that is is one-sentence per line and tokenized with names identified by <START> and <END> tags.

    
    //<start id="ne-namesample-type"/>
    String taggedSent = 
      "<START:person> Britney Spears <END> was reunited " +
      "with her sons <START:date> Saturday <END> ";
    ObjectStream<NameSample> nss = new NameSampleDataStream(
        new PlainTextByLineStream(new StringReader(taggedSent)));
    TokenNameFinderModel model = NameFinderME.train( 
        "en", 
        "default" ,
        nss,

View Full Code Here

  public void trainNameFinder() throws IOException {
    File baseDir = new File("src/test/resources");
    File destDir = new File("target");
    //<start id="ne-train"/>
    File inFile = new File(baseDir,"person.train");
    NameSampleDataStream nss = new NameSampleDataStream( //<co id="co.opennlp.name.initnamestream"/>
      new PlainTextByLineStream(
        new java.io.FileReader(inFile)));


    int iterations = 100;
    int cutoff = 5;

View Full Code Here

    </calloutlist>*/
    //<end id="ne-features"/>


    //<start id="ne-features-train"/>
    File inFile = new File(baseDir,"person.train");
    NameSampleDataStream nss = new NameSampleDataStream( //<co id="co.opennlp.name.initfeat"/>
      new PlainTextByLineStream(
        new java.io.FileReader(inFile)));


    int iterations = 100;
    int cutoff = 5;

View Full Code Here

          logger.log(Level.INFO, "Using additional training data file: " + additionalTrainingDataFile);
        }
        
        additionalTrainingDataIn = new FileInputStream(additionalTrainingDataFile);
        
        ObjectStream<NameSample> additionalSamples = new NameSampleDataStream(
            new PlainTextByLineStream(new InputStreamReader(additionalTrainingDataIn, additionalTrainingDataEncoding)));
        
        samples = ObjectStreamUtils.createObjectStream(samples, additionalSamples);
      }

View Full Code Here

    ObjectStream<String> lineStream;
    try {
      lineStream = new PlainTextByLineStream(new InputStreamReader(
          CmdLineUtil.openInFile(new File(params.getData())), params.getEncoding()));
      
      return new NameSampleDataStream(lineStream);
    } catch (UnsupportedEncodingException e) {
      System.err.println("Encoding not supported: " + params.getEncoding());
      throw new TerminateToolException(-1);
    }
  }

View Full Code Here

    FileInputStream sampleDataIn = CmdLineUtil.openInFile(sampleDataFile);


    ObjectStream<String> lineStream = new PlainTextByLineStream(sampleDataIn
        .getChannel(), encoding);


    return new NameSampleDataStream(lineStream);
  }

View Full Code Here

        }
        
        additionalTrainingDataIn = new FileInputStream(additionalTrainingDataFile);
        
        // TODO: Make encoding configurable, otherwise use UTF-8 as default!
        ObjectStream<NameSample> additionalSamples = new NameSampleDataStream(
            new PlainTextByLineStream(new InputStreamReader(additionalTrainingDataIn, additionalTrainingDataEncoding)));
        
        samples = ObjectStreamUtils.createObjectStream(samples, additionalSamples);
      }

View Full Code Here

    FileInputStream sampleDataIn = CmdLineUtil.openInFile(params.getData());


    ObjectStream<String> lineStream = new PlainTextByLineStream(sampleDataIn.getChannel(),
        params.getEncoding());


    return new NameSampleDataStream(lineStream);
  }

View Full Code Here

      lineStream = new PlainTextByLineStream((sampleDataIn), params.getEncoding());
    } catch (IOException ex) {
      CmdLineUtil.handleCreateObjectStreamError(ex);
    }


    return new NameSampleDataStream(lineStream);
  }

View Full Code Here

          logger.log(Level.INFO, "Using additional training data file: " + additionalTrainingDataFile);
        }


        additionalTrainingDataIn = new FileInputStream(additionalTrainingDataFile);


        ObjectStream<NameSample> additionalSamples = new NameSampleDataStream(
            new PlainTextByLineStream(new InputStreamReader(additionalTrainingDataIn, additionalTrainingDataEncoding)));


        samples = ObjectStreamUtils.createObjectStream(samples, additionalSamples);
      }

View Full Code Here

0 1

TOP

Related Classes of opennlp.tools.namefind.NameSampleDataStream

com.tamingtext.opennlp.NameFinderTest

opennlp.tools.cmdline.namefind.TokenNameFinderTrainerTool

opennlp.tools.formats.NameSampleDataStreamFactory

opennlp.tools.formats.NameSampleStreamFactory

opennlp.uima.namefind.NameFinderTrainer

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.