Package opennlp.tools.cmdline

Examples of opennlp.tools.cmdline.PerformanceMonitor

52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
      ChunkerME chunker = new ChunkerME(model, ChunkerME.DEFAULT_BEAM_SIZE);

      ObjectStream<String> lineStream =
        new PlainTextByLineStream(new InputStreamReader(System.in));

      PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
      perfMon.start();

      try {
        String line;
        while ((line = lineStream.read()) != null) {

          POSSample posSample;
          try {
            posSample = POSSample.parse(line);
          } catch (InvalidFormatException e) {
            System.err.println("Invalid format:");
            System.err.println(line);
            continue;
          }

          String[] chunks = chunker.chunk(posSample.getSentence(),
              posSample.getTags());

          System.out.println(new ChunkSample(posSample.getSentence(),
              posSample.getTags(), chunks).nicePrint());

          perfMon.incrementCounter();
        }
      }
      catch (IOException e) {
        CmdLineUtil.handleStdinIoError(e);
      }

      perfMon.stopAndPrintFinalResult();
    }
  }
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
          ParserFactory.create(model, beamSize, advancePercentage);

      ObjectStream<String> lineStream =
        new PlainTextByLineStream(new InputStreamReader(System.in));

      PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
      perfMon.start();

      try {
        String line;
        while ((line = lineStream.read()) != null) {
          if (line.length() == 0) {
            System.out.println();
          }
          else {
            Parse[] parses = parseLine(line, parser, numParses);

            for (int pi=0,pn=parses.length;pi<pn;pi++) {
              if (showTopK) {
                System.out.print(pi+" "+parses[pi].getProb()+" ");
              }

              parses[pi].show();

              perfMon.incrementCounter();
            }
          }
        }
      }
      catch (IOException e) {
        CmdLineUtil.handleStdinIoError(e);
      }

      perfMon.stopAndPrintFinalResult();
    }
  }
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
      POSModel model = new POSModelLoader().load(new File(args[0]));

      POSTaggerME tagger = new POSTaggerME(model);

      ObjectStream<String> lineStream = null;
      PerformanceMonitor perfMon = null;

      try {
        lineStream = new PlainTextByLineStream(new SystemInputStreamFactory(), SystemInputStreamFactory.encoding());
        perfMon = new PerformanceMonitor(System.err, "sent");
        perfMon.start();
        String line;
        while ((line = lineStream.read()) != null) {

          String whitespaceTokenizerLine[] = WhitespaceTokenizer.INSTANCE.tokenize(line);
          String[] tags = tagger.tag(whitespaceTokenizerLine);

          POSSample sample = new POSSample(whitespaceTokenizerLine, tags);
          System.out.println(sample.toString());

          perfMon.incrementCounter();
        }
      } catch (IOException e) {
        CmdLineUtil.handleStdinIoError(e);
      }

      perfMon.stopAndPrintFinalResult();
    }
  }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
      }
      catch (Exception e) {
        throw new TerminateToolException(-1, "Failed to instantiate the Entity Linker: " + e.getMessage());
      }

      PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
      perfMon.start();

      try {

        ObjectStream<String> untokenizedLineStream = new PlainTextByLineStream(
            new SystemInputStreamFactory(), SystemInputStreamFactory.encoding());

        List<NameSample> document = new ArrayList<NameSample>();

        String line;
        while ((line = untokenizedLineStream.read()) != null) {

          if (line.trim().isEmpty()) {
            // Run entity linker ... and output result ...

            StringBuilder text = new StringBuilder();
            Span sentences[] = new Span[document.size()];
            Span[][] tokensBySentence = new Span[document.size()][];
            Span[][] namesBySentence = new Span[document.size()][];

            for (int i = 0; i < document.size(); i++) {

              NameSample sample = document.get(i);
             
              namesBySentence[i] = sample.getNames();
             
              int sentenceBegin = text.length();
             
              Span[] tokens = new Span[sample.getSentence().length];

              // for all tokens
              for (int ti = 0; ti < sample.getSentence().length; ti++) {
                int tokenBegin = text.length();
                text.append(sample.getSentence()[ti]);
                text.append(" ");
                tokens[i] = new Span(tokenBegin, text.length());
              }
             
              tokensBySentence[i] = tokens;
             
              sentences[i] = new Span(sentenceBegin, text.length());
              text.append("\n");
            }

            List<Span> linkedSpans = entityLinker.find(text.toString(), sentences, tokensBySentence, namesBySentence);

            for (int i = 0; i < linkedSpans.size(); i++) {
              System.out.println(linkedSpans.get(i));
            }

            perfMon.incrementCounter(document.size());
            document.clear();
          }
          else {
            document.add(NameSample.parse(line, false));
          }
        }
      }
      catch (IOException e) {
        CmdLineUtil.handleStdinIoError(e);
      }

      perfMon.stopAndPrintFinalResult();
    }
  }
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
      SentenceModel model = new SentenceModelLoader().load(new File(args[0]));

      SentenceDetectorME sdetector = new SentenceDetectorME(model);

      PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
      perfMon.start();

      try {
        ObjectStream<String> paraStream = new ParagraphStream(new PlainTextByLineStream(new SystemInputStreamFactory(),
            SystemInputStreamFactory.encoding()));

        String para;
        while ((para = paraStream.read()) != null) {

          String[] sents = sdetector.sentDetect(para);
          for (String sentence : sents) {
            System.out.println(sentence);
          }

          perfMon.incrementCounter(sents.length);

          System.out.println();
        }
      }
      catch (IOException e) {
        CmdLineUtil.handleStdinIoError(e);
      }

      perfMon.stopAndPrintFinalResult();
    }
  }
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
  void process() {
    ObjectStream<String> untokenizedLineStream = null;

    ObjectStream<String> tokenizedLineStream = null;
    PerformanceMonitor perfMon = null;
    try {
      untokenizedLineStream =
              new PlainTextByLineStream(new SystemInputStreamFactory(), SystemInputStreamFactory.encoding());

      tokenizedLineStream = new WhitespaceTokenStream(
              new TokenizerStream(tokenizer, untokenizedLineStream));

      perfMon = new PerformanceMonitor(System.err, "sent");
      perfMon.start();


      String tokenizedLine;
      while ((tokenizedLine = tokenizedLineStream.read()) != null) {
        System.out.println(tokenizedLine);
        perfMon.incrementCounter();
      }
    } catch (IOException e) {
      CmdLineUtil.handleStdinIoError(e);
    }

    perfMon.stopAndPrintFinalResult();
  }
View Full Code Here
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
      TokenNameFinderEvaluator evaluator = new TokenNameFinderEvaluator(nameFinder);

      final NameSampleDataStream sampleStream = new NameSampleDataStream(
          new PlainTextByLineStream(new InputStreamReader(new FileInputStream(args[2]), args[1])));

      final PerformanceMonitor monitor = new PerformanceMonitor("sent");

      monitor.startAndPrintThroughput();

      ObjectStream<NameSample> iterator = new ObjectStream<NameSample>() {

        public NameSample read() throws IOException {
          monitor.incrementCounter();
          return sampleStream.read();
        }

        public void reset() throws IOException {
          sampleStream.reset();
        }

        public void close() throws IOException {
          sampleStream.close();
        }
      };

      evaluator.evaluate(iterator);

      monitor.stopAndPrintFinalResult();

      System.out.println();
      System.out.println("F-Measure: " + evaluator.getFMeasure().getFMeasure());
      System.out.println("Recall: " + evaluator.getFMeasure().getRecallScore());
      System.out.println("Precision: " + evaluator.getFMeasure().getPrecisionScore());
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
    DocumentCategorizerEvaluator evaluator = new DocumentCategorizerEvaluator(
        new DocumentCategorizerME(model),
        listeners.toArray(new DoccatEvaluationMonitor[listeners.size()]));

    final PerformanceMonitor monitor = new PerformanceMonitor("doc");

    ObjectStream<DocumentSample> measuredSampleStream = new ObjectStream<DocumentSample>() {

      public DocumentSample read() throws IOException {
        monitor.incrementCounter();
        return sampleStream.read();
      }

      public void reset() throws IOException {
        sampleStream.reset();
      }

      public void close() throws IOException {
        sampleStream.close();
      }
    };

    monitor.startAndPrintThroughput();

    try {
      evaluator.evaluate(measuredSampleStream);
    } catch (IOException e) {
      System.err.println("failed");
      throw new TerminateToolException(-1, "IO error while reading test data: "
          + e.getMessage(), e);
    } finally {
      try {
        measuredSampleStream.close();
      } catch (IOException e) {
        // sorry that this can fail
      }
    }

    monitor.stopAndPrintFinalResult();

    System.out.println();

    System.out.println(evaluator);
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
          new DetokenizationDictionaryLoader().load(new File(args[0])));

      ObjectStream<String> tokenizedLineStream =
        new PlainTextByLineStream(new SystemInputStreamFactory(), SystemInputStreamFactory.encoding());

      PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
      perfMon.start();


        String tokenizedLine;
        while ((tokenizedLine = tokenizedLineStream.read()) != null) {

          // white space tokenize line
          String tokens[] = WhitespaceTokenizer.INSTANCE.tokenize(tokenizedLine);

          System.out.println(detokenizer.detokenize(tokens, null));

          perfMon.incrementCounter();
        }
              perfMon.stopAndPrintFinalResult();
      }
      catch (IOException e) {
        CmdLineUtil.handleStdinIoError(e);
      }
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
      /**
       * moved initialization to the try block to catch new IOException
       */
      ObjectStream<String> documentStream;

      PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "doc");
      perfMon.start();

      try {
        documentStream = new ParagraphStream(
                new PlainTextByLineStream(new SystemInputStreamFactory(), SystemInputStreamFactory.encoding()));
        String document;
        while ((document = documentStream.read()) != null) {
          String[] tokens = model.getFactory().getTokenizer().tokenize(document);

          double prob[] = doccat.categorize(tokens);
          String category = doccat.getBestCategory(prob);

          DocumentSample sample = new DocumentSample(category, tokens);
          System.out.println(sample.toString());

          perfMon.incrementCounter();
        }
      } catch (IOException e) {
        CmdLineUtil.handleStdinIoError(e);
      }

      perfMon.stopAndPrintFinalResult();
    }
  }
View Full Code Here
TOP

Related Classes of opennlp.tools.cmdline.PerformanceMonitor

  • opennlp.tools.cmdline.chunker.ChunkerEvaluatorTool
  • opennlp.tools.cmdline.chunker.ChunkerMETool
  • opennlp.tools.cmdline.coref.CoreferencerTool
  • opennlp.tools.cmdline.doccat.DoccatEvaluatorTool
  • opennlp.tools.cmdline.doccat.DoccatTool
  • opennlp.tools.cmdline.entitylinker.EntityLinkerTool
  • opennlp.tools.cmdline.namefind.TokenNameFinderEvaluatorTool
  • opennlp.tools.cmdline.namefind.TokenNameFinderTool
  • opennlp.tools.cmdline.parser.ParserTool
  • opennlp.tools.cmdline.postag.POSTaggerTool
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.