Package weka.core.stemmers

Examples of weka.core.stemmers.ArabicStemmerKhoja

32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
        StanfordParser theParser = new StanfordParser(Language.Arabic);
        ParsingOptions opts = new ParsingOptions();
        opts.setPosTag(true);
        ArrayList<Word> textWords;
        ParsedData parsedOut;
        ArabicStemmerKhoja arabicStemmer = new ArabicStemmerKhoja();
        // Convert the Example into a tagged Stems Array
        textWords = StringToWordsTokenizer.tokenize(example.getDataBody());
        example.getDataBody();
        parsedOut = theParser.parse(textWords, opts);
        for (int i = 0; i < parsedOut.getTaggedWords().size(); i++) {
            temp = new TaggedStem();
            temp.setStemTag(parsedOut.getTaggedWords().get(i).getWordTag());
            temp.setTheStem(arabicStemmer.stem(textWords.get(i).word()));

            if (!taggedStems.contains(temp)) {
                taggedStems.add(temp);
            }
        }
View Full Code Here
32
33
34
35
36
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
        StanfordParser theParser = new StanfordParser(Language.Arabic);
        ParsingOptions opts = new ParsingOptions();
        opts.setPosTag(true);
        ArrayList<Word> textWords;
        ParsedData parsedOut;
        ArabicStemmerKhoja arabicStemmer = new ArabicStemmerKhoja();
        for (DataUnit textUnit : positiveExs) {
            textWords = StringToWordsTokenizer.tokenize(textUnit.getDataBody());
            textUnit.getDataBody();
            parsedOut = theParser.parse(textWords, opts);
            for (int i = 0; i < parsedOut.getTaggedWords().size(); i++) {
                temp = new TaggedStem();
                temp.setStemTag(parsedOut.getTaggedWords().get(i).getWordTag());
                temp.setTheStem(arabicStemmer.stem(textWords.get(i).word()));

                if (!taggedStems.contains(temp)) {
                    taggedStems.add(temp);
                }
            }
        }
        for (DataUnit textUnit : negativeExs) {
            textWords = StringToWordsTokenizer.tokenize(textUnit.getDataBody());
            textUnit.getDataBody();
            parsedOut = theParser.parse(textWords, opts);
            for (int i = 0; i < parsedOut.getTaggedWords().size(); i++) {
                temp = new TaggedStem();
                temp.setStemTag(parsedOut.getTaggedWords().get(i).getWordTag());
                temp.setTheStem(arabicStemmer.stem(textWords.get(i).word()));

                if (!taggedStems.contains(temp)) {
                    taggedStems.add(temp);
                }
            }
View Full Code Here
TOP

Related Classes of weka.core.stemmers.ArabicStemmerKhoja

  • seekfeel.miners.features.computers.BinaryComputerTaggedStem
  • seekfeel.miners.features.extractors.TaggedStemsExtractor
    • 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.