Examples of TaggedStem

Examples of seekfeel.miners.features.TaggedStem

26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
    @Override
    public LinkedHashMap<Integer, Double> computeFeatures(DataUnit example, ArrayList<Feature> features, CorpusHolder corpus) {
        LinkedHashMap<Integer, Double> featuresValues = new LinkedHashMap<Integer, Double>();
        ArrayList<Feature> taggedStems = new ArrayList<Feature>();
        TaggedStem temp;
        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

Examples of seekfeel.miners.features.TaggedStem

26
27
28
29
30
31
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
    @Override
    public ArrayList<Feature> extractFeatures(CorpusHolder corpus) {
        ArrayList<DataUnit> positiveExs = corpus.getPositiveExamples();
        ArrayList<DataUnit> negativeExs = corpus.getNegativeExamples();
        ArrayList<Feature> taggedStems = new ArrayList<Feature>();
        TaggedStem temp;
        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
Copyright © 2018 www.massapi.com. 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.