public weka.classifiers.Classifier getClassifier() throws Exception {
StringToWordVector stwv = new StringToWordVector();
stwv.setTFTransform(hasParam(Constant.RUNTIME_PARAMS.USE_TFIDF));
stwv.setIDFTransform(hasParam(Constant.RUNTIME_PARAMS.USE_TFIDF));
stwv.setLowerCaseTokens(hasParam(Constant.RUNTIME_PARAMS.CONV_LOWERCASE));
stwv.setUseStoplist(hasParam(Constant.RUNTIME_PARAMS.REM_STOP_WORDS));
stwv.setOutputWordCounts(hasParam(Constant.RUNTIME_PARAMS.USE_WORD_FREQ));
if (hasParam(Constant.RUNTIME_PARAMS.TRAIN_AND_TEST)) stwv.setInputFormat(getTrainData());
if (hasParam(Constant.RUNTIME_PARAMS.USE_BIGRAM)) {
NGramTokenizer tokenizer = new NGramTokenizer();
tokenizer.setNGramMinSize(2);
stwv.setTokenizer(tokenizer);
} else if (hasParam(Constant.RUNTIME_PARAMS.USE_TRIGRAM)) {
NGramTokenizer tokenizer = new NGramTokenizer();
tokenizer.setNGramMinSize(3);
stwv.setTokenizer(tokenizer);
}
if (hasParam(Constant.RUNTIME_PARAMS.USE_STEMMER)) {
SnowballStemmer stemmer = new SnowballStemmer("porter");
stwv.setStemmer(stemmer);
}
Logistic l = new Logistic();
FilteredClassifier cls = new FilteredClassifier();
cls.setClassifier(l);
cls.setFilter(stwv);
if (hasParam(Constant.RUNTIME_PARAMS.TRAIN_AND_TEST)) cls.buildClassifier(getTrainData());
return cls;
}
/**
* Make data sets and train and test model
*
* @param filePathTrain
* @param filePathTest
* @param gram
*/
public static void makeDataSet(String filePathTrain, String filePathTest, int gram) {
TextDirectoryLoader loader = new TextDirectoryLoader();
try {
loader.setDirectory(new File(filePathTrain));
Instances dataRawTrain = loader.getDataSet();
loader.setDirectory(new File(filePathTest));
Instances dataRawTest = loader.getDataSet();
StringToWordVector filter = new StringToWordVector();
NGramTokenizer tokeniser = new NGramTokenizer();
tokeniser.setNGramMinSize(gram);
tokeniser.setNGramMaxSize(gram);
filter.setTokenizer(tokeniser);
filter.setInputFormat(dataRawTrain);
Instances train = Filter.useFilter(dataRawTrain, filter);
// filter.setInputFormat(dataRawTest);
Instances test = Filter.useFilter(dataRawTest, filter);
/**
* *
*
* <p>Replace this function each time to change models
*/
trainModelNaiveBayes(train, test);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}