/**
* 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();
}
}
/**
* Parses a given list of options.
*
* <p>
* <!-- options-start -->
* Valid options are:
*
* <p>
*
* <pre> -D
* Enables debug output.
* (default: off)</pre>
*
* <pre> -F
* Stores the filename in an additional attribute.
* (default: off)</pre>
*
* <pre> -dir <directory>
* The directory to work on.
* (default: current directory)</pre>
*
* <pre> -charset <charset name>
* The character set to use, e.g UTF-8.
* (default: use the default character set)</pre>
*
* <pre> -R
* Retain all string attribute values when reading incrementally.</pre>
*
* <!-- options-end -->
*
* @param options the options
* @throws Exception if options cannot be set
*/
public void setOptions(String[] options) throws Exception {
setDebug(Utils.getFlag("D", options));
setOutputFilename(Utils.getFlag("F", options));
setDirectory(new File(Utils.getOption("dir", options)));
String charSet = Utils.getOption("charset", options);
m_charSet = "";
if (charSet.length() > 0) {
m_charSet = charSet;
}
setRetainStringValues(Utils.getFlag('R', options));
}