/**
* @param args
* @throws Exception
*/
public static void main(String args[]) throws Exception {
log.setLevel(Level.INFO);
Configuration v_HadoopConf = new Configuration();
s_HadoopConf = v_HadoopConf;
s_Config = Config.getInstance();
String v_PathPrefix = s_Config.getBaseDir() + s_Config.getDataDir() + "mahout/";
String v_TextDir = s_Config.getTextPath();
Path m_DocumentDir = new Path(v_TextDir);
Path m_SequenceDir = new Path(v_PathPrefix, "sequence/");
Path m_TokensDir = new Path(v_PathPrefix, "tokens");
Path m_TF = new Path(v_PathPrefix, "termfreq/");
String m_VecFolder = "Vectors";
Path m_tf_idf = new Path(v_PathPrefix, "tfidf/");
boolean m_Sequential = true;
HadoopUtil.delete(v_HadoopConf, new Path(v_PathPrefix, "clusters/"));
if (!s_Config.getReuseTFIDF()) {
createTFIDF(
v_HadoopConf, m_DocumentDir, m_SequenceDir, m_TokensDir, m_TF, m_VecFolder, m_tf_idf);
}
HierarchicalKMeansClusterer v_Hkmc = new HierarchicalKMeansClusterer();
SetTree<ClusterDescriptor> v_Tree = v_Hkmc.run(s_HadoopConf, m_Sequential);
saveAsTree(v_Tree);
saveAsXml(v_Tree);
}
private static void saveAsXml(SetTree<ClusterDescriptor> v_Tree) throws FileNotFoundException {
try {
PrintStream v_PS = new PrintStream(s_Config.getOutputXmlFilename());
JAXBContext jaxbContext = JAXBContext.newInstance(SetTree.class);
Marshaller jaxbMarshaller = jaxbContext.createMarshaller();
// output pretty printed
jaxbMarshaller.setProperty(Marshaller.JAXB_FORMATTED_OUTPUT, true);
jaxbMarshaller.marshal(v_Tree, v_PS);
} catch (JAXBException e) {
e.printStackTrace();
}
}
private static void saveAsTree(SetTree<ClusterDescriptor> v_Tree) throws FileNotFoundException {
PrintStream v_PS = new PrintStream(s_Config.getOutputTreeFilename());
v_PS.println("Canopy T2 values: " + s_Config.getCanopyRanges());
v_PS.println();
Util.prettyPrint(v_Tree, v_PS);
}