public void getIndexInfo(String indexdir, int freqThreshold) {
IndexReader reader = null;
try {
Directory dir = FSDirectory.open(new File(indexdir));
System.out.println(dir);
reader = IndexReader.open(dir);
System.out.println("document num:" + reader.numDocs());
System.out.println("======================");
TermEnum terms = reader.terms();
sortedTermQueue.clear();
maxDocNum = reader.maxDoc();
linkMap.clear();
termList.clear();
while (terms.next()) {
// System.out.print(terms.term() + "\tDocFreq:" +
TermDocs termDocs = reader.termDocs(terms.term());
MyTerm temp = new MyTerm(terms.term(), termDocs, maxDocNum);
if (temp.totalFreq < freqThreshold) {
continue;
} /*
* if(temp.originTrem.text().length()==1){ continue; }
*/
linkMap.put(temp.originTrem.text(), temp);
sortedTermQueue.add(temp);
termList.add(temp);
}
System.out.println("total Size:" + sortedTermQueue.size());
System.out.println("mapsize:" + linkMap.keySet().size());
// System.exit(0);
int num = 0;
this.maxFreq = sortedTermQueue.peek().totalFreq;
while (!sortedTermQueue.isEmpty()) {
num++;
System.out.println(num + ":" + sortedTermQueue.poll());
}
System.out.println("read index info done");
} catch (IOException e) {
e.printStackTrace();
} finally {
try {
reader.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
public JSONArray Cluster(String wekaFilePath, int clusterNum) throws Exception {
File inputFile = new File(wekaFilePath);
ArffLoader arf = new ArffLoader();
arf.setFile(inputFile);
Instances originIns = arf.getDataSet();
Instances insTest = new Instances(originIns);
insTest.deleteStringAttributes();
int totalNum = insTest.numInstances();
// SimpleKMeans sm = new SimpleKMeans();
EM em = new EM();
em.setNumClusters(clusterNum);
MakeDensityBasedClusterer sm = new MakeDensityBasedClusterer();
sm.setClusterer(em);
sm.buildClusterer(insTest);
System.out.println("totalNum:" + insTest.numInstances());
System.out.println("============================");
System.out.println(sm.toString());
Map<Integer, ArrayList<String>> result = new HashMap<Integer, ArrayList<String>>();
for (int i = 0; i < clusterNum; i++) {
result.put(i, new ArrayList<String>());
}
for (int i = 0; i < totalNum; i++) {
Instance ins = originIns.instance(i);
String word = ins.stringValue(0);
Instance tempIns = new Instance(ins);
tempIns.deleteAttributeAt(0);
int cluster = sm.clusterInstance(tempIns);
result.get(cluster).add(word);
}
// print the result
ArrayList<String> words = new ArrayList<String>();
JSONArray keyWords = new JSONArray();
for (int k : result.keySet()) {
words = result.get(k);
PriorityQueue<MyTerm> clusterQueue = new PriorityQueue<MyTerm>(1, MyTermCompare);
for (int i = 0; i < words.size(); i++) {
String s = words.get(i);
assert linkMap.containsKey(s);
int freq = linkMap.get(s).totalFreq;
clusterQueue.add(linkMap.get(s));
words.set(i, "(" + s + ":" + freq + ")");
}
JSONArray clusterArray = new JSONArray();
int num = clusterQueue.size() / 10 + 1; // 5%
int totalFreq = 0;
int totalLength = 0;
for (int i = 0; i < num && !clusterQueue.isEmpty(); ) {
JSONObject mem = new JSONObject();
MyTerm myTerm = clusterQueue.poll();
String word = myTerm.originTrem.text();
if (word.length() == 1) {
continue;
}
mem.put("text", word);
mem.put("freq", myTerm.totalFreq);
clusterArray.put(mem);
i++;
totalFreq += myTerm.totalFreq;
totalLength += word.length();
}
double averFreq = totalFreq * 1.0 / num;
double averLength = totalLength * 1.0 / num;
int count = 0;
while (!clusterQueue.isEmpty() && count < num) {
MyTerm myTerm = clusterQueue.poll();
String word = myTerm.originTrem.text();
int freq = myTerm.totalFreq;
int times = (int) (word.length() / averFreq) + 1;
if (freq > averFreq / times) {
JSONObject mem = new JSONObject();
mem.put("text", word);
mem.put("freq", freq);
mem.put("extra", true);
clusterArray.put(mem);
}
}
keyWords.put(clusterArray);
System.out.println(
"cluster" + k + ":" + words.size() + ":\t" + (int) (words.size() * 1.0 / totalNum * 100));
if (result.get(k).size() < 100) {
System.out.println(result.get(k));
}
}
// System.out.println("errorNum:"+errorNum);
return keyWords;
}