/**
* selects a given number of features by info gain eval
*
* @param number the number of features to select
* @throws Exception
*/
public void selectFeatures(int number) throws Exception {
weka.filters.supervised.attribute.AttributeSelection filter =
new weka.filters.supervised.attribute.AttributeSelection();
InfoGainAttributeEval eval = new InfoGainAttributeEval();
Ranker search = new Ranker();
search.setNumToSelect(number);
filter.setEvaluator(eval);
filter.setSearch(search);
filter.setInputFormat(_train);
Instances newData = Filter.useFilter(_train, filter);
Instances newData_test = Filter.useFilter(_test, filter);
_train = newData;
_test = newData_test;
}
private double[] classify(String test) {
String[] lab = {
"I.2", "I.3", "I.5", "I.6", "I.2.1", "I.2.6", "I.2.8", "I.3.5", "I.3.6", "I.3.7", "I.5.1",
"I.5.2", "I.5.4", "I.6.3", "I.6.5", "I.6.8",
};
int NSel = 1000; // Number of selection
Filter[] filters = new Filter[2];
double[] x = new double[16];
double[] prd = new double[16];
double clsLabel;
Ranker rank = new Ranker();
Evaluation eval = null;
StringToWordVector stwv = new StringToWordVector();
weka.filters.supervised.attribute.AttributeSelection featSel =
new weka.filters.supervised.attribute.AttributeSelection();
WordTokenizer wtok = new WordTokenizer();
String delim = " \r\n\t.,;:'\"()?!$*-&[]+/|\\";
InfoGainAttributeEval ig = new InfoGainAttributeEval();
String[] stwvOpts;
wtok.setDelimiters(delim);
Instances[] dataRaw = new Instances[10000];
DataSource[] source = new DataSource[16];
String str;
Instances testset = null;
DataSource testsrc = null;
try {
testsrc = new DataSource(test);
testset = testsrc.getDataSet();
} catch (Exception e1) {
// TODO Auto-generated catch block
e1.printStackTrace();
}
for (int j = 0; j < 16; j++) // 16 element 0-15
{
try {
str = lab[j];
source[j] =
new DataSource(
"D:/Users/nma1g11/workspace2/WebScraperFlatNew/dataPernode/new/" + str + ".arff");
dataRaw[j] = source[j].getDataSet();
} catch (Exception e) {
e.printStackTrace();
}
System.out.println(lab[j]);
if (dataRaw[j].classIndex() == -1) dataRaw[j].setClassIndex(dataRaw[j].numAttributes() - 1);
}
if (testset.classIndex() == -1) testset.setClassIndex(testset.numAttributes() - 1);
try {
stwvOpts =
weka.core.Utils.splitOptions(
"-R first-last -W 1000000 -prune-rate -1.0 -C -T -I -N 1 -L -S -stemmer weka.core.stemmers.LovinsStemmer -M 2 ");
stwv.setOptions(stwvOpts);
stwv.setTokenizer(wtok);
rank.setOptions(weka.core.Utils.splitOptions("-T -1.7976931348623157E308 -N 100"));
rank.setNumToSelect(NSel);
featSel.setEvaluator(ig);
featSel.setSearch(rank);
} catch (Exception e) {
e.printStackTrace();
}
filters[0] = stwv;
filters[1] = featSel;
System.out.println("Loading is Done!");
MultiFilter mfilter = new MultiFilter();
mfilter.setFilters(filters);
FilteredClassifier classify = new FilteredClassifier();
classify.setClassifier(
new NaiveBayesMultinomial()); ///////// Algorithm of The Classification /////////
classify.setFilter(mfilter);
String ss2 = "";
try {
Classifier[] clsArr = new Classifier[16];
clsArr = Classifier.makeCopies(classify, 16);
String strcls = "";
List<String> clsList = new ArrayList<String>();
String s = null;
String newcls = null;
String lb = "";
String prev = "";
boolean flag = false;
String Ocls = null;
int q = 0;
for (int i = 0; i < 16; i++) {
for (int k = 0; k < testset.numInstances(); k++) {
flag = false;
s = testset.instance(k).stringValue(1);
clsList.add(s);
if (lab[i].equals(s)) {
flag = true;
newcls = s;
}
}
clsArr[i].buildClassifier(dataRaw[i]);
eval = new Evaluation(dataRaw[i]);
for (int j = 0; j < testset.numInstances(); j++) {
Ocls = testset.instance(j).stringValue(1);
if (flag && !s.equals(null)) testset.instance(j).setClassValue(lab[i]);
// -----------------------------------------
strcls = testset.instance(j).stringValue(1);
if (i < 4) {
if (strcls.substring(0, 3).equals(lab[i])) testset.instance(j).setClassValue(lab[i]);
} else if (lab[i].substring(0, 3).equals(strcls))
testset.instance(j).setClassValue(lab[i]);
// ------------------------------------------------
System.out.println(
dataRaw[i].classAttribute().value(i)
+ " --- > Correct%:"
+ eval.pctCorrect()
+ " F-measure:"
+ eval.fMeasure(i));
if (!prev.equals(testset.instance(j).stringValue(0)) || !lab[i].equals(lb)) {
clsLabel = clsArr[i].classifyInstance(testset.instance(j));
x = clsArr[i].distributionForInstance(testset.instance(j));
prd[i] = x[i];
System.out.println(" --- > prob: " + clsLabel);
System.out.println(" --- > x :" + x[i]);
System.out.println(clsLabel + " --> " + testset.classAttribute().value((int) clsLabel));
}
testset.instance(j).setClassValue(Ocls);
prev = testset.instance(j).stringValue(0);
lb = lab[i];
}
System.out.println("Done with " + lab[i].replace("99", "") + " !!!!!!!!!!!");
}
System.out.println(eval.correct());
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return prd;
}