public static void RetrieveTrainMatrix() {
try {
BufferedReader flrdr =
new BufferedReader(
new FileReader("D:\\IR\\Assignment7\\Pytest\\part2\\output\\train_matrix.txt"));
String line = "";
int doc_count = 0;
while ((line = flrdr.readLine()) != null) {
SortedSet<Integer> word_ids = new TreeSet<Integer>();
int val_count = 0;
String[] key_value = line.split(" :: ");
key_value[1] = key_value[1].substring(1, key_value[1].length() - 2);
String[] values = key_value[1].split(",");
FeatureNode[] node = new FeatureNode[values.length];
for (String val : values) word_ids.add(Integer.parseInt(val.trim()));
for (int val : word_ids) node[val_count++] = new FeatureNode(val, 1);
if (spam_docs.contains(key_value[0].trim())) ylable[doc_count] = 1;
else ylable[doc_count] = 0;
train_matrix[doc_count++] = node;
}
flrdr.close();
} catch (Exception e) {
e.printStackTrace();
System.exit(0);
}
}
public static void WriteToFile() {
doc_score = sortByComparator(doc_score, false);
try {
FileWriter wrtr = new FileWriter("D:/IR/Assignment7/Pytest/part2/output/prediction.txt");
for (String key : doc_score.keySet()) {
wrtr.write(key + " : " + doc_score.get(key) + " \n");
}
wrtr.close();
} catch (Exception e) {
e.printStackTrace();
}
}
public static void RetrieveSpamFiles() {
try {
BufferedReader flrdr =
new BufferedReader(
new FileReader("D:\\IR\\Assignment7\\Pytest\\part2\\output\\spam_docs.txt"));
String line = flrdr.readLine();
line = line.substring(1, line.length() - 1);
for (String doc : line.split(",")) {
spam_docs.add(doc.substring(2, doc.length() - 1).trim());
}
flrdr.close();
} catch (Exception e) {
e.printStackTrace();
}
}
public static void MLalgo() {
try {
Problem problem = new Problem();
problem.l = train_count; // number of training examples
problem.n = max_feature_count; // number of features
problem.x = train_matrix; // feature nodes
problem.y = ylable; // target values;
SolverType solver = SolverType.L2R_LR; // -s 0
double C = 1.0; // cost of constraints violation
double eps = 0.01; // stopping criteria
Parameter parameter = new Parameter(solver, C, eps);
model = Linear.train(problem, parameter);
File modelFile = new File("model");
model.save(modelFile);
// load model or use it directly
model = Model.load(modelFile);
} catch (Exception e) {
e.printStackTrace();
}
}
public static void RetrieveTestMatrix() {
try {
BufferedReader flrdr =
new BufferedReader(
new FileReader("D:\\IR\\Assignment7\\Pytest\\part2\\output\\test_matrix.txt"));
String line = "";
while ((line = flrdr.readLine()) != null) {
SortedSet<Integer> word_ids = new TreeSet<Integer>();
int val_count = 0;
String[] key_value = line.split(" :: ");
if (key_value[1].trim().length() < 1)
System.out.println("Error on Train Doc " + key_value[0]);
key_value[1] = key_value[1].substring(1, key_value[1].length() - 2);
String[] values = key_value[1].split(",");
FeatureNode[] node = new FeatureNode[values.length];
for (String val : values) word_ids.add(Integer.parseInt(val.trim()));
for (int val : word_ids) node[val_count++] = new FeatureNode(val, 1);
double predict = Linear.predict(model, node);
doc_score.put(key_value[0].trim(), predict);
}
flrdr.close();
} catch (Exception e) {
e.printStackTrace();
System.exit(0);
}
}