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();
}
}
private void mainClassifierFunction(int option, String trainFile, String testFile, String ddgFile)
throws IOException {
// SentimentClassifierHindi this = new SentimentClassifierHindi();
// int finalSize = this.SentimentClassifierHindi();
int finalSize = this.generateFeature(option, trainFile, testFile, ddgFile);
System.out.println("Hello aspectCategorizationSemEval2016!");
// Create features
Problem problem = new Problem();
// Save X to problem
double a[] = new double[this.trainingFeature.size()];
File file = new File(rootDirectory + "\\dataset\\trainingLabels.txt");
BufferedReader reader = new BufferedReader(new FileReader(file));
String read;
int count = 0;
while ((read = reader.readLine()) != null) {
// System.out.println(read);
a[count++] = Double.parseDouble(read.toString());
}
// Feature[][] f = new Feature[][]{ {}, {}, {}, {}, {}, {} };
// trainingFeature = trainingObject.getList();
Feature[][] trainFeatureVector = new Feature[trainingFeature.size()][finalSize];
System.out.println("Training Instances: " + trainingFeature.size());
System.out.println("Feature Length: " + finalSize);
System.out.println("Test Instances: " + testFeature.size());
for (int i = 0; i < trainingFeature.size(); i++) {
// System.out.println();
// System.out.println(trainingFeature.get(i));
System.out.println(i + " trained.");
for (int j = 0; j < finalSize; j++) {
// System.out.print(trainingFeature.get(i).get(j + 1)+" ");
// trainingFeature.get(i).
if (trainingFeature.get(i).containsKey(j + 1)) {
// System.out.print(j + 1 + ", ");
trainFeatureVector[i][j] = new FeatureNode(j + 1, trainingFeature.get(i).get(j + 1));
} else {
trainFeatureVector[i][j] = new FeatureNode(j + 1, 0.0);
}
}
// System.out.println();
}
problem.l = trainingFeature.size(); // number of training examples
problem.n = finalSize; // number of features
problem.x = trainFeatureVector; // feature nodes
problem.y = a; // target values ----
BasicParser bp = new BasicParser();
SolverType solver = SolverType.L2R_LR; // -s 7
double C = 0.75; // cost of constraints violation
double eps = 0.0001; // stopping criteria
Parameter parameter = new Parameter(solver, C, eps);
Model model = Linear.train(problem, parameter);
File modelFile = new File("model");
model.save(modelFile);
// PrintWriter write = new PrintWriter(new BufferedWriter(new FileWriter(rootDirectory +
// "\\dataset\\predictedLabels.txt")));
PrintWriter write =
new PrintWriter(
new BufferedWriter(
new FileWriter(
rootDirectory
+ "\\dataset\\dataset_aspectCategorization\\predictedHotelsLabels.txt")));
if (option == 1) {
BufferedReader trainReader =
new BufferedReader(
new FileReader(
new File(
rootDirectory + "\\dataset\\dataset_aspectCategorization\\" + trainFile)));
HashMap<String, Integer> id = new HashMap<String, Integer>();
HashMap<String, String> review = new HashMap<String, String>();
double[] val = new double[trainingFeature.size()];
double[] tempVal = new double[trainingFeature.size()];
LinearCopy.crossValidation(problem, parameter, 5, val, tempVal);
for (int i = 0; i < trainingFeature.size(); i++) {
int flag = 0;
String tokens[] = trainReader.readLine().split("\\|");
if (id.containsKey(tokens[1]) == true || tokens[2].compareToIgnoreCase("True") == 0) {
} else {
// System.out.println(tokens[1]);
/*int max = -1;
double probMax = -1.0;
for(int j=0; j<13; j++){
if(probMax<val[i][j]){
probMax = val[i][j];
max = j;
}
}*/
// System.out.println(tempVal[i]);
write.println((int) (val[i]));
write.println("next");
id.put(tokens[1], 1);
System.out.println(tokens[1] + "\t" + (int) (val[i]));
if (review.containsKey(tokens[1])) {
System.out.println(tokens[3]);
System.out.println(review.get(tokens[1]));
} else {
review.put(tokens[1], tokens[3]);
}
} /*else{
for (int j = 0; j < 13; j++) {
//System.out.print(val[i][j]+", ");
if (val[i] >= 0.185) {
flag = 1;
//System.out.println("i");
write.println(j + 1);
}
}
if (flag == 1) {
write.println("next");
} else {
write.println("-1");
write.println("next");
}
//write.println(prediction);
id.put(tokens[1], 1);
//System.out.println();
}*/
}
write.close();
return;
}
if (option == 3) {
System.out.println(rootDirectory);
BufferedReader testReader =
new BufferedReader(
new FileReader(
new File(
rootDirectory + "\\dataset\\dataset_aspectCategorization\\" + testFile)));
HashMap<String, Integer> id = new HashMap<String, Integer>();
model = Model.load(modelFile);
int countNext = 0;
for (int i = 0; i < testFeature.size(); i++) {
// System.out.println(i+", "+testFeature.size()+", "+testFeature.get(i).size());
Feature[] instance = new Feature[testFeature.get(i).size()];
int j = 0;
for (Map.Entry<Integer, Double> entry : testFeature.get(i).entrySet()) {
// System.out.print(entry.getKey() + ": " + entry.getValue() + "; ");
// listOfMaps.get(i).put(start + entry.getKey(), entry.getValue());
// do stuff
instance[j++] = new FeatureNode(entry.getKey(), entry.getValue());
}
// double d = LinearCopy.predict(model, instance);
double[] predict = new double[85];
double prediction = LinearCopy.predictProbability(model, instance, predict);
int labelMap[] = new int[13];
labelMap = model.getLabels();
for (int ar = 0; ar < labelMap.length; ar++) {
System.out.println("********************** " + ar + ": " + labelMap[ar]);
}
// System.out.println(prediction);
// Arrays.sort(predict, Collections.reverseOrder());
// System.out.println();
// double prediction = LinearCopy.predict(model, instance);
String tokens[] = testReader.readLine().split("\\|");
// System.out.println(tokens[1]);
int flag = -1;
if (id.containsKey(tokens[1]) == true || tokens[2].compareToIgnoreCase("True") == 0) {
flag = 4;
// System.out.println("OutofScope: "+tokens[1]);
} else if (tokens[3].compareToIgnoreCase("abc") == 0) {
flag = 2;
System.out.println(tokens[1]);
write.println("-1");
write.println("next");
countNext++;
id.put(tokens[1], 1);
} else {
flag = 0;
for (int p = 0; p < 85; p++) {
if (predict[p] >= 0.128) {
flag = 1;
write.println(labelMap[p]);
}
}
if (flag == 1) {
countNext++;
write.println("next");
} else {
countNext++;
write.println("-1");
write.println("next");
}
// write.println((int)d);
// write.println("next");
/*write.println(prediction);
write.println("next");*/
id.put(tokens[1], 1);
}
if (flag == -1) {
System.out.println("-1, " + tokens[1]);
}
}
write.close();
System.out.println("count " + countNext);
}
write.close();
}