/**
* @param lr is the learning rate.
* @param ts is the training set.
*/
public LogisticRegression(double lr, double rp, TrainingExample[] ts) {
learningRate = lr;
regularizationParam = rp;
trainingSet = ts;
// Construct the correct number of hypothesis given
// the number of features in the trainingSet
// and the number of different classifications
ArrayList<Integer> classifications = new ArrayList<Integer>();
for (TrainingExample t : trainingSet) {
Integer c = t.getAnswer();
if (!classifications.contains(c)) classifications.add(c);
}
hypothesis = new Hypothesis[classifications.size() - 0];
int s = trainingSet[0].getInput().length + 1;
for (int i = 0; i < classifications.size() - 0; ++i) {
hypothesis[i] = new Hypothesis(s, classifications.get(i));
}
try {
costFunction = this.getClass().getMethod("defaultCostFunction", Hypothesis.class);
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* Runs gradient decent on the hypothesis
*
* @param tSet the training set to be used
*/
private void gradientDecent(TrainingExample[] tSet) {
double h, val, newVal;
int answer;
double lm = LogisticRegression.this.learningRate / tSet.length;
for (int i = 0; i < numFeatures; ++i) {
val = 0;
for (TrainingExample t : tSet) {
answer = t.getAnswer();
h = predict(t.getInput());
if (i == 0) val += (h - answer);
else val += (h - answer) * t.getInput()[i - 1];
}
newVal = parameter.get(i, 0) * (1 - lm * LogisticRegression.this.getRegularizationParam());
newVal -= lm * val;
parameter.set(i, 0, newVal);
}
}
/**
* Runs gradient decent to tune the parameters of each hypothesis.
*
* @param iterations the number of times to run gradient decent
*/
public void tune(int iterations) {
for (Hypothesis h : hypothesis) {
// construct a new training set using One vs. Rest
// if the training example has the same value as the
// hypothesis then set the answer to 1
// otherwise set the answer to 0.
TrainingExample[] tSet = new TrainingExample[trainingSet.length];
int answer;
int i = 0;
for (TrainingExample t : trainingSet) {
if (t.getAnswer() == h.getClassification()) answer = 1;
else answer = 0;
tSet[i] = new TrainingExample(t.getInput(), answer);
++i;
}
for (i = 0; i < iterations; ++i) {
h.gradientDecent(tSet);
}
}
}
/**
* Calculates the cost of the <code>trainingSet</code>.
*
* @param hyp the hypothesis to use in calculating the cost.
* @return the cost associated with the hypothesis.
*/
public double defaultCostFunction(Hypothesis hyp) {
double error = 0;
double h;
int answer;
for (TrainingExample t : trainingSet) {
try {
h = (Double) hyp.predict(t.getInput());
} catch (Exception e) {
e.printStackTrace();
continue;
}
answer = t.getAnswer();
error -= answer * log(h) + (1 - answer) * log(1 - h);
}
double regError = 0;
for (int i = 0; i < hyp.getNumFeatures(); ++i) {
regError += pow(hyp.getParameter(i), 2);
}
error += regError / regularizationParam;
return error / (2 * trainingSet.length);
}
public void labelGrids(int k) throws FileNotFoundException {
// Initializing the global arraylist
trainingData = new ArrayList<>();
int count = 0;
Scanner input = new Scanner(new File("data.txt"));
int noOfRows = input.nextInt();
int noOfColumns = input.nextInt();
input.nextLine();
String[] row;
for (int i = 0; i < noOfRows; i++) {
row = input.nextLine().split(" ");
for (int j = 0; j < row.length; j++) {
if (row[j].equals("+")) {
TrainingExample newExample = new TrainingExample();
newExample.x2 = i;
newExample.x1 = j;
newExample.y = '+';
newExample.ex_no = count;
count++;
trainingData.add(newExample);
} else if (row[j].equals("-")) {
TrainingExample newExample = new TrainingExample();
newExample.x2 = i;
newExample.x1 = j;
newExample.y = '-';
newExample.ex_no = count;
count++;
trainingData.add(newExample);
} else {
TrainingExample newExample = new TrainingExample();
newExample.x2 = i;
newExample.x1 = j;
newExample.y = '.';
newExample.ex_no = count;
count++;
trainingData.add(newExample);
}
}
}
for (int i = 0; i < trainingData.size(); i++) {
kNN(trainingData, i, 1, k, false, true);
}
labelPrint(trainingData, noOfRows, noOfColumns);
}
