/** Train L2 tree boost. */
private void train2(Attribute[] attributes, double[][] x, int[] y) {
int n = x.length;
int N = (int) Math.round(n * f);
int[] y2 = new int[n];
for (int i = 0; i < n; i++) {
if (y[i] == 1) {
y2[i] = 1;
} else {
y2[i] = -1;
}
}
y = y2;
double[] h = new double[n]; // current F(x_i)
double[] response = new double[n]; // response variable for regression tree.
double mu = Math.mean(y);
b = 0.5 * Math.log((1 + mu) / (1 - mu));
for (int i = 0; i < n; i++) {
h[i] = b;
}
int[][] order = SmileUtils.sort(attributes, x);
RegressionTree.NodeOutput output = new L2NodeOutput(response);
trees = new RegressionTree[T];
int[] perm = new int[n];
int[] samples = new int[n];
for (int i = 0; i < n; i++) {
perm[i] = i;
}
for (int m = 0; m < T; m++) {
Arrays.fill(samples, 0);
Math.permutate(perm);
for (int i = 0; i < N; i++) {
samples[perm[i]] = 1;
}
for (int i = 0; i < n; i++) {
response[i] = 2.0 * y[i] / (1 + Math.exp(2 * y[i] * h[i]));
}
trees[m] = new RegressionTree(attributes, x, response, J, order, samples, output);
for (int i = 0; i < n; i++) {
h[i] += shrinkage * trees[m].predict(x[i]);
}
}
}
/** Train L-k tree boost. */
private void traink(Attribute[] attributes, double[][] x, int[] y) {
int n = x.length;
int N = (int) Math.round(n * f);
double[][] h = new double[k][n]; // boost tree output.
double[][] p = new double[k][n]; // posteriori probabilities.
double[][] response = new double[k][n]; // pseudo response.
int[][] order = SmileUtils.sort(attributes, x);
forest = new RegressionTree[k][T];
RegressionTree.NodeOutput[] output = new LKNodeOutput[k];
for (int i = 0; i < k; i++) {
output[i] = new LKNodeOutput(response[i]);
}
int[] perm = new int[n];
int[] samples = new int[n];
for (int i = 0; i < n; i++) {
perm[i] = i;
}
for (int m = 0; m < T; m++) {
for (int i = 0; i < n; i++) {
double max = Double.NEGATIVE_INFINITY;
for (int j = 0; j < k; j++) {
if (max < h[j][i]) {
max = h[j][i];
}
}
double Z = 0.0;
for (int j = 0; j < k; j++) {
p[j][i] = Math.exp(h[j][i] - max);
Z += p[j][i];
}
for (int j = 0; j < k; j++) {
p[j][i] /= Z;
}
}
for (int j = 0; j < k; j++) {
for (int i = 0; i < n; i++) {
if (y[i] == j) {
response[j][i] = 1.0;
} else {
response[j][i] = 0.0;
}
response[j][i] -= p[j][i];
}
Arrays.fill(samples, 0);
Math.permutate(perm);
for (int i = 0; i < N; i++) {
samples[perm[i]] = 1;
}
forest[j][m] = new RegressionTree(attributes, x, response[j], J, order, samples, output[j]);
for (int i = 0; i < n; i++) {
h[j][i] += shrinkage * forest[j][m].predict(x[i]);
}
}
}
}
