public final double regularize(double[] u, Regularizer regularization) {
if (u == null) return 0;
double ureg = 0;
switch (regularization) {
case None:
return 0;
case Quadratic:
for (int i = 0; i < u.length; i++) ureg += u[i] * u[i];
return ureg;
case L2:
for (int i = 0; i < u.length; i++) ureg += u[i] * u[i];
return Math.sqrt(ureg);
case L1:
for (int i = 0; i < u.length; i++) ureg += Math.abs(u[i]);
return ureg;
case NonNegative:
for (int i = 0; i < u.length; i++) {
if (u[i] < 0) return Double.POSITIVE_INFINITY;
}
return 0;
case OneSparse:
int card = 0;
for (int i = 0; i < u.length; i++) {
if (u[i] < 0) return Double.POSITIVE_INFINITY;
else if (u[i] > 0) card++;
}
return card == 1 ? 0 : Double.POSITIVE_INFINITY;
case UnitOneSparse:
int ones = 0, zeros = 0;
for (int i = 0; i < u.length; i++) {
if (u[i] == 1) ones++;
else if (u[i] == 0) zeros++;
else return Double.POSITIVE_INFINITY;
}
return ones == 1 && zeros == u.length - 1 ? 0 : Double.POSITIVE_INFINITY;
case Simplex:
double sum = 0, absum = 0;
for (int i = 0; i < u.length; i++) {
if (u[i] < 0) return Double.POSITIVE_INFINITY;
else {
sum += u[i];
absum += Math.abs(u[i]);
}
}
return MathUtils.equalsWithinRecSumErr(sum, 1.0, u.length, absum)
? 0
: Double.POSITIVE_INFINITY;
default:
throw new RuntimeException("Unknown regularization function " + regularization);
}
}
/**
* Initialization of neural net weights cf.
* http://machinelearning.wustl.edu/mlpapers/paper_files/AISTATS2010_GlorotB10.pdf
*/
private void randomizeWeights() {
for (int w = 0; w < dense_row_weights.length; ++w) {
final Random rng =
water.util.RandomUtils.getRNG(
get_params()._seed + 0xBAD5EED + w + 1); // to match NeuralNet behavior
final double range = Math.sqrt(6. / (units[w] + units[w + 1]));
for (int i = 0; i < get_weights(w).rows(); i++) {
for (int j = 0; j < get_weights(w).cols(); j++) {
if (get_params()._initial_weight_distribution
== DeepLearningParameters.InitialWeightDistribution.UniformAdaptive) {
// cf. http://machinelearning.wustl.edu/mlpapers/paper_files/AISTATS2010_GlorotB10.pdf
if (w == dense_row_weights.length - 1 && _classification)
get_weights(w)
.set(
i,
j,
(float)
(4.
* uniformDist(
rng, -range,
range))); // Softmax might need an extra factor 4, since it's like
// a sigmoid
else get_weights(w).set(i, j, (float) uniformDist(rng, -range, range));
} else if (get_params()._initial_weight_distribution
== DeepLearningParameters.InitialWeightDistribution.Uniform) {
get_weights(w)
.set(
i,
j,
(float)
uniformDist(
rng,
-get_params()._initial_weight_scale,
get_params()._initial_weight_scale));
} else if (get_params()._initial_weight_distribution
== DeepLearningParameters.InitialWeightDistribution.Normal) {
get_weights(w)
.set(i, j, (float) (rng.nextGaussian() * get_params()._initial_weight_scale));
}
}
}
}
}
protected void calcModelStats(
CoxPHModel model, final double[] newCoef, final double newLoglik) {
CoxPHModel.CoxPHParameters p = model._parms;
CoxPHModel.CoxPHOutput o = model._output;
final int n_coef = o.coef.length;
final Matrix inv_hessian = new Matrix(o.hessian).inverse();
for (int j = 0; j < n_coef; ++j) {
for (int k = 0; k <= j; ++k) {
final double elem = -inv_hessian.get(j, k);
o.var_coef[j][k] = elem;
o.var_coef[k][j] = elem;
}
}
for (int j = 0; j < n_coef; ++j) {
o.coef[j] = newCoef[j];
o.exp_coef[j] = Math.exp(o.coef[j]);
o.exp_neg_coef[j] = Math.exp(-o.coef[j]);
o.se_coef[j] = Math.sqrt(o.var_coef[j][j]);
o.z_coef[j] = o.coef[j] / o.se_coef[j];
}
if (o.iter == 0) {
o.null_loglik = newLoglik;
o.maxrsq = 1 - Math.exp(2 * o.null_loglik / o.n);
o.score_test = 0;
for (int j = 0; j < n_coef; ++j) {
double sum = 0;
for (int k = 0; k < n_coef; ++k) sum += o.var_coef[j][k] * o.gradient[k];
o.score_test += o.gradient[j] * sum;
}
}
o.loglik = newLoglik;
o.loglik_test = -2 * (o.null_loglik - o.loglik);
o.rsq = 1 - Math.exp(-o.loglik_test / o.n);
o.wald_test = 0;
for (int j = 0; j < n_coef; ++j) {
double sum = 0;
for (int k = 0; k < n_coef; ++k) sum -= o.hessian[j][k] * (o.coef[k] - p.init);
o.wald_test += (o.coef[j] - p.init) * sum;
}
}
@SuppressWarnings("unused")
@Override
protected void init() {
super.init();
// Initialize local variables
_mtry =
(mtries == -1)
? // classification: mtry=sqrt(_ncols), regression: mtry=_ncols/3
(classification ? Math.max((int) Math.sqrt(_ncols), 1) : Math.max(_ncols / 3, 1))
: mtries;
if (!(1 <= _mtry && _mtry <= _ncols))
throw new IllegalArgumentException(
"Computed mtry should be in interval <1,#cols> but it is " + _mtry);
if (!(0.0 < sample_rate && sample_rate <= 1.0))
throw new IllegalArgumentException(
"Sample rate should be interval (0,1> but it is " + sample_rate);
if (DEBUG_DETERMINISTIC && seed == -1) _seed = 0x1321e74a0192470cL; // fixed version of seed
else if (seed == -1) _seed = _seedGenerator.nextLong();
else _seed = seed;
if (sample_rate == 1f && validation != null)
Log.warn(
Sys.DRF__,
"Sample rate is 100% and no validation dataset is required. There are no OOB data to perform validation!");
}