/**
* Compute Variable Importance, based on GEDEON: DATA MINING OF INPUTS: ANALYSING MAGNITUDE AND
* FUNCTIONAL MEASURES
*
* @return variable importances for input features
*/
public float[] computeVariableImportances() {
float[] vi = new float[units[0]];
Arrays.fill(vi, 0f);
float[][] Qik = new float[units[0]][units[2]]; // importance of input i on output k
float[] sum_wj = new float[units[1]]; // sum of incoming weights into first hidden layer
float[] sum_wk =
new float[units[2]]; // sum of incoming weights into output layer (or second hidden layer)
for (float[] Qi : Qik) Arrays.fill(Qi, 0f);
Arrays.fill(sum_wj, 0f);
Arrays.fill(sum_wk, 0f);
// compute sum of absolute incoming weights
for (int j = 0; j < units[1]; j++) {
for (int i = 0; i < units[0]; i++) {
float wij = get_weights(0).get(j, i);
sum_wj[j] += Math.abs(wij);
}
}
for (int k = 0; k < units[2]; k++) {
for (int j = 0; j < units[1]; j++) {
float wjk = get_weights(1).get(k, j);
sum_wk[k] += Math.abs(wjk);
}
}
// compute importance of input i on output k as product of connecting weights going through j
for (int i = 0; i < units[0]; i++) {
for (int k = 0; k < units[2]; k++) {
for (int j = 0; j < units[1]; j++) {
float wij = get_weights(0).get(j, i);
float wjk = get_weights(1).get(k, j);
// Qik[i][k] += Math.abs(wij)/sum_wj[j] * wjk; //Wong,Gedeon,Taggart '95
Qik[i][k] += Math.abs(wij) / sum_wj[j] * Math.abs(wjk) / sum_wk[k]; // Gedeon '97
}
}
}
// normalize Qik over all outputs k
for (int k = 0; k < units[2]; k++) {
float sumQk = 0;
for (int i = 0; i < units[0]; i++) sumQk += Qik[i][k];
for (int i = 0; i < units[0]; i++) Qik[i][k] /= sumQk;
}
// importance for feature i is the sum over k of i->k importances
for (int i = 0; i < units[0]; i++) vi[i] = ArrayUtils.sum(Qik[i]);
// normalize importances such that max(vi) = 1
ArrayUtils.div(vi, ArrayUtils.maxValue(vi));
// zero out missing categorical variables if they were never seen
if (_saw_missing_cats != null) {
for (int i = 0; i < _saw_missing_cats.length; ++i) {
assert (data_info._catMissing[i] == 1); // have a missing bucket for each categorical
if (!_saw_missing_cats[i]) vi[data_info._catOffsets[i + 1] - 1] = 0;
}
}
return vi;
}
public void testSum() {
assertEquals(0, ArrayUtils.sum(new long[0]));
assertEquals(0, ArrayUtils.sum(new long[10]));
assertEquals(5, ArrayUtils.sum(new long[] {1, 2, 2}));
assertEquals(0, ArrayUtils.sum(new int[0]));
assertEquals(0, ArrayUtils.sum(new int[10]));
assertEquals(5, ArrayUtils.sum(new int[] {1, 2, 2}));
assertEquals(
2L * Integer.MAX_VALUE, ArrayUtils.sum(new int[] {Integer.MAX_VALUE, Integer.MAX_VALUE}));
}
/** Unique identifier for this model's state, based on raw numbers */
protected long checksum_impl() {
long cs = parameters._seed;
cs ^= size() * get_processed_total();
cs ^= (long) (2234.3424 * ArrayUtils.sum(mean_bias));
cs *= (long) (9234.1343 * ArrayUtils.sum(rms_bias));
cs ^= (long) (9723.9734 * ArrayUtils.sum(mean_weight));
cs *= (long) (9234.1783 * ArrayUtils.sum(rms_weight));
cs ^= (long) (4273.2344 * (Math.E + ArrayUtils.sum(mean_rate)));
cs *= (long) (3378.1999 * (Math.PI + ArrayUtils.sum(rms_rate)));
return cs;
}
