@Override
public void setup(GibbsSampling.Context context) {
Configuration conf = context.getConfiguration();
if (conf.getBoolean("minibatch.job.setup", false)) {
Path[] jobSetupFiles = new Path[0];
try {
jobSetupFiles = DistributedCache.getLocalCacheFiles(conf);
} catch (IOException ioe) {
System.err.println(
"Caught exception while getting cached files: "
+ StringUtils.stringifyException(ioe));
}
for (Path jobSetup : jobSetupFiles) {
parseJobSetup(jobSetup);
}
}
}
// TODO: DOUBLECHECK EVERYTHING
@Override
public void map(Text key, jBLASArrayWritable input, GibbsSampling.Context context)
throws IOException, InterruptedException {
/* *******************************************************************/
/* initialize all memory we're going to use during the process */
long start_time = System.nanoTime();
ArrayList<DoubleMatrix> data = input.getData();
label = data.get(4);
v_data = data.get(5);
// check to see if we are in the first layer or there are layers beneath us we must sample
// from
if (data.size() > 6) {
int prelayer = (data.size() - 6) / 3;
DoubleMatrix[] preWeights = new DoubleMatrix[prelayer],
preHbias = new DoubleMatrix[prelayer],
preVbias = new DoubleMatrix[prelayer];
for (int i = 0; i < prelayer; i++) {
preWeights[i] = data.get(6 + i * 3);
preHbias[i] = data.get(7 + i * 3);
preVbias[i] = data.get(8 + i * 3);
}
DoubleMatrix vnew = null;
for (int i = 0; i < prelayer; i++) {
weights = preWeights[i];
vbias = preVbias[i];
hbias = preHbias[i];
vnew = sample_h_from_v(i == 0 ? v_data : vnew);
}
v_data = vnew;
}
weights = data.get(0);
hbias = data.get(1);
hiddenChain = data.get(2);
vbias = data.get(3);
// check if we need to attach labels to the observed variables
if (vbias.columns != v_data.columns) {
DoubleMatrix labels = DoubleMatrix.zeros(1, classCount);
int labelNum = (new Double(label.get(0))).intValue();
labels.put(labelNum, 1.0);
v_data = DoubleMatrix.concatHorizontally(v_data, labels);
}
w1 = DoubleMatrix.zeros(weights.rows, weights.columns);
hb1 = DoubleMatrix.zeros(hbias.rows, hbias.columns);
vb1 = DoubleMatrix.zeros(vbias.rows, vbias.columns);
/* ********************************************************************/
// sample hidden state to get positive phase
// if empty, use it as the start of the chain
// or use persistent hidden state from pCD
DoubleMatrix phaseSample = sample_h_from_v(v_data);
h1_data = new DoubleMatrix();
v1_data = new DoubleMatrix();
if (hiddenChain == null) {
data.set(2, new DoubleMatrix(hbias.rows, hbias.columns));
hiddenChain = data.get(2);
hiddenChain.copy(phaseSample);
h1_data.copy(phaseSample);
} else {
h1_data.copy(hiddenChain);
}
// run Gibbs chain for k steps
for (int j = 0; j < gibbsSteps; j++) {
v1_data.copy(sample_v_from_h(h1_data));
h1_data.copy(sample_h_from_v(v1_data));
}
DoubleMatrix hprob = propup(v1_data);
weight_contribution(hiddenChain, v_data, hprob, v1_data);
hiddenChain.copy(h1_data);
data.get(0).copy(w1);
data.get(1).copy(hb1);
data.get(2).copy(hiddenChain);
data.get(3).copy(vb1);
jBLASArrayWritable outputmatrix = new jBLASArrayWritable(data);
context.write(key, outputmatrix);
log.info("Job completed in: " + (System.nanoTime() - start_time) / (1E6) + " ms");
}