Vec2d predict2(InputArray _sample, OutputArray _probs) const
{
int ptype = CV_64F;
Mat sample = _sample.getMat();
CV_Assert(isTrained());
CV_Assert(!sample.empty());
if(sample.type() != CV_64FC1)
{
Mat tmp;
sample.convertTo(tmp, CV_64FC1);
sample = tmp;
}
sample = sample.reshape(1, 1);
Mat probs;
if( _probs.needed() )
{
if( _probs.fixedType() )
ptype = _probs.type();
_probs.create(1, nclusters, ptype);
probs = _probs.getMat();
}
return computeProbabilities(sample, !probs.empty() ? &probs : 0, ptype);
}
float predict(InputArray _inputs, OutputArray _outputs, int) const
{
bool needprobs = _outputs.needed();
Mat samples = _inputs.getMat(), probs, probsrow;
int ptype = CV_64F;
float firstres = 0.f;
int i, nsamples = samples.rows;
if( needprobs )
{
if( _outputs.fixedType() )
ptype = _outputs.type();
_outputs.create(samples.rows, nclusters, ptype);
}
else
nsamples = std::min(nsamples, 1);
for( i = 0; i < nsamples; i++ )
{
if( needprobs )
probsrow = probs.row(i);
Vec2d res = computeProbabilities(samples.row(i), needprobs ? &probsrow : 0, ptype);
if( i == 0 )
firstres = (float)res[1];
}
return firstres;
}
bool KlustersView::qt_emit( int _id, QUObject* _o )
{
switch ( _id - staticMetaObject()->signalOffset() ) {
case 0: updatedDimensions((int)static_QUType_int.get(_o+1),(int)static_QUType_int.get(_o+2)); break;
case 1: singleColorUpdated((int)static_QUType_int.get(_o+1),(bool)static_QUType_bool.get(_o+2)); break;
case 2: clusterRemovedFromView((int)static_QUType_int.get(_o+1),(bool)static_QUType_bool.get(_o+2)); break;
case 3: clusterAddedToView((int)static_QUType_int.get(_o+1),(bool)static_QUType_bool.get(_o+2)); break;
case 4: newClusterAddedToView((QValueList<int>&)*((QValueList<int>*)static_QUType_ptr.get(_o+1)),(int)static_QUType_int.get(_o+2),(bool)static_QUType_bool.get(_o+3)); break;
case 5: newClusterAddedToView((int)static_QUType_int.get(_o+1),(bool)static_QUType_bool.get(_o+2)); break;
case 6: spikesRemovedFromClusters((QValueList<int>&)*((QValueList<int>*)static_QUType_ptr.get(_o+1)),(bool)static_QUType_bool.get(_o+2)); break;
case 7: modeToSet((BaseFrame::Mode)(*((BaseFrame::Mode*)static_QUType_ptr.get(_o+1)))); break;
case 8: spikesAddedToCluster((int)static_QUType_int.get(_o+1),(bool)static_QUType_bool.get(_o+2)); break;
case 9: updateContents(); break;
case 10: emptySelection(); break;
case 11: modifiedClusters((QValueList<int>&)*((QValueList<int>*)static_QUType_ptr.get(_o+1)),(bool)static_QUType_bool.get(_o+2),(bool)static_QUType_bool.get(_o+3)); break;
case 12: modifiedClustersUndo((QValueList<int>&)*((QValueList<int>*)static_QUType_ptr.get(_o+1)),(bool)static_QUType_bool.get(_o+2)); break;
case 13: updatedTimeFrame((long)(*((long*)static_QUType_ptr.get(_o+1))),(long)(*((long*)static_QUType_ptr.get(_o+2)))); break;
case 14: sampleMode(); break;
case 15: timeFrameMode(); break;
case 16: meanPresentation(); break;
case 17: allWaveformsPresentation(); break;
case 18: overLayPresentation(); break;
case 19: sideBySidePresentation(); break;
case 20: increaseAmplitude(); break;
case 21: decreaseAmplitude(); break;
case 22: updateDisplayNbSpikes((long)(*((long*)static_QUType_ptr.get(_o+1)))); break;
case 23: increaseAmplitudeofCorrelograms(); break;
case 24: decreaseAmplitudeofCorrelograms(); break;
case 25: noScale(); break;
case 26: maxScale(); break;
case 27: shoulderScale(); break;
case 28: updatedBinSizeAndTimeFrame((int)static_QUType_int.get(_o+1),(int)static_QUType_int.get(_o+2)); break;
case 29: setShoulderLine((bool)static_QUType_bool.get(_o+1)); break;
case 30: updateDrawing(); break;
case 31: changeGain((int)static_QUType_int.get(_o+1)); break;
case 32: changeTimeInterval((int)static_QUType_int.get(_o+1),(bool)static_QUType_bool.get(_o+2)); break;
case 33: changeChannelPositions((QValueList<int>&)*((QValueList<int>*)static_QUType_ptr.get(_o+1))); break;
case 34: computeProbabilities(); break;
case 35: changeBackgroundColor((QColor)(*((QColor*)static_QUType_ptr.get(_o+1)))); break;
case 36: clustersRenumbered((bool)static_QUType_bool.get(_o+1)); break;
case 37: updateClusters((QString)static_QUType_QString.get(_o+1),(QValueList<int>&)*((QValueList<int>*)static_QUType_ptr.get(_o+2)),(ItemColors*)static_QUType_ptr.get(_o+3),(bool)static_QUType_bool.get(_o+4)); break;
case 38: increaseAllAmplitude(); break;
case 39: decreaseAllAmplitude(); break;
case 40: showLabels((bool)static_QUType_bool.get(_o+1)); break;
case 41: nextCluster(); break;
case 42: previousCluster(); break;
default:
return KDockArea::qt_emit(_id,_o);
}
return TRUE;
}
estimates_t EM(const estimates_t& initial, const dataPoints_t& X, unsigned int maxIterations, Progress *progress)
{
// This will be used for probabilites calculation at each step
prob_matrix_t prob;
// Number of classes
const unsigned int classes = initial.size();
// Sum of probabilites of all classes
std::vector<double> sums(classes, 0);
for(unsigned int i = 0; i < classes + 1; ++i)
{
prob.push_back(std::vector<double>());
std::vector<double>& ps = prob.back();
ps.resize(X.size());
}
// Estimates after each iteration
estimates_t next = initial;
for(unsigned int iteration = 1; iteration <= maxIterations; ++iteration)
{
if (progress != NULL)
{
progress->updateProgress("EM running on difference image", 100*iteration/maxIterations, NORMAL);
}
std::fill(sums.begin(), sums.end(), 0.0);
computeProbabilities(prob, sums, X, next);
estimates_t::iterator estimateItr = next.begin();
estimates_t::const_iterator prev_estimateItr = next.begin();
std::vector<double>::const_iterator sumItr = sums.begin();
prob_matrix_t::const_iterator probItr = prob.begin();
// M-step
for(; estimateItr != next.end(); ++estimateItr, ++sumItr, ++probItr, ++prev_estimateItr)
{
updateStdDevs(*estimateItr, *sumItr, *probItr, X, *prev_estimateItr);
updateMeans(*estimateItr, *sumItr, *probItr, X);
updateWeights(*estimateItr, *sumItr, X.size());
}
}
estimates_t final = next;
return final;
}
void EM::eStep()
{
// Compute probs_ik from means_k, covs_k and weights_k.
trainProbs.create(trainSamples.rows, nclusters, CV_64FC1);
trainLabels.create(trainSamples.rows, 1, CV_32SC1);
trainLogLikelihoods.create(trainSamples.rows, 1, CV_64FC1);
computeLogWeightDivDet();
CV_DbgAssert(trainSamples.type() == CV_64FC1);
CV_DbgAssert(means.type() == CV_64FC1);
for(int sampleIndex = 0; sampleIndex < trainSamples.rows; sampleIndex++)
{
Mat sampleProbs = trainProbs.row(sampleIndex);
Vec2d res = computeProbabilities(trainSamples.row(sampleIndex), &sampleProbs);
trainLogLikelihoods.at<double>(sampleIndex) = res[0];
trainLabels.at<int>(sampleIndex) = static_cast<int>(res[1]);
}
}
main(){
int N , exp, i, j;
double temp;
scanf("%d", &N);
exp = power(N);
for(i = 0; i <= exp; i++) // Initialize array with team IDs.
teamArray[i] = i;
for (i=0; i < MAXTEAMS; i++)
for (j=0; j < (MAXN +2); j++)
cumulativeProbabilityArray[i][j] = -1;
for(i = 1; i <= exp ; i++)
for(j = 1 ; j <= exp ; j++){ // Read and store probability matrix.
scanf("%lf", &temp);
probabilityArray[i][j] = temp/100;
}
computeProbabilities(exp, N+1);
sortAndPrint(N, exp);
}
