void print_histogram(std::ostream & os, FC::flow_complex<nt, st> fc) {
auto const INF = std::numeric_limits<nt>::infinity();
auto min_incidence = get_min_incidence(fc);
auto & a_ptr = std::get<0>(min_incidence);
auto & b_ptr = std::get<1>(min_incidence);
auto & min_ratio = std::get<2>(min_incidence);
using fc_type = FC::flow_complex<nt, st>;
auto print_hist = [&os] (nt ratio, fc_type const& fc) {
auto hist = compute_hist(fc);
os << ratio;
for (auto & p : hist)
os << " " << p.second;
os << std::endl;
};
print_hist(1, fc); // print initial fc
while (INF != min_ratio) {
fc = reduce(std::move(fc), a_ptr, b_ptr);
print_hist(min_ratio, fc);
// prepare next iteration
min_incidence = get_min_incidence(fc);
}
}
/* Constructor ------------------------------------------------------------- */
LeafNode::LeafNode(const std::vector < MultidimArray<double> > &leafFeatures,
int discrete_levels)
{
__discreteLevels = discrete_levels;
K = leafFeatures.size();
if (__discreteLevels==0)
{
// This is a dummy node for features that cannot classify
MultidimArray<int> newBins(1);
A1D_ELEM(newBins,0)=0;
Histogram1D hist;
hist.resize(1);
A1D_ELEM(hist,0)=1;
IrregularHistogram1D irregHist;
for (int k=0; k<K; k++)
{
irregHist.init(hist, newBins);
irregHist.selfNormalize();
__leafPDF.push_back(irregHist);
}
}
else
{
// Compute the minimum and maximum of each class
double minval=0., maxval=0.;
for(int k=0; k<K; k++)
{
double minvalk=0., maxvalk=0.;
leafFeatures[k].computeDoubleMinMax(minvalk, maxvalk);
if (k==0)
{
minval=minvalk;
maxval=maxvalk;
}
else
{
minval=std::min(minval,minvalk);
maxval=std::max(maxval,maxvalk);
}
}
if (minval==maxval)
{
__discreteLevels=0;
return;
}
// Compute the PDF of each class
std::vector<Histogram1D> hist(K);
for (int k=0; k<K; k++)
{
// There is variation of this feature for this class
compute_hist(leafFeatures[k], hist[k], minval, maxval, 100);
hist[k] += 1; // Apply Laplace correction
}
// Split the histograms into discrete_level (power of 2) bins
std::queue< Matrix1D<int> > intervals, splittedIntervals;
Matrix1D<int> limits(2);
VECTOR_R2(limits,0,99);
intervals.push(limits);
int imax=ROUND(log2(__discreteLevels));
for (int i=0; i<imax; i++)
{
// Split all the intervals in the queue
while (!intervals.empty())
{
Matrix1D<int> currentInterval = intervals.front();
intervals.pop();
int lsplit = splitHistogramsUsingEntropy(hist,
currentInterval(0), currentInterval(1));
VECTOR_R2(limits,currentInterval(0),lsplit);
splittedIntervals.push(limits);
VECTOR_R2(limits,lsplit+1, currentInterval(1));
splittedIntervals.push(limits);
}
// Copy the splitted intervals to the interval list
while (!splittedIntervals.empty())
{
intervals.push(splittedIntervals.front());
splittedIntervals.pop();
}
}
// Compute the bins of the split
MultidimArray<int> newBins(__discreteLevels);
imax=intervals.size();
for (int i=0; i<imax; i++)
{
A1D_ELEM(newBins,i) = intervals.front()(1);
intervals.pop();
}
// Compute now the irregular histograms
IrregularHistogram1D irregHist;
for (int k=0; k<K; k++)
{
irregHist.init(hist[k], newBins);
irregHist.selfNormalize();
__leafPDF.push_back(irregHist);
}
}
}
//majorAxis and minorAxis is the estimated particle size in px
void ProgSortByStatistics::processInprocessInputPrepareSPTH(MetaData &SF, bool trained)
{
//#define DEBUG
PCAMahalanobisAnalyzer tempPcaAnalyzer0;
PCAMahalanobisAnalyzer tempPcaAnalyzer1;
PCAMahalanobisAnalyzer tempPcaAnalyzer2;
PCAMahalanobisAnalyzer tempPcaAnalyzer3;
PCAMahalanobisAnalyzer tempPcaAnalyzer4;
//Morphology
tempPcaAnalyzer0.clear();
//Signal to noise ratio
tempPcaAnalyzer1.clear();
tempPcaAnalyzer2.clear();
tempPcaAnalyzer3.clear();
//Histogram analysis, to detect black points and saturated parts
tempPcaAnalyzer4.clear();
double sign = 1;//;-1;
int numNorm = 3;
int numDescriptors0=numNorm;
int numDescriptors2=4;
int numDescriptors3=11;
int numDescriptors4 = 10;
MultidimArray<float> v0(numDescriptors0);
MultidimArray<float> v2(numDescriptors2);
MultidimArray<float> v3(numDescriptors3);
MultidimArray<float> v4(numDescriptors4);
if (verbose>0)
{
std::cout << " Sorting particle set by new xmipp method..." << std::endl;
}
int nr_imgs = SF.size();
if (verbose>0)
init_progress_bar(nr_imgs);
int c = XMIPP_MAX(1, nr_imgs / 60);
int imgno = 0, imgnoPCA=0;
bool thereIsEnable=SF.containsLabel(MDL_ENABLED);
bool first=true;
// We assume that at least there is one particle
size_t Xdim, Ydim, Zdim, Ndim;
getImageSize(SF,Xdim,Ydim,Zdim,Ndim);
//Initialization:
MultidimArray<double> nI, modI, tempI, tempM, ROI;
MultidimArray<bool> mask;
nI.resizeNoCopy(Ydim,Xdim);
modI.resizeNoCopy(Ydim,Xdim);
tempI.resizeNoCopy(Ydim,Xdim);
tempM.resizeNoCopy(Ydim,Xdim);
mask.resizeNoCopy(Ydim,Xdim);
mask.initConstant(true);
MultidimArray<double> autoCorr(2*Ydim,2*Xdim);
MultidimArray<double> smallAutoCorr;
Histogram1D hist;
Matrix2D<double> U,V,temp;
Matrix1D<double> D;
MultidimArray<int> radial_count;
MultidimArray<double> radial_avg;
Matrix1D<int> center(2);
MultidimArray<int> distance;
int dim;
center.initZeros();
v0.initZeros(numDescriptors0);
v2.initZeros(numDescriptors2);
v3.initZeros(numDescriptors3);
v4.initZeros(numDescriptors4);
ROI.resizeNoCopy(Ydim,Xdim);
ROI.setXmippOrigin();
FOR_ALL_ELEMENTS_IN_ARRAY2D(ROI)
{
double temp = std::sqrt(i*i+j*j);
if ( temp < (Xdim/2))
A2D_ELEM(ROI,i,j)= 1;
else
A2D_ELEM(ROI,i,j)= 0;
}
Image<double> img;
FourierTransformer transformer(FFTW_BACKWARD);
FOR_ALL_OBJECTS_IN_METADATA(SF)
{
if (thereIsEnable)
{
int enabled;
SF.getValue(MDL_ENABLED,enabled,__iter.objId);
if ( (enabled==-1) )
{
imgno++;
continue;
}
}
img.readApplyGeo(SF,__iter.objId);
if (targetXdim!=-1 && targetXdim!=XSIZE(img()))
selfScaleToSize(LINEAR,img(),targetXdim,targetXdim,1);
MultidimArray<double> &mI=img();
mI.setXmippOrigin();
mI.statisticsAdjust(0,1);
mask.setXmippOrigin();
//The size of v1 depends on the image size and must be declared here
int numDescriptors1 = XSIZE(mI)/2; //=100;
MultidimArray<float> v1(numDescriptors1);
v1.initZeros(numDescriptors1);
double var = 1;
normalize(transformer,mI,tempI,modI,0,var,mask);
modI.setXmippOrigin();
tempI.setXmippOrigin();
nI = sign*tempI*(modI*modI);
tempM = (modI*modI);
A1D_ELEM(v0,0) = (tempM*ROI).sum();
int index = 1;
var+=2;
while (index < numNorm)
{
normalize(transformer,mI,tempI,modI,0,var,mask);
modI.setXmippOrigin();
tempI.setXmippOrigin();
nI += sign*tempI*(modI*modI);
tempM += (modI*modI);
A1D_ELEM(v0,index) = (tempM*ROI).sum();
index++;
var+=2;
}
nI /= tempM;
tempPcaAnalyzer0.addVector(v0);
nI=(nI*ROI);
auto_correlation_matrix(mI,autoCorr);
if (first)
{
radialAveragePrecomputeDistance(autoCorr, center, distance, dim);
first=false;
}
fastRadialAverage(autoCorr, distance, dim, radial_avg, radial_count);
for (int n = 0; n < numDescriptors1; ++n)
A1D_ELEM(v1,n)=(float)DIRECT_A1D_ELEM(radial_avg,n);
tempPcaAnalyzer1.addVector(v1);
#ifdef DEBUG
//String name = "000005@Images/Extracted/run_002/extra/BPV_1386.stk";
String name = "000010@Images/Extracted/run_001/extra/KLH_Dataset_I_Training_0028.stk";
//String name = "001160@Images/Extracted/run_001/DefaultFamily5";
std::cout << img.name() << std::endl;
if (img.name()==name2)
{
FileName fpName = "test_1.txt";
mI.write(fpName);
fpName = "test_2.txt";
nI.write(fpName);
fpName = "test_3.txt";
tempM.write(fpName);
fpName = "test_4.txt";
ROI.write(fpName);
//exit(1);
}
#endif
nI.binarize(0);
int im = labelImage2D(nI,nI,8);
compute_hist(nI, hist, 0, im, im+1);
size_t l;
int k,i,j;
hist.maxIndex(l,k,i,j);
A1D_ELEM(hist,j)=0;
hist.maxIndex(l,k,i,j);
nI.binarizeRange(j-1,j+1);
double x0=0,y0=0,majorAxis=0,minorAxis=0,ellipAng=0;
size_t area=0;
fitEllipse(nI,x0,y0,majorAxis,minorAxis,ellipAng,area);
A1D_ELEM(v2,0)=majorAxis/((img().xdim) );
A1D_ELEM(v2,1)=minorAxis/((img().xdim) );
A1D_ELEM(v2,2)= (fabs((img().xdim)/2-x0)+fabs((img().ydim)/2-y0))/((img().xdim)/2);
A1D_ELEM(v2,3)=area/( (double)((img().xdim)/2)*((img().ydim)/2) );
for (int n=0 ; n < numDescriptors2 ; n++)
{
if ( std::isnan(std::abs(A1D_ELEM(v2,n))))
A1D_ELEM(v2,n)=0;
}
tempPcaAnalyzer2.addVector(v2);
//mI.setXmippOrigin();
//auto_correlation_matrix(mI*ROI,autoCorr);
//auto_correlation_matrix(nI,autoCorr);
autoCorr.window(smallAutoCorr,-5,-5, 5, 5);
smallAutoCorr.copy(temp);
svdcmp(temp,U,D,V);
for (int n = 0; n < numDescriptors3; ++n)
A1D_ELEM(v3,n)=(float)VEC_ELEM(D,n); //A1D_ELEM(v3,n)=(float)VEC_ELEM(D,n)/VEC_ELEM(D,0);
tempPcaAnalyzer3.addVector(v3);
double minVal=0.;
double maxVal=0.;
mI.computeDoubleMinMax(minVal,maxVal);
compute_hist(mI, hist, minVal, maxVal, 100);
for (int n=0 ; n <= numDescriptors4-1 ; n++)
{
A1D_ELEM(v4,n)= (hist.percentil((n+1)*10));
}
tempPcaAnalyzer4.addVector(v4);
#ifdef DEBUG
if (img.name()==name1)
{
FileName fpName = "test.txt";
mI.write(fpName);
fpName = "test3.txt";
nI.write(fpName);
}
#endif
imgno++;
imgnoPCA++;
if (imgno % c == 0 && verbose>0)
progress_bar(imgno);
}
tempPcaAnalyzer0.evaluateZScore(2,20,trained);
tempPcaAnalyzer1.evaluateZScore(2,20,trained);
tempPcaAnalyzer2.evaluateZScore(2,20,trained);
tempPcaAnalyzer3.evaluateZScore(2,20,trained);
tempPcaAnalyzer4.evaluateZScore(2,20,trained);
pcaAnalyzer.push_back(tempPcaAnalyzer0);
pcaAnalyzer.push_back(tempPcaAnalyzer1);
pcaAnalyzer.push_back(tempPcaAnalyzer1);
pcaAnalyzer.push_back(tempPcaAnalyzer3);
pcaAnalyzer.push_back(tempPcaAnalyzer4);
}
void ProgSortByStatistics::processInputPrepare(MetaData &SF)
{
PCAMahalanobisAnalyzer tempPcaAnalyzer;
tempPcaAnalyzer.clear();
Image<double> img;
MultidimArray<double> img2;
MultidimArray<int> radial_count;
MultidimArray<double> radial_avg;
Matrix1D<int> center(2);
center.initZeros();
if (verbose>0)
std::cout << " Processing training set ..." << std::endl;
int nr_imgs = SF.size();
if (verbose>0)
init_progress_bar(nr_imgs);
int c = XMIPP_MAX(1, nr_imgs / 60);
int imgno = 0, imgnoPCA=0;
MultidimArray<float> v;
MultidimArray<int> distance;
int dim;
bool thereIsEnable=SF.containsLabel(MDL_ENABLED);
bool first=true;
FOR_ALL_OBJECTS_IN_METADATA(SF)
{
if (thereIsEnable)
{
int enabled;
SF.getValue(MDL_ENABLED,enabled,__iter.objId);
if (enabled==-1)
continue;
}
img.readApplyGeo(SF,__iter.objId);
if (targetXdim!=-1 && targetXdim!=XSIZE(img()))
selfScaleToSize(LINEAR,img(),targetXdim,targetXdim,1);
MultidimArray<double> &mI=img();
mI.setXmippOrigin();
mI.statisticsAdjust(0,1);
// Overall statistics
Histogram1D hist;
compute_hist(mI,hist,-4,4,31);
// Radial profile
img2.resizeNoCopy(mI);
FOR_ALL_DIRECT_ELEMENTS_IN_MULTIDIMARRAY(img2)
{
double val=DIRECT_MULTIDIM_ELEM(mI,n);
DIRECT_MULTIDIM_ELEM(img2,n)=val*val;
}
if (first)
{
radialAveragePrecomputeDistance(img2, center, distance, dim);
first=false;
}
fastRadialAverage(img2, distance, dim, radial_avg, radial_count);
// Build vector
v.initZeros(XSIZE(hist)+XSIZE(img2)/2);
int idx=0;
FOR_ALL_DIRECT_ELEMENTS_IN_ARRAY1D(hist)
v(idx++)=(float)DIRECT_A1D_ELEM(hist,i);
for (size_t i=0; i<XSIZE(img2)/2; i++)
v(idx++)=(float)DIRECT_A1D_ELEM(radial_avg,i);
tempPcaAnalyzer.addVector(v);
if (imgno % c == 0 && verbose>0)
progress_bar(imgno);
imgno++;
imgnoPCA++;
}
if (verbose>0)
progress_bar(nr_imgs);
MultidimArray<double> vavg,vstddev;
tempPcaAnalyzer.computeStatistics(vavg,vstddev);
tempPcaAnalyzer.evaluateZScore(2,20,false);
pcaAnalyzer.insert(pcaAnalyzer.begin(), tempPcaAnalyzer);
}
