bool testpca(bool silent)
{
bool result;
int passcount;
int maxn;
int maxm;
double threshold;
int m;
int n;
int i;
int j;
int k;
int info;
ap::real_1d_array means;
ap::real_1d_array s;
ap::real_1d_array t2;
ap::real_1d_array t3;
ap::real_2d_array v;
ap::real_2d_array x;
double t;
double h;
double tmean;
double tmeans;
double tstddev;
double tstddevs;
double tmean2;
double tmeans2;
double tstddev2;
double tstddevs2;
bool pcaconverrors;
bool pcaorterrors;
bool pcavarerrors;
bool pcaopterrors;
bool waserrors;
//
// Primary settings
//
maxm = 10;
maxn = 100;
passcount = 1;
threshold = 1000*ap::machineepsilon;
waserrors = false;
pcaconverrors = false;
pcaorterrors = false;
pcavarerrors = false;
pcaopterrors = false;
//
// Test 1: N random points in M-dimensional space
//
for(m = 1; m <= maxm; m++)
{
for(n = 1; n <= maxn; n++)
{
//
// Generate task
//
x.setbounds(0, n-1, 0, m-1);
means.setbounds(0, m-1);
for(j = 0; j <= m-1; j++)
{
means(j) = 1.5*ap::randomreal()-0.75;
}
for(i = 0; i <= n-1; i++)
{
for(j = 0; j <= m-1; j++)
{
x(i,j) = means(j)+(2*ap::randomreal()-1);
}
}
//
// Solve
//
pcabuildbasis(x, n, m, info, s, v);
if( info!=1 )
{
pcaconverrors = true;
continue;
}
//
// Orthogonality test
//
for(i = 0; i <= m-1; i++)
{
for(j = 0; j <= m-1; j++)
{
t = ap::vdotproduct(&v(0, i), v.getstride(), &v(0, j), v.getstride(), ap::vlen(0,m-1));
if( i==j )
{
t = t-1;
}
pcaorterrors = pcaorterrors||ap::fp_greater(fabs(t),threshold);
}
}
//
// Variance test
//
t2.setbounds(0, n-1);
for(k = 0; k <= m-1; k++)
{
for(i = 0; i <= n-1; i++)
{
t = ap::vdotproduct(&x(i, 0), 1, &v(0, k), v.getstride(), ap::vlen(0,m-1));
t2(i) = t;
}
calculatemv(t2, n, tmean, tmeans, tstddev, tstddevs);
if( n!=1 )
{
t = ap::sqr(tstddev)*n/(n-1);
}
else
{
t = 0;
}
pcavarerrors = pcavarerrors||ap::fp_greater(fabs(t-s(k)),threshold);
}
for(k = 0; k <= m-2; k++)
{
pcavarerrors = pcavarerrors||ap::fp_less(s(k),s(k+1));
}
//
// Optimality: different perturbations in V[..,0] can't
// increase variance of projection - can only decrease.
//
t2.setbounds(0, n-1);
t3.setbounds(0, n-1);
for(i = 0; i <= n-1; i++)
{
t = ap::vdotproduct(&x(i, 0), 1, &v(0, 0), v.getstride(), ap::vlen(0,m-1));
t2(i) = t;
}
calculatemv(t2, n, tmean, tmeans, tstddev, tstddevs);
for(k = 0; k <= 2*m-1; k++)
{
h = 0.001;
if( k%2!=0 )
{
h = -h;
}
ap::vmove(&t3(0), 1, &t2(0), 1, ap::vlen(0,n-1));
ap::vadd(&t3(0), 1, &x(0, k/2), x.getstride(), ap::vlen(0,n-1), h);
t = 0;
for(j = 0; j <= m-1; j++)
{
if( j!=k/2 )
{
t = t+ap::sqr(v(j,0));
}
else
{
t = t+ap::sqr(v(j,0)+h);
}
}
t = 1/sqrt(t);
ap::vmul(&t3(0), 1, ap::vlen(0,n-1), t);
calculatemv(t3, n, tmean2, tmeans2, tstddev2, tstddevs2);
pcaopterrors = pcaopterrors||ap::fp_greater(tstddev2,tstddev+threshold);
}
}
}
//
// Special test for N=0
//
for(m = 1; m <= maxm; m++)
{
//
// Solve
//
pcabuildbasis(x, 0, m, info, s, v);
if( info!=1 )
{
pcaconverrors = true;
continue;
}
//
// Orthogonality test
//
for(i = 0; i <= m-1; i++)
{
for(j = 0; j <= m-1; j++)
{
t = ap::vdotproduct(&v(0, i), v.getstride(), &v(0, j), v.getstride(), ap::vlen(0,m-1));
if( i==j )
{
t = t-1;
}
pcaorterrors = pcaorterrors||ap::fp_greater(fabs(t),threshold);
}
}
}
//
// Final report
//
waserrors = pcaconverrors||pcaorterrors||pcavarerrors||pcaopterrors;
if( !silent )
{
printf("PCA TEST\n");
printf("TOTAL RESULTS: ");
if( !waserrors )
{
printf("OK\n");
}
else
{
printf("FAILED\n");
}
printf("* CONVERGENCE ");
if( !pcaconverrors )
{
printf("OK\n");
}
else
{
printf("FAILED\n");
}
printf("* ORTOGONALITY ");
if( !pcaorterrors )
{
printf("OK\n");
}
else
{
printf("FAILED\n");
}
printf("* VARIANCE REPORT ");
if( !pcavarerrors )
{
printf("OK\n");
}
else
{
printf("FAILED\n");
}
printf("* OPTIMALITY ");
if( !pcaopterrors )
{
printf("OK\n");
}
else
{
printf("FAILED\n");
}
if( waserrors )
{
printf("TEST SUMMARY: FAILED\n");
}
else
{
printf("TEST SUMMARY: PASSED\n");
}
printf("\n\n");
}
result = !waserrors;
return result;
}
int main(int argc, const char * argv[])
{
FILE * pFile;
FILE * outputFile;
bool debug = false;
bool debugEig = true;
alglib::real_2d_array ptInput;
//Defaults (for my mac)
const char * rootDirectory = "/Users/AdamDossa/Documents/Columbia/GRA/Babel/";
const char * currentDirectory = "/Users/AdamDossa/Documents/XCode/Babel_SGD/Babel_SGD/log/";
//Get root directory from args or use default
if (argc > 1)
{
rootDirectory = argv[1];
}
if (argc > 2)
{
currentDirectory = argv[2];
}
//We want to find an unused log file name (to some limit)
char logFileName[200];
for (int i = 0; i < 100; i++)
{
snprintf(logFileName, sizeof(char) * 200,"%s/log/log_pca-%d.txt.%d", currentDirectory, NUM_FILES, i);
outputFile = fopen(logFileName,"r");
if (outputFile)
{
continue;
} else {
outputFile = fopen(logFileName,"w");
break;
}
}
fprintf(outputFile,"Log file: %s\n", logFileName);
//First calculate the number of training examples (since not every file is guaranteed to have 250 rows)
fprintf(outputFile, "Calculating number of training examples\n");
int noOfTrainingExamples = 0;
for (int i = 0; i < NUM_FILES; i++) {
char fName[200];
snprintf(fName, sizeof(char) * 200,"%s/labels/train.%d.lab", rootDirectory, i);
pFile = fopen(fName,"rb");
int n;
fread(&n,4,1,pFile);
n = ntohl(n);
noOfTrainingExamples += n;
//printf("File: %d No: %f\n",i,((float) noOfTrainingExamples) / 250.0f);
fclose(pFile);
}
fprintf(outputFile, "No of training examples: %d\n", noOfTrainingExamples);
fflush(outputFile);
//Set input size
ptInput.setlength(noOfTrainingExamples, FEATURE_COLS);
//Now read in the features - hold these in an array - assume same number as training examples
fprintf(outputFile,"Reading in features\n");
int readSoFar = 0;
//double * features = (double *) malloc(sizeof(double) * noOfTrainingExamples * FEATURE_COLS);
//double featureMeans[FEATURE_COLS];
// for (int i = 0; i< FEATURE_COLS; i++)
// {
// featureMeans[i] = 0.0;
// }
for (int i = 0; i < NUM_FILES; i++) {
char fName[200];
snprintf(fName, sizeof(char) * 200,"%s/features/train.%d.fea", rootDirectory, i);
pFile = fopen(fName,"rb");
int n;
fread(&n,4,1,pFile);
n = ntohl(n);
for (int j = 0; j < n; j++)
{
int m;
fread(&m,4,1,pFile);
m = ntohl(m);
float * tempFeatures = (float *) malloc(sizeof(float) * m);
fread(&tempFeatures[0],sizeof(float),m,pFile);
for (int k = 0; k < m; k++)
{
ptInput[readSoFar + j][k] = static_cast<double>(bin2flt(&tempFeatures[k]));
// featureMeans[k] += features[readSoFar + k];
}
free(tempFeatures);
}
readSoFar += n;
fclose(pFile);
}
// for (int i = 0; i < FEATURE_COLS; i++)
// {
// featureMeans[i] = featureMeans[i] / noOfTrainingExamples;
// }
// if (debug) {
// for (int i = 0; i < (noOfTrainingExamples * FEATURE_COLS); i++)
// {
// fprintf(outputFile,"Train: Feature coordinate: %d has value: %f\n",i,features[i]);
// }
// for (int i = 0; i < FEATURE_COLS; i++)
// {
// fprintf(outputFile, "Train: Feature coordinate: %d has mean: %f\n",i,featureMeans[i]);
// }
// }
fflush(outputFile);
//Now center data using featureMeans - not necessary for PCABuildBasis
// for (int i = 0; i < noOfTrainingExamples; i++)
// {
// for (int j = 0; j < FEATURE_COLS; j++)
// {
// features[(i * FEATURE_COLS) + j] = features[(i * FEATURE_COLS) + j] - featureMeans[j];
// }
// }
// if (debug) {
// for (int i = 0; i < (noOfTrainingExamples * FEATURE_COLS); i++)
// {
// fprintf(outputFile,"Train: Feature coordinate: %d has centered value: %f\n",i,features[i]);
// }
// }
// fflush(outputFile);
//Now run PCA
fprintf(outputFile,"Running PCA\n");
fflush(outputFile);
//Run PCA on input
// alglib::real_2d_array ptInput;
// ptInput.setcontent(noOfTrainingExamples, FEATURE_COLS , features);
// free(features);
fprintf(outputFile, "ptInput created\n");
fflush(outputFile);
alglib::ae_int_t info;
alglib::real_1d_array eigValues;
alglib::real_2d_array eigVectors;
if (debug) {
for (int i = 0; i < noOfTrainingExamples; i++)
{
for (int j = 0; j < FEATURE_COLS; j++)
{
fprintf(outputFile, "ptInput: %d, %d, %f\n", i,j, ptInput[i][j]);
}
}
}
try {
pcabuildbasis(ptInput, noOfTrainingExamples, FEATURE_COLS, info, eigValues, eigVectors);
} catch (alglib::ap_error& err) {
std::cout << err.msg;
}
//pcabuildbasis(ptInput, noOfTrainingExamples, FEATURE_COLS, info, eigValues, eigVectors);
if (debugEig) {
for (int i = 0; i < FEATURE_COLS; i++)
{
fprintf(outputFile, "EIGVALS: %f\n", eigValues[i]);
}
}
fflush(outputFile);
//Now compute scores
// alglib::real_2d_array scores;
// scores.setlength(noOfTrainingExamples, FEATURE_COLS);
// alglib::rmatrixgemm(noOfTrainingExamples, FEATURE_COLS ,FEATURE_COLS, 1, ptInput, 0,0,0, eigVectors, 0,0,0, 0, scores,0,0);
// if (debug)
// {
// for (int i = 0; i < noOfTrainingExamples; i++)
// {
// for (int j = 0; j < FEATURE_COLS; j++)
// {
// fprintf(outputFile, "PCA SCORES: %d, %d, %f\n", i,j,scores[i][j]);
// }
// }
// }
// fclose(outputFile);
//Write out loadings to a file
char fName[200];
snprintf(fName, sizeof(char) * 200,"%s/loadings/loadings-%d.load", currentDirectory, NUM_FILES);
pFile = fopen(fName,"wb");
for (int k = 0; k < FEATURE_COLS; k++)
{
for (int j = 0; j < FEATURE_COLS; j++)
{
fwrite(&eigVectors[k][j],sizeof(double),1,pFile);
}
}
fclose(pFile);
fclose(outputFile);
return 0;
}
bool PCAWrapper::train(vector<vector<double> > &inputData, int pDim, string outputFile) {
if (inputData.size() < 1 || inputData[0].size() < 1)
return false;
size_t numSamples = inputData.size();
oDim = inputData[0].size();
double *dataMat = new double[numSamples * oDim];
aveVec = new double[oDim];
for (int i = 0; i < oDim; i++)
aveVec[i] = 0.0;
for (int i = 0; i < numSamples; i++)
for (int j = 0; j < oDim; j++) {
dataMat[i*oDim+j] = inputData[i][j];
aveVec[j] += inputData[i][j];
}
for (int i = 0; i < oDim; i++)
aveVec[i] /= (double) numSamples;
alglib::real_2d_array ptInput;
ptInput.setcontent(numSamples, oDim, dataMat);
alglib::ae_int_t info;
alglib::real_1d_array eigValues;
alglib::real_2d_array eigVectors;
pcabuildbasis(ptInput, numSamples, oDim, info, eigValues, eigVectors);
delete [] dataMat;
size_t cols = eigVectors.cols();
if (cols < pDim)
pDim = cols;
this->pDim = pDim;
projMat = new double[pDim * oDim];
eigVec = new double[pDim];
for (int i = 0; i < pDim; i++) {
eigVec[i] = 1 / sqrt(eigValues[i]);
for (int j = 0; j < oDim; j++)
projMat[i*oDim + j] = eigVectors[j][i];
}
// save to file
ofstream fout;
fout.open(outputFile.c_str());
if (!fout.is_open()) {
cout<<"Cannot save projection matrix to "<<outputFile<<endl;
return false;
}
fout<<oDim<<" "<<pDim<<endl;
fout<<projMat[0];
for (int i = 1; i < oDim*pDim; i++)
fout<<" "<<projMat[i];
fout<<endl;
fout<<aveVec[0];
for (int i = 1; i < oDim; i++)
fout<<" "<<aveVec[i];
fout<<endl;
fout<<eigVec[0];
for (int i = 1; i < pDim; i++)
fout<<" "<<eigVec[i];
fout<<endl;
fout.close();
return true;
}
