void singularValueDecomposition(GArgReader& args)
{
// Load
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
// Parse options
string ufilename = "u.arff";
string sigmafilename;
string vfilename = "v.arff";
int maxIters = 100;
while(args.size() > 0)
{
if(args.if_pop("-ufilename"))
ufilename = args.pop_string();
else if(args.if_pop("-sigmafilename"))
sigmafilename = args.pop_string();
else if(args.if_pop("-vfilename"))
vfilename = args.pop_string();
else if(args.if_pop("-maxiters"))
maxIters = args.pop_uint();
else
ThrowError("Invalid option: ", args.peek());
}
GMatrix* pU;
double* pDiag;
GMatrix* pV;
pData->singularValueDecomposition(&pU, &pDiag, &pV, false, maxIters);
Holder<GMatrix> hU(pU);
ArrayHolder<double> hDiag(pDiag);
Holder<GMatrix> hV(pV);
pU->saveArff(ufilename.c_str());
pV->saveArff(vfilename.c_str());
if(sigmafilename.length() > 0)
{
GMatrix sigma(pU->rows(), pV->rows());
sigma.setAll(0.0);
size_t m = std::min(sigma.rows(), (size_t)sigma.cols());
for(size_t i = 0; i < m; i++)
sigma.row(i)[i] = pDiag[i];
sigma.saveArff(sigmafilename.c_str());
}
else
{
GVec::print(cout, 14, pDiag, std::min(pU->rows(), pV->rows()));
cout << "\n";
}
}
void split(GArgReader& args)
{
// Load
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
int pats = (int)pData->rows() - args.pop_uint();
if(pats < 0)
ThrowError("out of range. The data only has ", to_str(pData->rows()), " rows.");
const char* szFilename1 = args.pop_string();
const char* szFilename2 = args.pop_string();
unsigned int nSeed = getpid() * (unsigned int)time(NULL);
bool shouldShuffle = false;
while(args.size() > 0){
if(args.if_pop("-shuffle")){
shouldShuffle = true;
}else if(args.if_pop("-seed")){
nSeed = args.pop_uint();
}else
ThrowError("Invalid option: ", args.peek());
}
// Shuffle if necessary
GRand rng(nSeed);
if(shouldShuffle){
pData->shuffle(rng);
}
// Split
GMatrix other(pData->relation());
pData->splitBySize(&other, pats);
pData->saveArff(szFilename1);
other.saveArff(szFilename2);
}
void Loader::loadAirPassengerData(GMatrix &trainFeat, GMatrix &trainLab, GMatrix &testFeat, GMatrix &testLab)
{
GMatrix raw;
raw.loadArff("data/air_passengers.arff");
size_t dims = 1;
size_t offset = 0;
size_t train_size = 72;
size_t test_size = 72;
double *x, *y;
trainFeat.resize(train_size, 1);
trainLab.resize(train_size, dims);
testFeat.resize(test_size, 1);
testLab.resize(test_size, dims);
double log_10 = log(10);
double vert_offset = 2;
double scale = 10;//0.1;
for(size_t i = 0; i < train_size + test_size; i++)
{
if(i < train_size)
{
x = trainFeat[i];
y = trainLab[i];
}
else
{
x = testFeat[i - train_size];
y = testLab[i - train_size];
}
*x = double(i) / train_size;
*y = ((log(scale * raw[offset + i][0]) / log_10) - vert_offset);
}
trainLab.saveArff("out/train.arff");
testLab.saveArff("out/test.arff");
}
void Loader::loadOzoneData(GMatrix &trainFeat, GMatrix &trainLab, GMatrix &testFeat, GMatrix &testLab)
{
GMatrix raw;
raw.loadArff("data/mhsets_monthly-ozone.arff");
size_t dims = 1;
size_t offset = 0;
size_t train_size = 108;
size_t test_size = 44;
double *x, *y;
trainFeat.resize(train_size, 1);
trainLab.resize(train_size, dims);
testFeat.resize(test_size, 1);
testLab.resize(test_size, dims);
for(size_t i = 0; i < train_size + test_size; i++)
{
if(i < train_size)
{
x = trainFeat[i];
y = trainLab[i];
}
else
{
x = testFeat[i - train_size];
y = testLab[i - train_size];
}
*x = double(i) / train_size;
*y = log(raw[offset + i][0]) / log(10);
}
trainLab.saveArff("out/train.arff");
testLab.saveArff("out/test.arff");
}
void attributeSelector(GArgReader& args)
{
// Load the data
size_t labelDims;
std::vector<size_t> originalIndices;
GMatrix data;
loadDataWithSwitches(data, args, labelDims, originalIndices);
// Parse the options
unsigned int seed = getpid() * (unsigned int)time(NULL);
int targetFeatures = 1;
string outFilename = "";
while(args.next_is_flag())
{
if(args.if_pop("-seed"))
seed = args.pop_uint();
else if(args.if_pop("-out"))
{
targetFeatures = args.pop_uint();
outFilename = args.pop_string();
}
else
throw Ex("Invalid neighbor finder option: ", args.peek());
}
// Do the attribute selection
GRand prng(seed);
GAttributeSelector as(labelDims, targetFeatures, &prng);
if(outFilename.length() > 0)
{
as.train(data);
GMatrix* pDataOut = as.transformBatch(data);
Holder<GMatrix> hDataOut(pDataOut);
cout << "Reduced data saved to " << outFilename.c_str() << ".\n";
pDataOut->saveArff(outFilename.c_str());
}
else
as.train(data);
cout << "\nAttribute rankings from most salient to least salient. (Attributes are zero-indexed.)\n";
GArffRelation* pRel = (GArffRelation*)data.relation().get();
for(size_t i = 0; i < as.ranks().size(); i++)
cout << originalIndices.at(as.ranks()[i]) << " " << pRel->attrName(as.ranks()[i]) << "\n";
}
