void addNoise(GArgReader& args)
{
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
double dev = args.pop_double();
// Parse the options
unsigned int seed = getpid() * (unsigned int)time(NULL);
int excludeLast = 0;
while(args.next_is_flag())
{
if(args.if_pop("-seed"))
seed = args.pop_uint();
else if(args.if_pop("-excludelast"))
excludeLast = args.pop_uint();
else
ThrowError("Invalid neighbor finder option: ", args.peek());
}
GRand prng(seed);
size_t cols = pData->cols() - excludeLast;
for(size_t r = 0; r < pData->rows(); r++)
{
double* pRow = pData->row(r);
for(size_t c = 0; c < cols; c++)
*(pRow++) += dev * prng.normal();
}
pData->print(cout);
}
void lle(GArgReader& args)
{
// Load the file and params
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
unsigned int nSeed = getpid() * (unsigned int)time(NULL);
GRand prng(nSeed);
GNeighborFinder* pNF = instantiateNeighborFinder(pData, &prng, args);
Holder<GNeighborFinder> hNF(pNF);
int targetDims = args.pop_uint();
// Parse Options
while(args.size() > 0)
{
if(args.if_pop("-seed"))
prng.setSeed(args.pop_uint());
else
throw Ex("Invalid option: ", args.peek());
}
// Transform the data
GLLE transform(pNF->neighborCount(), targetDims, &prng);
transform.setNeighborFinder(pNF);
GMatrix* pDataAfter = transform.doit(*pData);
Holder<GMatrix> hDataAfter(pDataAfter);
pDataAfter->print(cout);
}
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 crossValidate(GArgReader& args)
{
// Parse options
unsigned int seed = getpid() * (unsigned int)time(NULL);
size_t folds = 2;
while(args.next_is_flag())
{
if(args.if_pop("-seed"))
seed = args.pop_uint();
else if(args.if_pop("-folds"))
folds = args.pop_uint();
else
ThrowError("Invalid crossvalidate option: ", args.peek());
}
if(folds < 2)
ThrowError("There must be at least 2 folds.");
// Load the data
if(args.size() < 1)
ThrowError("No dataset specified.");
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
// Instantiate the recommender
GRand prng(seed);
GCollaborativeFilter* pModel = InstantiateAlgorithm(prng, args);
Holder<GCollaborativeFilter> hModel(pModel);
if(args.size() > 0)
ThrowError("Superfluous argument: ", args.peek());
// Do cross-validation
double mae;
double mse = pModel->crossValidate(*pData, folds, &mae);
cout << "RMSE=" << sqrt(mse) << ", MSE=" << mse << ", MAE=" << mae << "\n";
}
void kmeans(GArgReader& args)
{
// Load the file and params
GMatrix data;
loadData(data, args.pop_string());
int clusters = args.pop_uint();
// Parse Options
unsigned int nSeed = getpid() * (unsigned int)time(NULL);
size_t reps = 1;
while(args.size() > 0)
{
if(args.if_pop("-seed"))
nSeed = args.pop_uint();
else if(args.if_pop("-reps"))
reps = args.pop_uint();
else
throw Ex("Invalid option: ", args.peek());
}
// Do the clustering
GRand prng(nSeed);
GKMeans clusterer(clusters, &prng);
clusterer.setReps(reps);
GMatrix* pOut = clusterer.reduce(data);
std::unique_ptr<GMatrix> hOut(pOut);
pOut->print(cout);
}
void isomap(GArgReader& args)
{
// Load the file and params
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
unsigned int nSeed = getpid() * (unsigned int)time(NULL);
GRand prng(nSeed);
GNeighborFinder* pNF = instantiateNeighborFinder(pData, &prng, args);
Holder<GNeighborFinder> hNF(pNF);
int targetDims = args.pop_uint();
// Parse Options
bool tolerant = false;
while(args.size() > 0)
{
if(args.if_pop("-seed"))
prng.setSeed(args.pop_uint());
else if(args.if_pop("-tolerant"))
tolerant = true;
else
throw Ex("Invalid option: ", args.peek());
}
// Transform the data
GIsomap transform(pNF->neighborCount(), targetDims, &prng);
transform.setNeighborFinder(pNF);
if(tolerant)
transform.dropDisconnectedPoints();
GMatrix* pDataAfter = transform.reduce(*pData);
Holder<GMatrix> hDataAfter(pDataAfter);
pDataAfter->print(cout);
}
void breadthFirstUnfolding(GArgReader& args)
{
// Load the file and params
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
size_t nSeed = getpid() * (unsigned int)time(NULL);
GRand prng(nSeed);
GNeighborFinder* pNF = instantiateNeighborFinder(pData, &prng, args);
Holder<GNeighborFinder> hNF(pNF);
int targetDims = args.pop_uint();
// Parse Options
size_t reps = 1;
Holder<GMatrix> hControlData(NULL);
while(args.size() > 0)
{
if(args.if_pop("-seed"))
nSeed = args.pop_uint();
else if(args.if_pop("-reps"))
reps = args.pop_uint();
else
throw Ex("Invalid option: ", args.peek());
}
// Transform the data
GBreadthFirstUnfolding transform(reps, pNF->neighborCount(), targetDims);
transform.rand().setSeed(nSeed);
transform.setNeighborFinder(pNF);
GMatrix* pDataAfter = transform.reduce(*pData);
Holder<GMatrix> hDataAfter(pDataAfter);
pDataAfter->print(cout);
}
void curviness2(GArgReader& args)
{
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
GNormalize norm;
GMatrix* pDataNormalized = norm.doit(*pData);
Holder<GMatrix> hDataNormalized(pDataNormalized);
hData.reset();
pData = NULL;
// Parse Options
size_t maxEigs = 10;
unsigned int seed = getpid() * (unsigned int)time(NULL);
Holder<GMatrix> hControlData(NULL);
while(args.size() > 0)
{
if(args.if_pop("-seed"))
seed = args.pop_uint();
else if(args.if_pop("-maxeigs"))
maxEigs = args.pop_uint();
else
throw Ex("Invalid option: ", args.peek());
}
GRand rand(seed);
size_t targetDims = std::min(maxEigs, pDataNormalized->cols());
// Do linear PCA
GNeuroPCA np1(targetDims, &rand);
np1.setActivation(new GActivationIdentity());
np1.computeEigVals();
GMatrix* pResults1 = np1.doit(*pDataNormalized);
Holder<GMatrix> hResults1(pResults1);
double* pEigVals1 = np1.eigVals();
for(size_t i = 0; i + 1 < targetDims; i++)
pEigVals1[i] = sqrt(pEigVals1[i]) - sqrt(pEigVals1[i + 1]);
size_t max1 = GVec::indexOfMax(pEigVals1, targetDims - 1, &rand);
double v1 = (double)max1;
if(max1 > 0 && max1 + 2 < targetDims)
v1 += (pEigVals1[max1 - 1] - pEigVals1[max1 + 1]) / (2.0 * (pEigVals1[max1 - 1] + pEigVals1[max1 + 1] - 2.0 * pEigVals1[max1]));
// Do non-linear PCA
GNeuroPCA np2(targetDims, &rand);
np1.setActivation(new GActivationLogistic());
np2.computeEigVals();
GMatrix* pResults2 = np2.doit(*pDataNormalized);
Holder<GMatrix> hResults2(pResults2);
double* pEigVals2 = np2.eigVals();
for(size_t i = 0; i + 1 < targetDims; i++)
pEigVals2[i] = sqrt(pEigVals2[i]) - sqrt(pEigVals2[i + 1]);
size_t max2 = GVec::indexOfMax(pEigVals2, targetDims - 1, &rand);
double v2 = (double)max2;
if(max2 > 0 && max2 + 2 < targetDims)
v2 += (pEigVals2[max2 - 1] - pEigVals2[max2 + 1]) / (2.0 * (pEigVals2[max2 - 1] + pEigVals2[max2 + 1] - 2.0 * pEigVals2[max2]));
// Compute the difference in where the eigenvalues fall
cout.precision(14);
cout << (v1 - v2) << "\n";
}
void ManifoldSculpting(GArgReader& args)
{
// Load the file and params
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
unsigned int nSeed = getpid() * (unsigned int)time(NULL);
GRand prng(nSeed);
GNeighborFinder* pNF = instantiateNeighborFinder(pData, &prng, args);
Holder<GNeighborFinder> hNF(pNF);
size_t targetDims = args.pop_uint();
// Parse Options
const char* szPreprocessedData = NULL;
double scaleRate = 0.999;
while(args.size() > 0)
{
if(args.if_pop("-seed"))
prng.setSeed(args.pop_uint());
else if(args.if_pop("-continue"))
szPreprocessedData = args.pop_string();
else if(args.if_pop("-scalerate"))
scaleRate = args.pop_double();
else
throw Ex("Invalid option: ", args.peek());
}
// Load the hint data
GMatrix* pDataHint = NULL;
Holder<GMatrix> hDataHint(NULL);
if(szPreprocessedData)
{
pDataHint = loadData(szPreprocessedData);
hDataHint.reset(pDataHint);
if(pDataHint->relation()->size() != targetDims)
throw Ex("Wrong number of dims in the hint data");
if(pDataHint->rows() != pData->rows())
throw Ex("Wrong number of patterns in the hint data");
}
// Transform the data
GManifoldSculpting transform(pNF->neighborCount(), targetDims, &prng);
transform.setSquishingRate(scaleRate);
if(pDataHint)
transform.setPreprocessedData(hDataHint.release());
transform.setNeighborFinder(pNF);
GMatrix* pDataAfter = transform.doit(*pData);
Holder<GMatrix> hDataAfter(pDataAfter);
pDataAfter->print(cout);
}
void splitClass(GArgReader& args)
{
const char* filename = args.pop_string();
GMatrix* pData = loadData(filename);
Holder<GMatrix> hData(pData);
size_t classAttr = args.pop_uint();
bool dropClass = false;
while(args.size() > 0)
{
if(args.if_pop("-dropclass"))
dropClass = true;
else
ThrowError("Invalid option: ", args.peek());
}
for(size_t i = 0; i < pData->relation()->valueCount(classAttr); i++)
{
GMatrix tmp(pData->relation(), pData->heap());
pData->splitByNominalValue(&tmp, classAttr, i);
std::ostringstream oss;
PathData pd;
GFile::parsePath(filename, &pd);
string fn;
fn.assign(filename + pd.fileStart, pd.extStart - pd.fileStart);
oss << fn << "_";
pData->relation()->printAttrValue(oss, classAttr, (double)i);
oss << ".arff";
string s = oss.str();
if(dropClass)
tmp.deleteColumn(classAttr);
tmp.saveArff(s.c_str());
}
}
void aggregateCols(GArgReader& args)
{
size_t c = args.pop_uint();
vector<string> files;
GFile::fileList(files);
GMatrix* pResults = NULL;
Holder<GMatrix> hResults;
size_t i = 0;
for(vector<string>::iterator it = files.begin(); it != files.end(); it++)
{
PathData pd;
GFile::parsePath(it->c_str(), &pd);
if(strcmp(it->c_str() + pd.extStart, ".arff") != 0)
continue;
GMatrix* pData = loadData(it->c_str());
Holder<GMatrix> hData(pData);
if(!pResults)
{
pResults = new GMatrix(pData->rows(), files.size());
hResults.reset(pResults);
}
pResults->copyColumns(i, pData, c, 1);
i++;
}
pResults->print(cout);
}
void nominalToCat(GArgReader& args)
{
// Load the file
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
// Parse Options
int maxValues = 12;
while(args.size() > 0)
{
if(args.if_pop("-maxvalues"))
maxValues = args.pop_uint();
else
ThrowError("Invalid option: ", args.peek());
}
// Transform the data
GNominalToCat transform(maxValues);
transform.train(*pData);
GMatrix* pDataNew = transform.transformBatch(*pData);
Holder<GMatrix> hDataNew(pDataNew);
// Print results
pDataNew->print(cout);
}
void neighbors(GArgReader& args)
{
// Load the data
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
int neighborCount = args.pop_uint();
// Find the neighbors
GKdTree neighborFinder(pData, neighborCount, NULL, true);
GTEMPBUF(size_t, neighbors, neighborCount);
GTEMPBUF(double, distances, neighborCount);
double sumClosest = 0;
double sumAll = 0;
for(size_t i = 0; i < pData->rows(); i++)
{
neighborFinder.neighbors(neighbors, distances, i);
neighborFinder.sortNeighbors(neighbors, distances);
sumClosest += sqrt(distances[0]);
for(int j = 0; j < neighborCount; j++)
sumAll += sqrt(distances[j]);
}
cout.precision(14);
cout << "average closest neighbor distance = " << (sumClosest / pData->rows()) << "\n";
cout << "average neighbor distance = " << (sumAll / (pData->rows() * neighborCount)) << "\n";
}
void GRecommenderLib::transacc(GArgReader& args)
{
// Parse options
unsigned int seed = getpid() * (unsigned int)time(NULL);
while(args.next_is_flag())
{
if(args.if_pop("-seed"))
seed = args.pop_uint();
else
throw Ex("Invalid crossvalidate option: ", args.peek());
}
// Load the data
if(args.size() < 1)
throw Ex("No training set specified.");
GMatrix train;
loadData(train, args.pop_string());
if(args.size() < 1)
throw Ex("No test set specified.");
GMatrix test;
loadData(test, args.pop_string());
// Instantiate the recommender
GCollaborativeFilter* pModel = InstantiateAlgorithm(args);
std::unique_ptr<GCollaborativeFilter> hModel(pModel);
if(args.size() > 0)
throw Ex("Superfluous argument: ", args.peek());
pModel->rand().setSeed(seed);
// Do cross-validation
double mae;
double mse = pModel->trainAndTest(train, test, &mae);
cout << "MSE=" << mse << ", MAE=" << mae << "\n";
}
void GRecommenderLib::precisionRecall(GArgReader& args)
{
// Parse options
unsigned int seed = getpid() * (unsigned int)time(NULL);
bool ideal = false;
while(args.next_is_flag())
{
if(args.if_pop("-seed"))
seed = args.pop_uint();
else if(args.if_pop("-ideal"))
ideal = true;
else
throw Ex("Invalid option: ", args.peek());
}
// Load the data
if(args.size() < 1)
throw Ex("No dataset specified.");
GMatrix data;
loadData(data, args.pop_string());
// Instantiate the recommender
GCollaborativeFilter* pModel = InstantiateAlgorithm(args);
std::unique_ptr<GCollaborativeFilter> hModel(pModel);
if(args.size() > 0)
throw Ex("Superfluous argument: ", args.peek());
pModel->rand().setSeed(seed);
// Generate precision-recall data
GMatrix* pResults = pModel->precisionRecall(data, ideal);
std::unique_ptr<GMatrix> hResults(pResults);
pResults->deleteColumns(2, 1); // we don't need the false-positive rate column
pResults->print(cout);
}
void fillMissingValues(GArgReader& args)
{
// Load
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
// Parse options
unsigned int nSeed = getpid() * (unsigned int)time(NULL);
bool random = false;
while(args.size() > 0)
{
if(args.if_pop("-seed"))
nSeed = args.pop_uint();
else if(args.if_pop("-random"))
random = true;
else
ThrowError("Invalid option: ", args.peek());
}
// Replace missing values and print
GRand prng(nSeed);
if(random)
{
for(size_t i = 0; i < pData->relation()->size(); i++)
pData->replaceMissingValuesRandomly(i, &prng);
}
else
{
for(size_t i = 0; i < pData->relation()->size(); i++)
pData->replaceMissingValuesWithBaseline(i);
}
pData->print(cout);
}
void transacc(GArgReader& args)
{
// Parse options
unsigned int seed = getpid() * (unsigned int)time(NULL);
while(args.next_is_flag())
{
if(args.if_pop("-seed"))
seed = args.pop_uint();
else
ThrowError("Invalid crossvalidate option: ", args.peek());
}
// Load the data
if(args.size() < 1)
ThrowError("No training set specified.");
GMatrix* pTrain = loadData(args.pop_string());
Holder<GMatrix> hTrain(pTrain);
if(args.size() < 1)
ThrowError("No test set specified.");
GMatrix* pTest = loadData(args.pop_string());
Holder<GMatrix> hTest(pTest);
// Instantiate the recommender
GRand prng(seed);
GCollaborativeFilter* pModel = InstantiateAlgorithm(prng, args);
Holder<GCollaborativeFilter> hModel(pModel);
if(args.size() > 0)
ThrowError("Superfluous argument: ", args.peek());
// Do cross-validation
double mae;
double mse = pModel->trainAndTest(*pTrain, *pTest, &mae);
cout << "MSE=" << mse << ", MAE=" << mae << "\n";
}
void correlation(GArgReader& args)
{
GMatrix* pA = loadData(args.pop_string());
Holder<GMatrix> hA(pA);
int attr1 = args.pop_uint();
int attr2 = args.pop_uint();
// Parse Options
bool aboutorigin = false;
while(args.size() > 0)
{
if(args.if_pop("-aboutorigin"))
aboutorigin = true;
else
ThrowError("Invalid option: ", args.peek());
}
double m1, m2;
if(aboutorigin)
{
m1 = 0;
m2 = 0;
}
else
{
m1 = pA->mean(attr1);
m2 = pA->mean(attr2);
}
double corr = pA->linearCorrelationCoefficient(attr1, m1, attr2, m2);
cout.precision(14);
cout << corr << "\n";
}
void precisionRecall(GArgReader& args)
{
// Parse options
unsigned int seed = getpid() * (unsigned int)time(NULL);
bool ideal = false;
while(args.next_is_flag())
{
if(args.if_pop("-seed"))
seed = args.pop_uint();
else if(args.if_pop("-ideal"))
ideal = true;
else
ThrowError("Invalid option: ", args.peek());
}
// Load the data
if(args.size() < 1)
ThrowError("No dataset specified.");
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
// Instantiate the recommender
GRand prng(seed);
GCollaborativeFilter* pModel = InstantiateAlgorithm(prng, args);
Holder<GCollaborativeFilter> hModel(pModel);
if(args.size() > 0)
ThrowError("Superfluous argument: ", args.peek());
// Generate precision-recall data
GMatrix* pResults = pModel->precisionRecall(*pData, ideal);
Holder<GMatrix> hResults(pResults);
pResults->deleteColumn(2); // we don't need the false-positive rate column
pResults->print(cout);
}
void enumerateValues(GArgReader& args)
{
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
size_t col = args.pop_uint();
if(pData->relation()->valueCount(col) > 0)
((GArffRelation*)pData->relation().get())->setAttrValueCount(col, 0);
else
{
size_t n = 0;
map<double,size_t> themap;
for(size_t i = 0; i < pData->rows(); i++)
{
double* pRow = pData->row(i);
map<double,size_t>::iterator it = themap.find(pRow[col]);
if(it == themap.end())
{
themap[pRow[col]] = n;
pRow[col] = (double)n;
n++;
}
else
pRow[col] = (double)it->second;
}
}
pData->print(cout);
}
void wilcoxon(GArgReader& args)
{
size_t n = args.pop_uint();
double w = args.pop_double();
double p = GMath::wilcoxonPValue(n, w);
cout << p << "\n";
}
void threshold(GArgReader& args){
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
unsigned column=args.pop_uint();
if(column >= hData->cols()){
std::stringstream msg;
if(hData->cols() >= 1){
msg << "The column to threshold is too large. It should be in "
<< "the range [0.." << (hData->cols()-1) << "].";
}else{
msg << "This data has no columns to threshold.";
}
ThrowError(msg.str());
}
if(hData->relation()->valueCount(column) != 0){
ThrowError("Can only use threshold on continuous attributes.");
}
double value = args.pop_double();
//Do the actual thresholding
for(size_t i = 0; i < hData->rows(); ++i){
double& v = hData->row(i)[column];
if(v <= value){ v = 0;
}else { v = 1; }
}
//Print the data
hData->print(cout);
}
void dropRows(GArgReader& args)
{
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
size_t newSize = args.pop_uint();
while(pData->rows() > newSize)
pData->deleteRow(pData->rows() - 1);
pData->print(cout);
}
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";
}
void rotate(GArgReader& args)
{
GMatrix* pA = loadData(args.pop_string());
Holder<GMatrix> hA(pA);
sp_relation relation = pA->relation();
unsigned colx = args.pop_uint();
if(colx >= pA->cols()){
ThrowError("Rotation first column index (",to_str(colx),") "
"should not be greater "
"than the largest index, which is ", to_str(pA->cols()-1),
".");
}
if(!relation->areContinuous(colx,1)){
ThrowError("Rotation first column index (",to_str(colx),") "
"should be continuous and it is not.");
}
unsigned coly = args.pop_uint();
if(coly >= pA->cols()){
ThrowError("Rotation second column index (",to_str(coly),") "
"should not be greater "
"than the largest index, which is ", to_str(pA->cols()-1),
".");
}
if(!relation->areContinuous(coly,1)){
ThrowError("Rotation second column index (",to_str(coly),") "
"should be continuous and it is not.");
}
double angle = args.pop_double();
angle = angle * M_PI / 180; //Convert from degrees to radians
double cosAngle = std::cos(angle);
double sinAngle = std::sin(angle);
for(std::size_t rowIdx = 0; rowIdx < pA->rows(); ++rowIdx){
double* row = (*pA)[rowIdx];
double x = row[colx];
double y = row[coly];
row[colx]=x*cosAngle-y*sinAngle;
row[coly]=x*sinAngle+y*cosAngle;
}
pA->print(cout);
}
void Discretize(GArgReader& args)
{
// Load the file
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
// Parse Options
size_t nFirst = 0;
size_t nLast = pData->relation()->size() - 1;
size_t nBuckets = std::max(2, (int)floor(sqrt((double)pData->rows() + 0.5)));
while(args.size() > 0)
{
if(args.if_pop("-buckets"))
nBuckets = args.pop_uint();
else if(args.if_pop("-colrange"))
{
nFirst = args.pop_uint();
nLast = args.pop_uint();
}
else
ThrowError("Invalid option: ", args.peek());
}
if(nFirst < 0 || nLast >= pData->relation()->size() || nLast < nFirst)
ThrowError("column index out of range");
// Discretize the continuous attributes in the specified range
for(size_t i = nFirst; i <= nLast; i++)
{
if(pData->relation()->valueCount(i) != 0)
continue;
double min, range;
pData->minAndRange(i, &min, &range);
for(size_t j = 0; j < pData->rows(); j++)
{
double* pPat = pData->row(j);
pPat[i] = (double)std::max((size_t)0, std::min(nBuckets - 1, (size_t)floor(((pPat[i] - min) * nBuckets) / range)));
}
((GArffRelation*)pData->relation().get())->setAttrValueCount(i, nBuckets);
}
// Print results
pData->print(cout);
}
void agglomerativeclusterer(GArgReader& args)
{
// Load the file and params
GMatrix data;
loadData(data, args.pop_string());
int clusters = args.pop_uint();
// Do the clustering
GAgglomerativeClusterer clusterer(clusters);
GMatrix* pOut = clusterer.reduce(data);
std::unique_ptr<GMatrix> hOut(pOut);
pOut->print(cout);
}
void splitFold(GArgReader& args)
{
// Load
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
size_t fold = args.pop_uint();
size_t folds = args.pop_uint();
if(fold >= folds)
ThrowError("fold index out of range. It must be less than the total number of folds.");
// Options
string filenameTrain = "train.arff";
string filenameTest = "test.arff";
while(args.size() > 0)
{
if(args.if_pop("-out"))
{
filenameTrain = args.pop_string();
filenameTest = args.pop_string();
}
else
ThrowError("Invalid option: ", args.peek());
}
// Copy relevant portions of the data
GMatrix train(pData->relation());
GMatrix test(pData->relation());
size_t begin = pData->rows() * fold / folds;
size_t end = pData->rows() * (fold + 1) / folds;
for(size_t i = 0; i < begin; i++)
train.copyRow(pData->row(i));
for(size_t i = begin; i < end; i++)
test.copyRow(pData->row(i));
for(size_t i = end; i < pData->rows(); i++)
train.copyRow(pData->row(i));
train.saveArff(filenameTrain.c_str());
test.saveArff(filenameTest.c_str());
}
///TODO: this command should be documented
void center(GArgReader& args)
{
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
unsigned int r = args.pop_uint();
size_t cols = pData->cols();
double* pRow = pData->row(r);
for(size_t i = 0; i < r; ++i)
GVec::subtract(pData->row(i), pRow, cols);
for(size_t i = r + 1; i < pData->rows(); ++i)
GVec::subtract(pData->row(i), pRow, cols);
GVec::setAll(pRow, 0.0, cols);
pData->print(cout);
}
void SwapAttributes(GArgReader& args)
{
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
size_t nAttr1 = args.pop_uint();
size_t nAttr2 = args.pop_uint();
size_t attrCount = pData->relation()->size();
if(nAttr1 >= attrCount)
ThrowError("Index out of range");
if(nAttr2 >= attrCount)
ThrowError("Index out of range");
pData->swapColumns(nAttr1, nAttr2);
pData->print(cout);
}