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 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 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 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 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 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 showError(GArgReader& args, const char* szAppName, const char* szMessage)
{
cerr << "_________________________________\n";
cerr << szMessage << "\n\n";
args.set_pos(1);
const char* szCommand = args.peek();
UsageNode* pUsageTree = makeClusterUsageTree();
std::unique_ptr<UsageNode> hUsageTree(pUsageTree);
if(szCommand)
{
UsageNode* pUsageCommand = pUsageTree->choice(szCommand);
if(pUsageCommand)
{
cerr << "Brief Usage Information:\n\n";
cerr << szAppName << " ";
pUsageCommand->print(cerr, 0, 3, 76, 1000, true);
}
else
{
cerr << "Brief Usage Information:\n\n";
pUsageTree->print(cerr, 0, 3, 76, 1, false);
}
}
else
{
pUsageTree->print(cerr, 0, 3, 76, 1, false);
cerr << "\nFor more specific usage information, enter as much of the command as you know.\n";
}
cerr << "\nTo see full usage information, run:\n " << szAppName << " usage\n\n";
cerr << "For a graphical tool that will help you to build a command, run:\n waffles_wizard\n";
cerr.flush();
}
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 showInstantiateNeighborFinderError(const char* szMessage, GArgReader& args)
{
cerr << "_________________________________\n";
cerr << szMessage << "\n\n";
const char* szNFName = args.peek();
UsageNode* pNFTree = makeNeighborUsageTree();
Holder<UsageNode> hNFTree(pNFTree);
if(szNFName)
{
UsageNode* pUsageAlg = pNFTree->choice(szNFName);
if(pUsageAlg)
{
cerr << "Partial Usage Information:\n\n";
pUsageAlg->print(cerr, 0, 3, 76, 1000, true);
}
else
{
cerr << "\"" << szNFName << "\" is not a recognized neighbor-finding techniqie. Try one of these:\n\n";
pNFTree->print(cerr, 0, 3, 76, 1, false);
}
}
else
{
cerr << "Expected a neighbor-finding technique. Here are some choices:\n";
pNFTree->print(cerr, 0, 3, 76, 1, false);
}
cerr << "\nTo see full usage information, run:\n waffles_transform usage\n\n";
cerr << "For a graphical tool that will help you to build a command, run:\n waffles_wizard\n";
cerr.flush();
}
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 AddIndexAttribute(GArgReader& args)
{
// Parse args
const char* filename = args.pop_string();
double nStartValue = 0.0;
double nIncrement = 1.0;
while(args.size() > 0)
{
if(args.if_pop("-start"))
nStartValue = args.pop_double();
else if(args.if_pop("-increment"))
nIncrement = args.pop_double();
else
ThrowError("Invalid option: ", args.peek());
}
GMatrix* pData = loadData(filename);
Holder<GMatrix> hData(pData);
GArffRelation* pIndexRelation = new GArffRelation();
pIndexRelation->addAttribute("index", 0, NULL);
sp_relation pIndexRel = pIndexRelation;
GMatrix indexes(pIndexRel);
indexes.newRows(pData->rows());
for(size_t i = 0; i < pData->rows(); i++)
indexes.row(i)[0] = nStartValue + i * nIncrement;
GMatrix* pUnified = GMatrix::mergeHoriz(&indexes, pData);
Holder<GMatrix> hUnified(pUnified);
pUnified->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 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 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 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 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 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 showInstantiateAlgorithmError(const char* szMessage, GArgReader& args)
{
cerr << "_________________________________\n";
cerr << szMessage << "\n\n";
const char* szAlgName = args.peek();
UsageNode* pAlgTree = makeCollaborativeFilterUsageTree();
Holder<UsageNode> hAlgTree(pAlgTree);
if(szAlgName)
{
UsageNode* pUsageAlg = pAlgTree->choice(szAlgName);
if(pUsageAlg)
{
cerr << "Partial Usage Information:\n\n";
pUsageAlg->print(cerr, 0, 3, 76, 1000, true);
}
else
{
cerr << "\"" << szAlgName << "\" is not a recognized algorithm. Try one of these:\n\n";
pAlgTree->print(cerr, 0, 3, 76, 1, false);
}
}
else
{
cerr << "Expected an algorithm. Here are some choices:\n";
pAlgTree->print(cerr, 0, 3, 76, 1, false);
}
cerr << "\nTo see full usage information, run:\n waffles_learn usage\n\n";
cerr << "For a graphical tool that will help you to build a command, run:\n waffles_wizard\n";
cerr.flush();
}
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 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 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 dropRandomValues(GArgReader& args)
{
GMatrix* pData = loadData(args.pop_string());
double portion = args.pop_double();
// Parse the 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 option: ", args.peek());
}
GRand rand(seed);
size_t n = pData->rows() * pData->cols();
size_t k = size_t(portion * n);
for(size_t i = 0; i < pData->cols(); i++)
{
size_t vals = pData->relation()->valueCount(i);
if(vals == 0)
{
for(size_t j = 0; j < pData->rows(); j++)
{
if(rand.next(n) < k)
{
pData->row(j)[i] = UNKNOWN_REAL_VALUE;
k--;
}
n--;
}
}
else
{
for(size_t j = 0; j < pData->rows(); j++)
{
if(rand.next(n) < k)
{
pData->row(j)[i] = UNKNOWN_DISCRETE_VALUE;
k--;
}
n--;
}
}
}
pData->print(cout);
}
void blendEmbeddings(GArgReader& args)
{
// Load the files and params
GMatrix* pDataOrig = loadData(args.pop_string());
Holder<GMatrix> hDataOrig(pDataOrig);
unsigned int seed = getpid() * (unsigned int)time(NULL);
GRand prng(seed);
GNeighborFinder* pNF = instantiateNeighborFinder(pDataOrig, &prng, args);
Holder<GNeighborFinder> hNF(pNF);
GMatrix* pDataA = loadData(args.pop_string());
Holder<GMatrix> hDataA(pDataA);
GMatrix* pDataB = loadData(args.pop_string());
Holder<GMatrix> hDataB(pDataB);
if(pDataA->rows() != pDataOrig->rows() || pDataB->rows() != pDataOrig->rows())
throw Ex("mismatching number of rows");
if(pDataA->cols() != pDataB->cols())
throw Ex("mismatching number of cols");
// Parse Options
while(args.size() > 0)
{
if(args.if_pop("-seed"))
prng.setSeed(args.pop_uint());
else
throw Ex("Invalid option: ", args.peek());
}
// Get a neighbor table
if(!pNF->isCached())
{
GNeighborFinderCacheWrapper* pNF2 = new GNeighborFinderCacheWrapper(hNF.release(), true);
hNF.reset(pNF2);
pNF = pNF2;
}
((GNeighborFinderCacheWrapper*)pNF)->fillCache();
size_t* pNeighborTable = ((GNeighborFinderCacheWrapper*)pNF)->cache();
// Do the blending
size_t startPoint = (size_t)prng.next(pDataA->rows());
double* pRatios = new double[pDataA->rows()];
ArrayHolder<double> hRatios(pRatios);
GVec::setAll(pRatios, 0.5, pDataA->rows());
GMatrix* pDataC = GManifold::blendEmbeddings(pDataA, pRatios, pDataB, pNF->neighborCount(), pNeighborTable, startPoint);
Holder<GMatrix> hDataC(pDataC);
pDataC->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 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 multiDimensionalScaling(GArgReader& args)
{
GRand prng(0);
GMatrix* pDistances = loadData(args.pop_string());
int targetDims = args.pop_uint();
// Parse Options
bool useSquaredDistances = false;
while(args.size() > 0)
{
if(args.if_pop("-squareddistances"))
useSquaredDistances = true;
else
throw Ex("Invalid option: ", args.peek());
}
GMatrix* pResults = GManifold::multiDimensionalScaling(pDistances, targetDims, &prng, useSquaredDistances);
Holder<GMatrix> hResults(pResults);
pResults->print(cout);
}
void Shuffle(GArgReader& args)
{
// Load
GMatrix* pData = loadData(args.pop_string());
Holder<GMatrix> hData(pData);
// Parse options
unsigned int nSeed = getpid() * (unsigned int)time(NULL);
while(args.size() > 0)
{
if(args.if_pop("-seed"))
nSeed = args.pop_uint();
else
ThrowError("Invalid option: ", args.peek());
}
// Shuffle and print
GRand prng(nSeed);
pData->shuffle(prng);
pData->print(cout);
}
void transition(GArgReader& args)
{
// Load the input data
GMatrix* pActions = loadData(args.pop_string());
Holder<GMatrix> hActions(pActions);
GMatrix* pState = loadData(args.pop_string());
Holder<GMatrix> hState(pState);
if(pState->rows() != pActions->rows())
ThrowError("Expected the same number of rows in both datasets");
// Parse options
bool delta = false;
while(args.size() > 0)
{
if(args.if_pop("-delta"))
delta = true;
else
ThrowError("Invalid option: ", args.peek());
}
// Make the output data
size_t actionDims = pActions->cols();
size_t stateDims = pState->cols();
GMixedRelation* pRelation = new GMixedRelation();
sp_relation pRel = pRelation;
pRelation->addAttrs(pActions->relation().get());
pRelation->addAttrs(stateDims + stateDims, 0);
GMatrix* pTransition = new GMatrix(pRel);
pTransition->newRows(pActions->rows() - 1);
for(size_t i = 0; i < pActions->rows() - 1; i++)
{
double* pOut = pTransition->row(i);
GVec::copy(pOut, pActions->row(i), actionDims);
GVec::copy(pOut + actionDims, pState->row(i), stateDims);
GVec::copy(pOut + actionDims + stateDims, pState->row(i + 1), stateDims);
if(delta)
GVec::subtract(pOut + actionDims + stateDims, pState->row(i), stateDims);
}
pTransition->print(cout);
}
void Import(GArgReader& args)
{
// Load the file
size_t len;
const char* filename = args.pop_string();
char* pFile = GFile::loadFile(filename, &len);
ArrayHolder<char> hFile(pFile);
// Parse Options
char separator = ',';
bool tolerant = false;
bool columnNamesInFirstRow = false;
while(args.size() > 0)
{
if(args.if_pop("-tab"))
separator = '\t';
else if(args.if_pop("-space"))
separator = ' ';
else if(args.if_pop("-whitespace"))
separator = '\0';
else if(args.if_pop("-semicolon"))
separator = ';';
else if(args.if_pop("-separator"))
separator = args.pop_string()[0];
else if(args.if_pop("-tolerant"))
tolerant = true;
else if(args.if_pop("-columnnames"))
columnNamesInFirstRow = true;
else
ThrowError("Invalid option: ", args.peek());
}
// Parse the file
GMatrix* pData = GMatrix::parseCsv(pFile, len, separator, columnNamesInFirstRow, tolerant);
Holder<GMatrix> hData(pData);
((GArffRelation*)pData->relation().get())->setName(filename);
// Print the data
pData->print(cout);
}