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);
}
GSparseMatrix* loadSparseData(const char* szFilename)
{
// Load the dataset by extension
PathData pd;
GFile::parsePath(szFilename, &pd);
if(_stricmp(szFilename + pd.extStart, ".arff") == 0)
{
// Convert a 3-column dense ARFF file to a sparse matrix
GMatrix* pData = GMatrix::loadArff(szFilename);
if(pData->cols() != 3)
ThrowError("Expected 3 columns: 0) user or row-index, 1) item or col-index, 2) value or rating");
double m0, r0, m1, r1;
pData->minAndRange(0, &m0, &r0);
pData->minAndRange(1, &m1, &r1);
if(m0 < 0 || m0 > 1e10 || r0 < 2 || r0 > 1e10)
ThrowError("Invalid row indexes");
if(m1 < 0 || m1 > 1e10 || r1 < 2 || r1 > 1e10)
ThrowError("Invalid col indexes");
GSparseMatrix* pMatrix = new GSparseMatrix(size_t(m0 + r0) + 1, size_t(m1 + r1) + 1, UNKNOWN_REAL_VALUE);
Holder<GSparseMatrix> hMatrix(pMatrix);
for(size_t i = 0; i < pData->rows(); i++)
{
double* pRow = pData->row(i);
pMatrix->set(size_t(pRow[0]), size_t(pRow[1]), pRow[2]);
}
return hMatrix.release();
}
else if(_stricmp(szFilename + pd.extStart, ".sparse") == 0)
{
GDom doc;
doc.loadJson(szFilename);
return new GSparseMatrix(doc.root());
}
ThrowError("Unsupported file format: ", szFilename + pd.extStart);
return NULL;
}
