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 GRecommenderLib::fillMissingValues(GArgReader& args)
{
unsigned int seed = getpid() * (unsigned int)time(NULL);
bool normalize = true;
while(args.next_is_flag())
{
if(args.if_pop("-seed"))
seed = args.pop_uint();
else if(args.if_pop("-nonormalize"))
normalize = false;
else
throw Ex("Invalid option: ", args.peek());
}
// Load the data and the filter
GMatrix dataOrig;
dataOrig.loadArff(args.pop_string());
// Parse params
vector<size_t> ignore;
while(args.next_is_flag())
{
if(args.if_pop("-ignore"))
parseAttributeList(ignore, args, dataOrig.cols());
else
throw Ex("Invalid option: ", args.peek());
}
// Throw out the ignored attributes
std::sort(ignore.begin(), ignore.end());
for(size_t i = ignore.size() - 1; i < ignore.size(); i--)
dataOrig.deleteColumns(ignore[i], 1);
GRelation* pOrigRel = dataOrig.relation().clone();
std::unique_ptr<GRelation> hOrigRel(pOrigRel);
GCollaborativeFilter* pModel = InstantiateAlgorithm(args);
std::unique_ptr<GCollaborativeFilter> hModel(pModel);
if(args.size() > 0)
throw Ex("Superfluous argument: ", args.peek());
pModel->rand().setSeed(seed);
// Convert to all normalized real values
GNominalToCat* pNtc = new GNominalToCat();
GIncrementalTransform* pFilter = pNtc;
std::unique_ptr<GIncrementalTransformChainer> hChainer;
if(normalize)
{
GIncrementalTransformChainer* pChainer = new GIncrementalTransformChainer(new GNormalize(), pNtc);
hChainer.reset(pChainer);
pFilter = pChainer;
}
pNtc->preserveUnknowns();
pFilter->train(dataOrig);
GMatrix* pData = pFilter->transformBatch(dataOrig);
std::unique_ptr<GMatrix> hData(pData);
// Convert to 3-column form
GMatrix* pMatrix = new GMatrix(0, 3);
std::unique_ptr<GMatrix> hMatrix(pMatrix);
size_t dims = pData->cols();
for(size_t i = 0; i < pData->rows(); i++)
{
GVec& row = pData->row(i);
for(size_t j = 0; j < dims; j++)
{
if(row[j] != UNKNOWN_REAL_VALUE)
{
GVec& vec = pMatrix->newRow();
vec[0] = (double)i;
vec[1] = (double)j;
vec[2] = row[j];
}
}
}
// Train the collaborative filter
pModel->train(*pMatrix);
hMatrix.release();
pMatrix = NULL;
// Predict values for missing elements
for(size_t i = 0; i < pData->rows(); i++)
{
GVec& row = pData->row(i);
for(size_t j = 0; j < dims; j++)
{
if(row[j] == UNKNOWN_REAL_VALUE)
row[j] = pModel->predict(i, j);
GAssert(row[j] != UNKNOWN_REAL_VALUE);
}
}
// Convert the data back to its original form
GMatrix* pOut = pFilter->untransformBatch(*pData);
pOut->setRelation(hOrigRel.release());
pOut->print(cout);
}
///Return a pointer to newly allocated data read from the command line
///represented by args.
///
///The returned matrix is allocated by new and it is the caller's
///responsibility to deallocate it. The suggested manner is to use a
///Holder<GMatrix*>
///
///In the returned matrix, all of the attributes designated as labels
///have been moved to the end and ignored attributes have been
///removed. The original indices of all the attributes are returned in
///originalIndices.
///
///\param args the command-line arguments
///
///\param pLabelDims (out parameter) the index of the first attribute
///which is designated a label.
///
///\param originalIndices the vector in which to place the original
///indices. originalIndices[i] is the index in the original data file
///of the attribute currently at index i.
void loadDataWithSwitches(GMatrix& data, GArgReader& args, size_t& pLabelDims,
std::vector<size_t>& originalIndices)
{
// Load the dataset by extension
const char* szFilename = args.pop_string();
PathData pd;
GFile::parsePath(szFilename, &pd);
if(_stricmp(szFilename + pd.extStart, ".arff") == 0)
data.loadArff(szFilename);
else if(_stricmp(szFilename + pd.extStart, ".csv") == 0)
{
GCSVParser parser;
parser.parse(data, szFilename);
cerr << "\nParsing Report:\n";
for(size_t i = 0; i < data.cols(); i++)
cerr << to_str(i) << ") " << parser.report(i) << "\n";
}
else if(_stricmp(szFilename + pd.extStart, ".dat") == 0)
{
GCSVParser parser;
parser.setSeparator('\0');
parser.parse(data, szFilename);
cerr << "\nParsing Report:\n";
for(size_t i = 0; i < data.cols(); i++)
cerr << to_str(i) << ") " << parser.report(i) << "\n";
}
else
throw Ex("Unsupported file format: ", szFilename + pd.extStart);
//Make the initial list of original indices
originalIndices.resize(data.cols());
for(std::size_t i = 0; i < originalIndices.size(); ++i){
originalIndices.at(i) = i;
}
// Parse params
vector<size_t> ignore;
vector<size_t> labels;
while(args.next_is_flag())
{
if(args.if_pop("-labels"))
parseAttributeList(labels, args, data.cols());
else if(args.if_pop("-ignore"))
parseAttributeList(ignore, args, data.cols());
else
break;
}
// Throw out the ignored attributes
std::sort(ignore.begin(), ignore.end());
for(size_t i = ignore.size() - 1; i < ignore.size(); i--)
{
data.deleteColumns(ignore[i], 1);
originalIndices.erase(originalIndices.begin()+ignore[i]);
for(size_t j = 0; j < labels.size(); j++)
{
if(labels[j] >= ignore[i])
{
if(labels[j] == ignore[i])
throw Ex("Attribute ", to_str(labels[j]), " is both ignored and used as a label");
labels[j]--;
}
}
}
// Swap label columns to the end
pLabelDims = std::max((size_t)1, labels.size());
for(size_t i = 0; i < labels.size(); i++)
{
size_t src = labels[i];
size_t dst = data.cols() - pLabelDims + i;
if(src != dst)
{
data.swapColumns(src, dst);
std::swap(originalIndices.at(src),
originalIndices.at(dst));
for(size_t j = i + 1; j < labels.size(); j++)
{
if(labels[j] == dst)
{
labels[j] = src;
break;
}
}
}
}
}
