void MDDAGClassifier::run(const string& dataFileName, const string& shypFileName,
int numIterations, const string& outResFileName, int numRanksEnclosed)
{
InputData* pData = loadInputData(dataFileName, shypFileName);
if (_verbose > 0)
cout << "Loading strong hypothesis..." << flush;
// The class that loads the weak hypotheses
UnSerialization us;
// Where to put the weak hypotheses
vector<BaseLearner*> weakHypotheses;
// loads them
us.loadHypotheses(shypFileName, weakHypotheses, pData);
// where the results go
vector< ExampleResults* > results;
if (_verbose > 0)
cout << "Classifying..." << flush;
// get the results
computeResults( pData, weakHypotheses, results, numIterations );
const int numClasses = pData->getNumClasses();
if (_verbose > 0)
{
// well.. if verbose = 0 no results are displayed! :)
cout << "Done!" << endl;
vector< vector<float> > rankedError(numRanksEnclosed);
// Get the per-class error for the numRanksEnclosed-th ranks
for (int i = 0; i < numRanksEnclosed; ++i)
getClassError( pData, results, rankedError[i], i );
// output it
cout << endl;
cout << "Error Summary" << endl;
cout << "=============" << endl;
for ( int l = 0; l < numClasses; ++l )
{
// first rank (winner): rankedError[0]
cout << "Class '" << pData->getClassMap().getNameFromIdx(l) << "': "
<< setprecision(4) << rankedError[0][l] * 100 << "%";
// output the others on its side
if (numRanksEnclosed > 1 && _verbose > 1)
{
cout << " (";
for (int i = 1; i < numRanksEnclosed; ++i)
cout << " " << i+1 << ":[" << setprecision(4) << rankedError[i][l] * 100 << "%]";
cout << " )";
}
cout << endl;
}
// the overall error
cout << "\n--> Overall Error: "
<< setprecision(4) << getOverallError(pData, results, 0) * 100 << "%";
// output the others on its side
if (numRanksEnclosed > 1 && _verbose > 1)
{
cout << " (";
for (int i = 1; i < numRanksEnclosed; ++i)
cout << " " << i+1 << ":[" << setprecision(4) << getOverallError(pData, results, i) * 100 << "%]";
cout << " )";
}
cout << endl;
} // verbose
// If asked output the results
if ( !outResFileName.empty() )
{
const int numExamples = pData->getNumExamples();
ofstream outRes(outResFileName.c_str());
outRes << "Instance" << '\t' << "Forecast" << '\t' << "Labels" << '\n';
string exampleName;
for (int i = 0; i < numExamples; ++i)
{
// output the name if it exists, otherwise the number
// of the example
exampleName = pData->getExampleName(i);
if ( exampleName.empty() )
outRes << i << '\t';
else
outRes << exampleName << '\t';
// output the predicted class
outRes << pData->getClassMap().getNameFromIdx( results[i]->getWinner().first ) << '\t';
outRes << '|';
vector<Label>& labels = pData->getLabels(i);
for (vector<Label>::iterator lIt=labels.begin(); lIt != labels.end(); ++lIt) {
if (lIt->y>0)
{
outRes << ' ' << pData->getClassMap().getNameFromIdx(lIt->idx);
}
}
outRes << endl;
}
if (_verbose > 0)
cout << "\nPredictions written on file <" << outResFileName << ">!" << endl;
}
// delete the input data file
if (pData)
delete pData;
vector<ExampleResults*>::iterator it;
for (it = results.begin(); it != results.end(); ++it)
delete (*it);
}
void AdaBoostMHClassifier::saveROC(const string& dataFileName, const string& shypFileName,
const string& outFileName, int numIterations)
{
InputData* pData = loadInputData(dataFileName, shypFileName);
ofstream outFile(outFileName.c_str());
if ( ! outFile.is_open() )
{
cout << "Cannot open outfile" << endl;
exit( -1 );
}
if (_verbose > 0)
cout << "Loading strong hypothesis..." << flush;
// The class that loads the weak hypotheses
UnSerialization us;
// Where to put the weak hypotheses
vector<BaseLearner*> weakHypotheses;
// loads them
us.loadHypotheses(shypFileName, weakHypotheses, pData);
weakHypotheses.resize( numIterations );
// where the results go
vector< ExampleResults* > results;
if (_verbose > 0)
cout << "Classifying..." << flush;
// get the results
computeResults( pData, weakHypotheses, results, weakHypotheses.size());
const int numClasses = pData->getNumClasses();
const int numExamples = pData->getNumExamples();
if (_verbose > 0)
cout << "Done!" << endl;
vector< pair< int, double> > sortedExample( numExamples );
for( int i=0; i<numExamples; i++ )
{
sortedExample[i].first = i;
sortedExample[i].second = results[i]->getVotesVector()[0];
}
sort( sortedExample.begin(), sortedExample.end(), nor_utils::comparePair< 2, int, double, greater<double> >() );
vector<double> positiveWeights( numExamples );
double sumOfPositiveWeights = 0.0;
vector<double> negativeWeights( numExamples );
double sumOfNegativeWeights = 0.0;
fill( positiveWeights.begin(), positiveWeights.end(), 0.0 );
fill( negativeWeights.begin(), negativeWeights.end(), 0.0 );
string className = pData->getClassMap().getNameFromIdx( 0 );
vector<Label>& labels = pData->getLabels( sortedExample[0].first );
vector<Label>::iterator labIt = find( labels.begin(), labels.end(), 0);
if ( labIt != labels.end() )
{
if ( labIt->y > 0.0 )
{
positiveWeights[0] = labIt->initialWeight;
sumOfPositiveWeights += labIt->initialWeight;
} else
{
negativeWeights[0] = labIt->initialWeight;
sumOfNegativeWeights += labIt->initialWeight;
}
}
for( int i=1; i<numExamples; i++ )
{
labels = pData->getLabels( sortedExample[i].first );
labIt = find( labels.begin(), labels.end(), 0);
if ( labIt != labels.end() )
{
if ( labIt->y > 0.0 )
{
negativeWeights[i] = negativeWeights[i-1];
positiveWeights[i] = positiveWeights[i-1] + labIt->initialWeight;
sumOfPositiveWeights += labIt->initialWeight;
} else
{
positiveWeights[i] = positiveWeights[i-1];
negativeWeights[i] = negativeWeights[i-1] + labIt->initialWeight;
sumOfNegativeWeights += labIt->initialWeight;
}
} else {
positiveWeights[i] = positiveWeights[i-1];
negativeWeights[i] = negativeWeights[i-1];
}
}
outFile << "Class name: " << className << endl;
for( int i=0; i<numExamples; i++ )
{
outFile << sortedExample[i].first << " ";
// false positive rate
outFile << ( positiveWeights[i] / sumOfPositiveWeights ) << " ";
//true negative rate
outFile << ( negativeWeights[i] / sumOfNegativeWeights ) << endl;
}
outFile.close();
// delete the input data file
if (pData)
delete pData;
vector<ExampleResults*>::iterator it;
for (it = results.begin(); it != results.end(); ++it)
delete (*it);
}
void VJCascadeClassifier::savePosteriors(const string& dataFileName, const string& shypFileName,
const string& outFileName, int numIterations)
{
// loading data
InputData* pData = loadInputData(dataFileName, shypFileName);
const int numOfExamples = pData->getNumExamples();
//get the index of positive label
const NameMap& namemap = pData->getClassMap();
_positiveLabelIndex = namemap.getIdxFromName( _positiveLabelName );
if (_verbose > 0)
cout << "Loading strong hypothesis..." << flush;
// open outfile
ofstream outRes(outFileName.c_str());
if (!outRes.is_open())
{
cout << "Cannot open outfile!!! " << outFileName << endl;
}
// The class that loads the weak hypotheses
UnSerialization us;
// Where to put the weak hypotheses
vector<vector<BaseLearner*> > weakHypotheses;
// For stagewise thresholds
vector<AlphaReal> thresholds(0);
// loads them
//us.loadHypotheses(shypFileName, weakHypotheses, pData);
us.loadCascadeHypotheses(shypFileName, weakHypotheses, thresholds, pData);
// output the number of stages
outRes << "StageNum " << weakHypotheses.size() << endl;
// output original labels
outRes << "Labels";
for(int i=0; i<numOfExamples; ++i )
{
vector<Label>& labels = pData->getLabels(i);
if (labels[_positiveLabelIndex].y>0) // pos label
outRes << " 1";
else
outRes << " 0";
}
outRes << endl;
// store result
vector<CascadeOutputInformation> cascadeData(0);
vector<CascadeOutputInformation>::iterator it;
cascadeData.resize(numOfExamples);
for( it=cascadeData.begin(); it != cascadeData.end(); ++it )
{
it->active=true;
}
for(int stagei=0; stagei < weakHypotheses.size(); ++stagei )
{
// for posteriors
vector<AlphaReal> posteriors(0);
// calculate the posteriors after stage
VJCascadeLearner::calculatePosteriors( pData, weakHypotheses[stagei], posteriors, _positiveLabelIndex );
// update the data (posteriors, active element index etc.)
//VJCascadeLearner::forecastOverAllCascade( pData, posteriors, activeInstances, thresholds[stagei] );
updateCascadeData(pData, weakHypotheses, stagei, posteriors, thresholds, _positiveLabelIndex, cascadeData);
int numberOfActiveInstance = 0;
for( int i = 0; i < numOfExamples; ++i )
if (cascadeData[i].active) numberOfActiveInstance++;
if (_verbose > 0 )
cout << "Number of active instances: " << numberOfActiveInstance << "(" << numOfExamples << ")" << endl;
// output stats
outRes << "Stage " << stagei << " " << weakHypotheses[stagei].size() << endl;
outRes << "Forecast";
for(int i=0; i<numOfExamples; ++i )
{
outRes << " " << cascadeData[i].forecast;
}
outRes << endl;
outRes << "Active";
for(int i=0; i<numOfExamples; ++i )
{
if( cascadeData[i].active)
outRes << " 1";
else
outRes << " 0";
}
outRes << endl;
outRes << "Posteriors";
for(int i=0; i<numOfExamples; ++i )
{
outRes << " " << cascadeData[i].score;
}
outRes << endl;
}
outRes.close();
// free memory allocation
vector<vector<BaseLearner*> >::iterator bvIt;
for( bvIt = weakHypotheses.begin(); bvIt != weakHypotheses.end(); ++bvIt )
{
vector<BaseLearner* >::iterator bIt;
for( bIt = (*bvIt).begin(); bIt != (*bvIt).end(); ++bIt )
delete *bIt;
}
}
void VJCascadeClassifier::run(const string& dataFileName, const string& shypFileName,
int numIterations, const string& outResFileName )
{
// loading data
InputData* pData = loadInputData(dataFileName, shypFileName);
const int numOfExamples = pData->getNumExamples();
//get the index of positive label
const NameMap& namemap = pData->getClassMap();
_positiveLabelIndex = namemap.getIdxFromName( _positiveLabelName );
if (_verbose > 0)
cout << "Loading strong hypothesis..." << flush;
// The class that loads the weak hypotheses
UnSerialization us;
// Where to put the weak hypotheses
vector<vector<BaseLearner*> > weakHypotheses;
// For stagewise thresholds
vector<AlphaReal> thresholds(0);
// loads them
//us.loadHypotheses(shypFileName, weakHypotheses, pData);
us.loadCascadeHypotheses(shypFileName, weakHypotheses, thresholds, pData);
// store result
vector<CascadeOutputInformation> cascadeData(0);
vector<CascadeOutputInformation>::iterator it;
cascadeData.resize(numOfExamples);
for( it=cascadeData.begin(); it != cascadeData.end(); ++it )
{
it->active=true;
}
if (!_outputInfoFile.empty())
{
outputHeader();
}
for(int stagei=0; stagei < weakHypotheses.size(); ++stagei )
{
// for posteriors
vector<AlphaReal> posteriors(0);
// calculate the posteriors after stage
VJCascadeLearner::calculatePosteriors( pData, weakHypotheses[stagei], posteriors, _positiveLabelIndex );
// update the data (posteriors, active element index etc.)
updateCascadeData(pData, weakHypotheses, stagei, posteriors, thresholds, _positiveLabelIndex, cascadeData);
if (!_outputInfoFile.empty())
{
_output << stagei + 1 << "\t";
_output << weakHypotheses[stagei].size() << "\t";
outputCascadeResult( pData, cascadeData );
}
int numberOfActiveInstance = 0;
for( int i = 0; i < numOfExamples; ++i )
if (cascadeData[i].active) numberOfActiveInstance++;
if (_verbose > 0 )
cout << "Number of active instances: " << numberOfActiveInstance << "(" << numOfExamples << ")" << endl;
}
vector<vector<int> > confMatrix(2);
confMatrix[0].resize(2);
fill( confMatrix[0].begin(), confMatrix[0].end(), 0 );
confMatrix[1].resize(2);
fill( confMatrix[1].begin(), confMatrix[1].end(), 0 );
// print accuracy
for(int i=0; i<numOfExamples; ++i )
{
vector<Label>& labels = pData->getLabels(i);
if (labels[_positiveLabelIndex].y>0) // pos label
if (cascadeData[i].forecast==1)
confMatrix[1][1]++;
else
confMatrix[1][0]++;
else // negative label
if (cascadeData[i].forecast==0)
confMatrix[0][0]++;
else
confMatrix[0][1]++;
}
double acc = 100.0 * (confMatrix[0][0] + confMatrix[1][1]) / ((double) numOfExamples);
// output it
cout << endl;
cout << "Error Summary" << endl;
cout << "=============" << endl;
cout << "Accuracy: " << setprecision(4) << acc << endl;
cout << setw(10) << "\t" << setw(10) << namemap.getNameFromIdx(1-_positiveLabelIndex) << setw(10) << namemap.getNameFromIdx(_positiveLabelIndex) << endl;
cout << setw(10) << namemap.getNameFromIdx(1-_positiveLabelIndex) << setw(10) << confMatrix[0][0] << setw(10) << confMatrix[0][1] << endl;
cout << setw(10) << namemap.getNameFromIdx(_positiveLabelIndex) << setw(10) << confMatrix[1][0] << setw(10) << confMatrix[1][1] << endl;
// output forecast
if (!outResFileName.empty() ) outputForecast(pData, outResFileName, cascadeData );
// free memory allocation
vector<vector<BaseLearner*> >::iterator bvIt;
for( bvIt = weakHypotheses.begin(); bvIt != weakHypotheses.end(); ++bvIt )
{
vector<BaseLearner* >::iterator bIt;
for( bIt = (*bvIt).begin(); bIt != (*bvIt).end(); ++bIt )
delete *bIt;
}
}
/**
* The main function. Everything starts here!
* \param argc The number of arguments.
* \param argv The arguments.
* \date 11/11/2005
*/
int main(int argc, const char* argv[])
{
// initializing the random number generator
srand ( time(NULL) );
// no need to synchronize with C style stream
std::ios_base::sync_with_stdio(false);
#if STABLE_SORT
cerr << "WARNING: Stable sort active! It might be slower!!" << endl;
#endif
//////////////////////////////////////////////////////////////////////////
// Standard arguments
nor_utils::Args args;
args.setArgumentDiscriminator("--");
args.declareArgument("help");
args.declareArgument("static");
args.declareArgument("h", "Help", 1, "<optiongroup>");
//////////////////////////////////////////////////////////////////////////
// Basic Arguments
args.setGroup("Parameters");
args.declareArgument("train", "Performs training.", 2, "<dataFile> <nInterations>");
args.declareArgument("traintest", "Performs training and test at the same time.", 3, "<trainingDataFile> <testDataFile> <nInterations>");
args.declareArgument("trainvalidtest", "Performs training and test at the same time.", 4, "<trainingDataFile> <validDataFile> <testDataFile> <nInterations>");
args.declareArgument("test", "Test the model.", 3, "<dataFile> <numIters> <shypFile>");
args.declareArgument("test", "Test the model and output the results", 4, "<datafile> <shypFile> <numIters> <outFile>");
args.declareArgument("cmatrix", "Print the confusion matrix for the given model.", 2, "<dataFile> <shypFile>");
args.declareArgument("cmatrixfile", "Print the confusion matrix with the class names to a file.", 3, "<dataFile> <shypFile> <outFile>");
args.declareArgument("posteriors", "Output the posteriors for each class, that is the vector-valued discriminant function for the given dataset and model.", 4, "<dataFile> <shypFile> <outFile> <numIters>");
args.declareArgument("posteriors", "Output the posteriors for each class, that is the vector-valued discriminant function for the given dataset and model periodically.", 5, "<dataFile> <shypFile> <outFile> <numIters> <period>");
args.declareArgument("encode", "Save the coefficient vector of boosting individually on each point using ParasiteLearner", 6, "<inputDataFile> <autoassociativeDataFile> <outputDataFile> <nIterations> <poolFile> <nBaseLearners>");
args.declareArgument("ssfeatures", "Print matrix data for SingleStump-Based weak learners (if numIters=0 it means all of them).", 4, "<dataFile> <shypFile> <outFile> <numIters>");
args.declareArgument( "fileformat", "Defines the type of intput file. Available types are:\n"
"* simple: each line has attributes separated by whitespace and class at the end (DEFAULT!)\n"
"* arff: arff filetype. The header file can be specified using --headerfile option\n"
"* arffbzip: bziped arff filetype. The header file can be specified using --headerfile option\n"
"* svmlight: \n"
"(Example: --fileformat simple)",
1, "<fileFormat>" );
args.declareArgument("headerfile", "The header file for arff and SVMLight and arff formats.", 1, "header.txt");
args.declareArgument("constant", "Check constant learner in each iteration.", 0, "");
args.declareArgument("timelimit", "Time limit in minutes", 1, "<minutes>" );
args.declareArgument("stronglearner", "Available strong learners:\n"
"AdaBoost (default)\n"
"FilterBoost\n"
"SoftCascade\n"
"VJcascade\n", 1, "<stronglearner>" );
args.declareArgument("slowresumeprocess", "Computes every statitstic in each iteration (slow resume)\n"
"Computes only the statistics in the last iteration (fast resume, default)\n", 0, "" );
args.declareArgument("weights", "Outputs the weights of instances at the end of the learning process", 1, "<filename>" );
args.declareArgument("Cn", "Resampling size for FilterBoost (default=300)", 1, "<value>" );
args.declareArgument("onlinetraining", "The weak learner will be trained online\n", 0, "" );
//// ignored for the moment!
//args.declareArgument("arffheader", "Specify the arff header.", 1, "<arffHeaderFile>");
// for MDDAG
//args.setGroup("MDDAG");
args.declareArgument("traintestmddag", "Performs training and test at the same time using mddag.", 5, "<trainingDataFile> <testDataFile> <modelFile> <nIterations> <baseIter>");
args.declareArgument("policytrainingiter", "The iteration number the policy learner takes.", 1, "<iternum>");
args.declareArgument("rollouts", "The number of rollouts.", 1, "<num>");
args.declareArgument("rollouttype", "Rollout type (montecarlo or szatymaz)", 1, "<rollouttype>");
args.declareArgument("beta", "Trade-off parameter", 1, "<beta>");
args.declareArgument("outdir", "Output directory.", 1, "<outdir>");
args.declareArgument("policyalpha", "Alpha for policy array.", 1, "<alpha>");
args.declareArgument("succrewardtype", "Rewrd type (e01 or hammng)", 1, "<rward_type");
args.declareArgument("outtrainingerror", "Output training error", 0, "");
args.declareArgument("epsilon", "Exploration term", 1, "<epsilon>");
args.declareArgument("updateperc", "Number of component in the policy are updated", 1, "<perc>");
// for VJ cascade
VJCascadeLearner::declareBaseArguments(args);
// for SoftCascade
SoftCascadeLearner::declareBaseArguments(args);
//////////////////////////////////////////////////////////////////////////
// Options
args.setGroup("I/O Options");
/////////////////////////////////////////////
// these are valid only for .txt input!
// they might be removed!
args.declareArgument("d", "The separation characters between the fields (default: whitespaces).\nExample: -d \"\\t,.-\"\nNote: new-line is always included!", 1, "<separators>");
args.declareArgument("classend", "The class is the last column instead of the first (or second if -examplelabel is active).");
args.declareArgument("examplename", "The data file has an additional column (the very first) which contains the 'name' of the example.");
/////////////////////////////////////////////
args.setGroup("Basic Algorithm Options");
args.declareArgument("weightpolicy", "Specify the type of weight initialization. The user specified weights (if available) are used inside the policy which can be:\n"
"* sharepoints Share the weight equally among data points and between positiv and negative labels (DEFAULT)\n"
"* sharelabels Share the weight equally among data points\n"
"* proportional Share the weights freely", 1, "<weightType>");
args.setGroup("General Options");
args.declareArgument("verbose", "Set the verbose level 0, 1 or 2 (0=no messages, 1=default, 2=all messages).", 1, "<val>");
args.declareArgument("outputinfo", "Output informations on the algorithm performances during training, on file <filename>.", 1, "<filename>");
args.declareArgument("outputinfo", "Output specific informations on the algorithm performances during training, on file <filename> <outputlist>. <outputlist> must be a concatenated list of three characters abreviation (ex: err for error, fpr for false positive rate)", 2, "<filename> <outputlist>");
args.declareArgument("seed", "Defines the seed for the random operations.", 1, "<seedval>");
//////////////////////////////////////////////////////////////////////////
// Shows the list of available learners
string learnersComment = "Available learners are:";
vector<string> learnersList;
BaseLearner::RegisteredLearners().getList(learnersList);
vector<string>::const_iterator it;
for (it = learnersList.begin(); it != learnersList.end(); ++it)
{
learnersComment += "\n ** " + *it;
// defaultLearner is defined in Defaults.h
if ( *it == defaultLearner )
learnersComment += " (DEFAULT)";
}
args.declareArgument("learnertype", "Change the type of weak learner. " + learnersComment, 1, "<learner>");
//////////////////////////////////////////////////////////////////////////
//// Declare arguments that belongs to all weak learners
BaseLearner::declareBaseArguments(args);
////////////////////////////////////////////////////////////////////////////
//// Weak learners (and input data) arguments
for (it = learnersList.begin(); it != learnersList.end(); ++it)
{
args.setGroup(*it + " Options");
// add weaklearner-specific options
BaseLearner::RegisteredLearners().getLearner(*it)->declareArguments(args);
}
//////////////////////////////////////////////////////////////////////////
//// Declare arguments that belongs to all bandit learner
GenericBanditAlgorithm::declareBaseArguments(args);
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
switch ( args.readArguments(argc, argv) )
{
case nor_utils::AOT_NO_ARGUMENTS:
showBase();
break;
case nor_utils::AOT_UNKOWN_ARGUMENT:
exit(1);
break;
case nor_utils::AOT_INCORRECT_VALUES_NUMBER:
exit(1);
break;
case nor_utils::AOT_OK:
break;
}
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
if ( args.hasArgument("help") )
showHelp(args, learnersList);
if ( args.hasArgument("static") )
showStaticConfig();
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
if ( args.hasArgument("h") )
showOptionalHelp(args);
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
int verbose = 1;
if ( args.hasArgument("verbose") )
args.getValue("verbose", 0, verbose);
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
// defines the seed
if (args.hasArgument("seed"))
{
unsigned int seed = args.getValue<unsigned int>("seed", 0);
srand(seed);
}
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
GenericStrongLearner* pModel = NULL;
if ( args.hasArgument("train") ||
args.hasArgument("traintest") ||
args.hasArgument("trainvalidtest") ) // for Viola-Jones Cascade
{
// get the name of the learner
string baseLearnerName = defaultLearner;
if ( args.hasArgument("learnertype") )
args.getValue("learnertype", 0, baseLearnerName);
checkBaseLearner(baseLearnerName);
if (verbose > 1)
cout << "--> Using learner: " << baseLearnerName << endl;
// This hould be changed: the user decides the strong learner
BaseLearner* pWeakHypothesisSource = BaseLearner::RegisteredLearners().getLearner(baseLearnerName);
pModel = pWeakHypothesisSource->createGenericStrongLearner( args );
pModel->run(args);
}
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
else if ( args.hasArgument("traintestmddag") )
{
// -test <dataFile> <shypFile> <numIters>
string shypFileName = args.getValue<string>("traintestmddag", 2);
string baseLearnerName = UnSerialization::getWeakLearnerName(shypFileName);
BaseLearner* pWeakHypothesisSource = BaseLearner::RegisteredLearners().getLearner(baseLearnerName);
pModel = pWeakHypothesisSource->createGenericStrongLearner( args );
pModel->run(args);
}
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
else if ( args.hasArgument("test") )
{
// -test <dataFile> <shypFile> <numIters>
string shypFileName = args.getValue<string>("test", 1);
string baseLearnerName = UnSerialization::getWeakLearnerName(shypFileName);
BaseLearner* pWeakHypothesisSource = BaseLearner::RegisteredLearners().getLearner(baseLearnerName);
pModel = pWeakHypothesisSource->createGenericStrongLearner( args );
pModel->classify(args);
}
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
else if ( args.hasArgument("cmatrix") )
{
// -cmatrix <dataFile> <shypFile>
string shypFileName = args.getValue<string>("cmatrix", 1);
string baseLearnerName = UnSerialization::getWeakLearnerName(shypFileName);
BaseLearner* pWeakHypothesisSource = BaseLearner::RegisteredLearners().getLearner(baseLearnerName);
pModel = pWeakHypothesisSource->createGenericStrongLearner( args );
pModel->doConfusionMatrix(args);
}
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
else if ( args.hasArgument("posteriors") )
{
// -posteriors <dataFile> <shypFile> <outFileName>
string shypFileName = args.getValue<string>("posteriors", 1);
string baseLearnerName = UnSerialization::getWeakLearnerName(shypFileName);
BaseLearner* pWeakHypothesisSource = BaseLearner::RegisteredLearners().getLearner(baseLearnerName);
pModel = pWeakHypothesisSource->createGenericStrongLearner( args );
pModel->doPosteriors(args);
}
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
else if ( args.hasArgument("ssfeatures") )
{
// ONLY for AdaBoostMH classifiers
// -ssfeatures <dataFile> <shypFile> <outFile> <numIters>
string testFileName = args.getValue<string>("ssfeatures", 0);
string shypFileName = args.getValue<string>("ssfeatures", 1);
string outFileName = args.getValue<string>("ssfeatures", 2);
int numIterations = args.getValue<int>("ssfeatures", 3);
cerr << "ERROR: ssfeatures has been deactivated for the moment!" << endl;
//classifier.saveSingleStumpFeatureData(testFileName, shypFileName, outFileName, numIterations);
}
//////////////////////////////////////////////////////////////////////////////////////////
//////////////////////////////////////////////////////////////////////////////////////////
else if ( args.hasArgument("encode") )
{
// --encode <inputDataFile> <outputDataFile> <nIterations> <poolFile> <nBaseLearners>
string labelsFileName = args.getValue<string>("encode", 0);
string autoassociativeFileName = args.getValue<string>("encode", 1);
string outputFileName = args.getValue<string>("encode", 2);
int numIterations = args.getValue<int>("encode", 3);
string poolFileName = args.getValue<string>("encode", 4);
int numBaseLearners = args.getValue<int>("encode", 5);
string outputInfoFile;
const char* tmpArgv1[] = {"bla", // for ParasiteLearner
"--pool",
args.getValue<string>("encode", 4).c_str(),
args.getValue<string>("encode", 5).c_str()};
args.readArguments(4,tmpArgv1);
InputData* pAutoassociativeData = new InputData();
pAutoassociativeData->initOptions(args);
pAutoassociativeData->load(autoassociativeFileName,IT_TRAIN,verbose);
// for the original labels
InputData* pLabelsData = new InputData();
pLabelsData->initOptions(args);
pLabelsData->load(labelsFileName,IT_TRAIN,verbose);
// set up all the InputData members identically to pAutoassociativeData
EncodeData* pOnePoint = new EncodeData();
pOnePoint->initOptions(args);
pOnePoint->load(autoassociativeFileName,IT_TRAIN,verbose);
const int numExamples = pAutoassociativeData->getNumExamples();
BaseLearner* pWeakHypothesisSource =
BaseLearner::RegisteredLearners().getLearner("ParasiteLearner");
pWeakHypothesisSource->declareArguments(args);
ParasiteLearner* pWeakHypothesis;
ofstream outFile(outputFileName.c_str());
if (!outFile.is_open())
{
cerr << "ERROR: Cannot open strong hypothesis file <" << outputFileName << ">!" << endl;
exit(1);
}
for (int i = 0; i < numExamples ; ++i)
{
vector<float> alphas;
alphas.resize(numBaseLearners);
fill(alphas.begin(), alphas.end(), 0);
if (verbose >= 1)
cout << "--> Encoding example no " << (i+1) << endl;
pOnePoint->resetData();
pOnePoint->addExample( pAutoassociativeData->getExample(i) );
AlphaReal energy = 1;
OutputInfo* pOutInfo = NULL;
if ( args.hasArgument("outputinfo") )
{
args.getValue("outputinfo", 0, outputInfoFile);
pOutInfo = new OutputInfo(args);
pOutInfo->initialize(pOnePoint);
}
for (int t = 0; t < numIterations; ++t)
{
pWeakHypothesis = (ParasiteLearner*)pWeakHypothesisSource->create();
pWeakHypothesis->initLearningOptions(args);
pWeakHypothesis->setTrainingData(pOnePoint);
energy *= pWeakHypothesis->run();
// if (verbose >= 2)
// cout << "energy = " << energy << endl << flush;
AdaBoostMHLearner adaBoostMHLearner;
if (i == 0 && t == 0)
{
if ( pWeakHypothesis->getBaseLearners().size() < numBaseLearners )
numBaseLearners = pWeakHypothesis->getBaseLearners().size();
outFile << "%Hidden representation using autoassociative boosting" << endl << endl;
outFile << "@RELATION " << outputFileName << endl << endl;
outFile << "% numBaseLearners" << endl;
for (int j = 0; j < numBaseLearners; ++j)
outFile << "@ATTRIBUTE " << j << "_" <<
pWeakHypothesis->getBaseLearners()[j]->getId() << " NUMERIC" << endl;
outFile << "@ATTRIBUTE class {" << pLabelsData->getClassMap().getNameFromIdx(0);
for (int l = 1; l < pLabelsData->getClassMap().getNumNames(); ++l)
outFile << ", " << pLabelsData->getClassMap().getNameFromIdx(l);
outFile << "}" << endl<< endl<< "@DATA" << endl;
}
alphas[pWeakHypothesis->getSelectedIndex()] +=
pWeakHypothesis->getAlpha() * pWeakHypothesis->getSignOfAlpha();
if ( pOutInfo )
adaBoostMHLearner.printOutputInfo(pOutInfo, t, pOnePoint, NULL, pWeakHypothesis);
adaBoostMHLearner.updateWeights(pOnePoint,pWeakHypothesis);
}
float sumAlphas = 0;
for (int j = 0; j < numBaseLearners; ++j)
sumAlphas += alphas[j];
for (int j = 0; j < numBaseLearners; ++j)
outFile << alphas[j]/sumAlphas << ",";
const vector<Label>& labels = pLabelsData->getLabels(i);
for (int l = 0; l < labels.size(); ++l)
if (labels[l].y > 0)
outFile << pLabelsData->getClassMap().getNameFromIdx(labels[l].idx) << endl;
delete pOutInfo;
}
outFile.close();
}
if (pModel)
delete pModel;
return 0;
}
