示例#1
0
    void FilterBoostLearner::run(const nor_utils::Args& args)
    {
        // load the arguments
        this->getArgs(args);

        time_t startTime, currentTime;
        time(&startTime);

        // get the registered weak learner (type from name)
        BaseLearner* pWeakHypothesisSource = 
            BaseLearner::RegisteredLearners().getLearner(_baseLearnerName);
        // initialize learning options; normally it's done in the strong loop
        // also, here we do it for Product learners, so input data can be created
        pWeakHypothesisSource->initLearningOptions(args);

        BaseLearner* pConstantWeakHypothesisSource = 
            BaseLearner::RegisteredLearners().getLearner("ConstantLearner");

        // get the training input data, and load it

        InputData* pTrainingData = pWeakHypothesisSource->createInputData();
        pTrainingData->initOptions(args);
        pTrainingData->load(_trainFileName, IT_TRAIN, _verbose);

        const int numClasses = pTrainingData->getNumClasses();
        const int numExamples = pTrainingData->getNumExamples();
                
        //initialize the margins variable
        _margins.resize( numExamples );
        for( int i=0; i<numExamples; i++ )
        {
            _margins[i].resize( numClasses );
            fill( _margins[i].begin(), _margins[i].end(), 0.0 );
        }


        // get the testing input data, and load it
        InputData* pTestData = NULL;
        if ( !_testFileName.empty() )
        {
            pTestData = pWeakHypothesisSource->createInputData();
            pTestData->initOptions(args);
            pTestData->load(_testFileName, IT_TEST, _verbose);
        }

        // The output information object
        OutputInfo* pOutInfo = NULL;


        if ( !_outputInfoFile.empty() ) 
        {
            // Baseline: constant classifier - goes into 0th iteration

            BaseLearner* pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
            pConstantWeakHypothesis->initLearningOptions(args);
            pConstantWeakHypothesis->setTrainingData(pTrainingData);
            AlphaReal constantEnergy = pConstantWeakHypothesis->run();

            pOutInfo = new OutputInfo(args);
            pOutInfo->initialize(pTrainingData);

            updateMargins( pTrainingData, pConstantWeakHypothesis );

            if (pTestData)
                pOutInfo->initialize(pTestData);
            pOutInfo->outputHeader(pTrainingData->getClassMap() );

            pOutInfo->outputIteration(-1);
            pOutInfo->outputCustom(pTrainingData, pConstantWeakHypothesis);

            if (pTestData)
            {
                pOutInfo->separator();
                pOutInfo->outputCustom(pTestData, pConstantWeakHypothesis);
            }
                        
            pOutInfo->outputCurrentTime();

            pOutInfo->endLine();
            pOutInfo->initialize(pTrainingData);
                        
            if (pTestData)
                pOutInfo->initialize(pTestData);
        }
        // reload the previously found weak learners if -resume is set. 
        // otherwise just return 0
        int startingIteration = resumeWeakLearners(pTrainingData);


        Serialization ss(_shypFileName, _isShypCompressed );
        ss.writeHeader(_baseLearnerName); // this must go after resumeProcess has been called

        // perform the resuming if necessary. If not it will just return
        resumeProcess(ss, pTrainingData, pTestData, pOutInfo);

        if (_verbose == 1)
            cout << "Learning in progress..." << endl;
                                
        ///////////////////////////////////////////////////////////////////////
        // Starting the AdaBoost main loop
        ///////////////////////////////////////////////////////////////////////
        for (int t = startingIteration; t < _numIterations; ++t)
        {                       
            if (_verbose > 1)
                cout << "------- WORKING ON ITERATION " << (t+1) << " -------" << endl;
                
            // create the weak learner
            BaseLearner* pWeakHypothesis;
            BaseLearner* pConstantWeakHypothesis;
            pWeakHypothesis = pWeakHypothesisSource->create();
            pWeakHypothesis->initLearningOptions(args);
            //pTrainingData->clearIndexSet();
            pWeakHypothesis->setTrainingData(pTrainingData);
            AlphaReal edge, energy=0.0;
                        
            // create the constant learner
            pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
            pConstantWeakHypothesis->initLearningOptions(args);
            pConstantWeakHypothesis->setTrainingData(pTrainingData);
            AlphaReal constantEdge = -numeric_limits<AlphaReal>::max();
                        
            int currentNumberOfUsedData = static_cast<int>(_Cn * log(t+3.0));
                        
            if ( _onlineWeakLearning )
            {
                //check whether the weak learner is a ScalarLeaerner
                try {
                    StochasticLearner* pStochasticLearner = dynamic_cast<StochasticLearner*>(pWeakHypothesis);
                    StochasticLearner* pStochasticConstantWeakHypothesis = dynamic_cast<StochasticLearner*> (pConstantWeakHypothesis);
                                        
                    pStochasticLearner->initLearning();
                    pStochasticConstantWeakHypothesis->initLearning();                                                                              
                                        
                    if (_verbose>1)
                        cout << "Number of random instances: \t" << currentNumberOfUsedData << endl;
                                        
                    // set the weights
                    setWeightToMargins(pTrainingData);
                                        
                    //learning
                    for (int i=0; i<currentNumberOfUsedData; ++i )
                    {
                        int randomIndex = (rand() % pTrainingData->getNumExamples());   
                        //int randomIndex = getRandomIndex();
                        pStochasticLearner->update(randomIndex);
                        pStochasticConstantWeakHypothesis->update(randomIndex);
                    }                                       
                    pStochasticLearner->finishLearning();           
                    pStochasticConstantWeakHypothesis->finishLearning();
                }
                catch (bad_cast& e) {
                    cerr << "The weak learner must be a StochasticLearner!!!" << endl;
                    exit(-1);
                }                                                                                               
            }
            else
            {
                filter( pTrainingData, currentNumberOfUsedData );
                if ( pTrainingData->getNumExamples() < 2 ) 
                {
                    filter( pTrainingData, currentNumberOfUsedData, false );
                }
                                
                if (_verbose > 1)
                {
                    cout << "--> Size of training data = " << pTrainingData->getNumExamples() << endl;
                }
                                
                energy = pWeakHypothesis->run();                                                                
                pConstantWeakHypothesis->run(); 
            }                       

            //estimate edge
            filter( pTrainingData, currentNumberOfUsedData, false );
            edge = pWeakHypothesis->getEdge(true) / 2.0;                                            
            constantEdge = pConstantWeakHypothesis->getEdge() / 2.0;
                        
                        
            if ( constantEdge > edge )
            {
                delete pWeakHypothesis;
                pWeakHypothesis = pConstantWeakHypothesis;
                edge = constantEdge;
            } else {
                delete pConstantWeakHypothesis;
            }
                                                                        
            // calculate alpha
            AlphaReal alpha = 0.0;
            alpha = 0.5 * log( ( 1 + edge ) / ( 1 - edge ) );
            pWeakHypothesis->setAlpha( alpha );
            _sumAlpha += alpha;
                        
            if (_verbose > 1)
                cout << "Weak learner: " << pWeakHypothesis->getName()<< endl;
            // Output the step-by-step information
            pTrainingData->clearIndexSet();
            printOutputInfo(pOutInfo, t, pTrainingData, pTestData, pWeakHypothesis);

            // Updates the weights and returns the edge
            //AlphaReal gamma = updateWeights(pTrainingData, pWeakHypothesis);

            if (_verbose > 1)
            {
                cout << setprecision(5)
                     << "--> Alpha = " << pWeakHypothesis->getAlpha() << endl
                     << "--> Edge  = " << edge << endl
                     << "--> Energy  = " << energy << endl
                    //            << "--> ConstantEnergy  = " << constantEnergy << endl
                    //            << "--> difference  = " << (energy - constantEnergy) << endl
                    ;
            }

            // update the margins
            //saveMargins();
            updateMargins( pTrainingData, pWeakHypothesis );
                        
            // append the current weak learner to strong hypothesis file,
            // that is, serialize it.
            ss.appendHypothesis(t, pWeakHypothesis);

            // Add it to the internal list of weak hypotheses
            _foundHypotheses.push_back(pWeakHypothesis); 

            // check if the time limit has been reached
            if (_maxTime > 0)
            {
                time( &currentTime );
                float diff = difftime(currentTime, startTime); // difftime is in seconds
                diff /= 60; // = minutes

                if (diff > _maxTime)
                {
                    if (_verbose > 0)
                        cout << "Time limit of " << _maxTime 
                             << " minutes has been reached!" << endl;
                    break;     
                }
            } // check for maxtime
            delete pWeakHypothesis;
        }  // loop on iterations
        /////////////////////////////////////////////////////////

        // write the footer of the strong hypothesis file
        ss.writeFooter();

        // Free the two input data objects
        if (pTrainingData)
            delete pTrainingData;
        if (pTestData)
            delete pTestData;

        if (pOutInfo)
            delete pOutInfo;

        if (_verbose > 0)
            cout << "Learning completed." << endl;
    }
示例#2
0
	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;
		}
	}
示例#3
0
	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;
		}
	}
示例#4
0
	void FilterBoostClassifier::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;

		const int colSize = 7;

		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);
	}
示例#5
0
文件: main.cpp 项目: busarobi/MDDAG2
/**
 * 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;
}
示例#6
0
	void FilterBoostClassifier::saveLikelihoods(const string& dataFileName, const string& shypFileName, 
		const string& outFileName, int numIterations)
	{
		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;

		const int numClasses = pData->getNumClasses();
		const int numExamples = pData->getNumExamples();


		ofstream outFile(outFileName.c_str());
		string exampleName;

		if (_verbose > 0)
			cout << "Output likelihoods..." << flush;

		// get the results
		/////////////////////////////////////////////////////////////////////
		// computeResults( pData, weakHypotheses, results, numIterations );
		assert( !weakHypotheses.empty() );

		// Initialize the output info
		OutputInfo* pOutInfo = NULL;

		if ( !_outputInfoFile.empty() )
			pOutInfo = new OutputInfo(_outputInfoFile);

		// Creating the results structures. See file Structures.h for the
		// PointResults structure
		results.clear();
		results.reserve(numExamples);
		for (int i = 0; i < numExamples; ++i)
			results.push_back( new ExampleResults(i, numClasses) );

		// sum votes for classes
		vector< float > votesForExamples( numClasses );
		vector< double > expVotesForExamples( numClasses );

		// iterator over all the weak hypotheses
		vector<BaseLearner*>::const_iterator whyIt;
		int t;

		pOutInfo->initialize( pData );

		// for every feature: 1..T
		for (whyIt = weakHypotheses.begin(), t = 0; 
			whyIt != weakHypotheses.end() && t < numIterations; ++whyIt, ++t)
		{
			BaseLearner* currWeakHyp = *whyIt;
			float alpha = currWeakHyp->getAlpha();

			// for every point
			for (int i = 0; i < numExamples; ++i)
			{
				// a reference for clarity and speed
				vector<float>& currVotesVector = results[i]->getVotesVector();

				// for every class
				for (int l = 0; l < numClasses; ++l)
					currVotesVector[l] += alpha * currWeakHyp->classify(pData, i, l);
			}

			// if needed output the step-by-step information
			if ( pOutInfo )
			{
				pOutInfo->outputIteration(t);
				pOutInfo->outputError(pData, currWeakHyp);

				// Margins and edge requires an update of the weight,
				// therefore I keep them out for the moment
				//outInfo.outputMargins(pData, currWeakHyp);
				//outInfo.outputEdge(pData, currWeakHyp);
				pOutInfo->endLine();
			} // for (int i = 0; i < numExamples; ++i)
			// calculate likelihoods from votes

			fill( votesForExamples.begin(), votesForExamples.end(), 0.0 );
			double lLambda = 0.0;
			for (int i = 0; i < numExamples; ++i)
			{
				// a reference for clarity and speed
				vector<float>& currVotesVector = results[i]->getVotesVector();
				double sumExp = 0.0;
				// for every class
				for (int l = 0; l < numClasses; ++l) 
				{				 
					expVotesForExamples[l] =  exp( currVotesVector[l] ) ;
					sumExp += expVotesForExamples[l];
				}			

				if ( sumExp > numeric_limits<double>::epsilon() ) 
				{
					for (int l = 0; l < numClasses; ++l) 
					{
						expVotesForExamples[l] /= sumExp;
					}
				}

				Example ex = pData->getExample( results[i]->getIdx() );
				vector<Label> labs = ex.getLabels();
				double m = numeric_limits<double>::infinity();
				for (int l = 0; l < numClasses; ++l)  
				{
					if ( labs[l].y > 0 )
					{
						if ( expVotesForExamples[l] > numeric_limits<double>::epsilon() )
						{
							double logVal = log( expVotesForExamples[l] );
							
							if ( logVal != m ) {
								lLambda += ( ( 1.0/(double)numExamples ) * logVal );
							}
						}
					}
				}


			}
			

			outFile << t << "\t" << lLambda ;
			outFile << '\n';
			
			outFile.flush();
		}

		if (pOutInfo)
			delete pOutInfo;

		// computeResults( pData, weakHypotheses, results, numIterations );
		///////////////////////////////////////////////////////////////////////////////////


		/*
		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() )
				outFile << exampleName << ',';

			// output the posteriors
			outFile << results[i]->getVotesVector()[0];
			for (int l = 1; l < numClasses; ++l)
				outFile << ',' << results[i]->getVotesVector()[l];
			outFile << '\n';
		}
		*/

		if (_verbose > 0)
			cout << "Done!" << endl;

		if (_verbose > 1)
		{
			cout << "\nClass order (You can change it in the header of the data file):" << endl;
			for (int l = 0; l < numClasses; ++l)
				cout << "- " << pData->getClassMap().getNameFromIdx(l) << endl;
		}

		// delete the input data file
		if (pData) 
			delete pData;

		vector<ExampleResults*>::iterator it;
		for (it = results.begin(); it != results.end(); ++it)
			delete (*it);
	}
示例#7
0
	void FilterBoostClassifier::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());

			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 ) << 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);
	}
示例#8
0
	void FilterBoostClassifier::saveCalibratedPosteriors(const string& dataFileName, const string& shypFileName, 
		const string& outFileName, int numIterations)
	{
		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();
		const int numExamples = pData->getNumExamples();

		ofstream outFile(outFileName.c_str());
		string exampleName;

		if (_verbose > 0)
			cout << "Output posteriors..." << flush;

		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() )
				outFile << exampleName << ',';

			// output the posteriors
			outFile << results[i]->getVotesVector()[0];
			for (int l = 1; l < numClasses; ++l)
				outFile << ',' << results[i]->getVotesVector()[l];
			outFile << '\n';
		}

		if (_verbose > 0)
			cout << "Done!" << endl;

		if (_verbose > 1)
		{
			cout << "\nClass order (You can change it in the header of the data file):" << endl;
			for (int l = 0; l < numClasses; ++l)
				cout << "- " << pData->getClassMap().getNameFromIdx(l) << endl;
		}

		// delete the input data file
		if (pData) 
			delete pData;

		vector<ExampleResults*>::iterator it;
		for (it = results.begin(); it != results.end(); ++it)
			delete (*it);
	}
示例#9
0
	void FilterBoostClassifier::saveConfusionMatrix(const string& dataFileName, const string& shypFileName,
		const string& outFileName)
	{
		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, weakHypotheses.size() );

		const int numClasses = pData->getNumClasses();
		const int numExamples = pData->getNumExamples();

		ofstream outFile(outFileName.c_str());

		//////////////////////////////////////////////////////////////////////////

		for (int l = 0; l < numClasses; ++l)
			outFile << '\t' << pData->getClassMap().getNameFromIdx(l);
		outFile << endl;

		for (int l = 0; l < numClasses; ++l)
		{
			vector<int> winnerCount(numClasses, 0);
			for (int i = 0; i < numExamples; ++i)
			{
				if ( pData->hasPositiveLabel(i,l) )
					++winnerCount[ results[i]->getWinner().first ];
			}

			// class name
			outFile << pData->getClassMap().getNameFromIdx(l);

			for (int j = 0; j < numClasses; ++j)
				outFile << '\t' << winnerCount[j];

			outFile << endl;
		}

		//////////////////////////////////////////////////////////////////////////

		if (_verbose > 0)
			cout << "Done!" << endl;

		// delete the input data file
		if (pData) 
			delete pData;

		vector<ExampleResults*>::iterator it;
		for (it = results.begin(); it != results.end(); ++it)
			delete (*it);
	}
示例#10
0
	void FilterBoostClassifier::printConfusionMatrix(const string& dataFileName, const string& shypFileName)
	{
		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, weakHypotheses.size());

		const int numClasses = pData->getNumClasses();
		const int numExamples = pData->getNumExamples();

		if (_verbose > 0)
			cout << "Done!" << endl;

		const int colSize = 7;

		if (_verbose > 0)
		{
			cout << "Raw Confusion Matrix:\n";
			cout << setw(colSize) << "Truth       ";

			for (int l = 0; l < numClasses; ++l)
				cout << setw(colSize) << nor_utils::getAlphanumeric(l);

			cout << "\nClassification\n";

			for (int l = 0; l < numClasses; ++l)
			{
				vector<int> winnerCount(numClasses, 0);
				for (int i = 0; i < numExamples; ++i)
				{
					if ( pData->hasPositiveLabel(i, l) )
						++winnerCount[ results[i]->getWinner().first ];
				}

				// class
				cout << setw(colSize) << "           " << nor_utils::getAlphanumeric(l);

				for (int j = 0; j < numClasses; ++j)
					cout << setw(colSize) << winnerCount[j];

				cout << endl;
			}

		}

		cout << "\nMatrix Key:\n";

		// Print the legend
		for (int l = 0; l < numClasses; ++l)
			cout << setw(5) << nor_utils::getAlphanumeric(l) << ": " << 
			pData->getClassMap().getNameFromIdx(l) << "\n";

		// delete the input data file
		if (pData) 
			delete pData;

		vector<ExampleResults*>::iterator it;
		for (it = results.begin(); it != results.end(); ++it)
			delete (*it);
	}
示例#11
0
	void AdaBoostMHLearner::run(const nor_utils::Args& args)
	{
		// load the arguments
		this->getArgs(args);

		// get the registered weak learner (type from name)
		BaseLearner* pWeakHypothesisSource = 
			BaseLearner::RegisteredLearners().getLearner(_baseLearnerName);
		// initialize learning options; normally it's done in the strong loop
		// also, here we do it for Product learners, so input data can be created
		pWeakHypothesisSource->initLearningOptions(args);

		BaseLearner* pConstantWeakHypothesisSource = 
			BaseLearner::RegisteredLearners().getLearner("ConstantLearner");

		// get the training input data, and load it

		InputData* pTrainingData = pWeakHypothesisSource->createInputData();
		pTrainingData->initOptions(args);
		pTrainingData->load(_trainFileName, IT_TRAIN, _verbose);
		
		// get the testing input data, and load it
		InputData* pTestData = NULL;
		if ( !_testFileName.empty() )
		{
			pTestData = pWeakHypothesisSource->createInputData();
			pTestData->initOptions(args);
			pTestData->load(_testFileName, IT_TEST, _verbose);
		}

		// The output information object
		OutputInfo* pOutInfo = NULL;


		if ( !_outputInfoFile.empty() ) 
		{
			// Baseline: constant classifier - goes into 0th iteration

			BaseLearner* pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
			pConstantWeakHypothesis->initLearningOptions(args);
			pConstantWeakHypothesis->setTrainingData(pTrainingData);
			AlphaReal constantEnergy = pConstantWeakHypothesis->run();

			//pOutInfo = new OutputInfo(_outputInfoFile);
            pOutInfo = new OutputInfo(args);
			pOutInfo->initialize(pTrainingData);

			if (pTestData)
				pOutInfo->initialize(pTestData);
			pOutInfo->outputHeader(pTrainingData->getClassMap());

			pOutInfo->outputIteration(-1);
            pOutInfo->outputCustom(pTrainingData, pConstantWeakHypothesis);
            
			if (pTestData != NULL)
            {
                pOutInfo->separator();
                pOutInfo->outputCustom(pTestData, pConstantWeakHypothesis);   
            }

			pOutInfo->outputCurrentTime();

			pOutInfo->endLine(); 
			pOutInfo->initialize(pTrainingData);

			if (pTestData)
				pOutInfo->initialize(pTestData);
		}
		//cout << "Before serialization" << endl;
		// reload the previously found weak learners if -resume is set. 
		// otherwise just return 0
		int startingIteration = resumeWeakLearners(pTrainingData);


		Serialization ss(_shypFileName, _isShypCompressed );
		ss.writeHeader(_baseLearnerName); // this must go after resumeProcess has been called

		// perform the resuming if necessary. If not it will just return
		resumeProcess(ss, pTrainingData, pTestData, pOutInfo);

		if (_verbose == 1)
			cout << "Learning in progress..." << endl;

		//I put here the starting time, but it may take very long time to load the saved model
		time_t startTime, currentTime;
		time(&startTime);

		///////////////////////////////////////////////////////////////////////
		// Starting the AdaBoost main loop
		///////////////////////////////////////////////////////////////////////
		for (int t = startingIteration; t < _numIterations; ++t)
		{
			if (_verbose > 1)
				cout << "------- WORKING ON ITERATION " << (t+1) << " -------" << endl;

			BaseLearner* pWeakHypothesis = pWeakHypothesisSource->create();
			pWeakHypothesis->initLearningOptions(args);
			//pTrainingData->clearIndexSet();

			pWeakHypothesis->setTrainingData(pTrainingData);
			
			AlphaReal energy = pWeakHypothesis->run();
			
			//float gamma = pWeakHypothesis->getEdge();
			//cout << gamma << endl;

			if ( (_withConstantLearner) || ( energy != energy ) ) // check constant learner if user wants it (if energi is nan, then we chose constant learner
			{
				BaseLearner* pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
				pConstantWeakHypothesis->initLearningOptions(args);
				pConstantWeakHypothesis->setTrainingData(pTrainingData);
				AlphaReal constantEnergy = pConstantWeakHypothesis->run();

				if ( (constantEnergy <= energy) || ( energy != energy ) ) {
					delete pWeakHypothesis;
					pWeakHypothesis = pConstantWeakHypothesis;
				}
			}

			if (_verbose > 1)
				cout << "Weak learner: " << pWeakHypothesis->getName()<< endl;
			// Output the step-by-step information
			printOutputInfo(pOutInfo, t, pTrainingData, pTestData, pWeakHypothesis);

			// Updates the weights and returns the edge
			AlphaReal gamma = updateWeights(pTrainingData, pWeakHypothesis);

			if (_verbose > 1)
			{
				cout << setprecision(5)
					<< "--> Alpha = " << pWeakHypothesis->getAlpha() << endl
					<< "--> Edge  = " << gamma << endl
					<< "--> Energy  = " << energy << endl
					//            << "--> ConstantEnergy  = " << constantEnergy << endl
					//            << "--> difference  = " << (energy - constantEnergy) << endl
					;
			}

			// If gamma <= theta the algorithm must stop.
			// If theta == 0 and gamma is 0, it means that the weak learner is no better than chance
			// and no further training is possible.
			if (gamma <= _theta)
			{
				if (_verbose > 0)
				{
					cout << "Can't train any further: edge = " << gamma 
						<< " (with and edge offset (theta)=" << _theta << ")" << endl;
				}

				//          delete pWeakHypothesis;
				//          break; 
			}

			// append the current weak learner to strong hypothesis file,
			// that is, serialize it.
			ss.appendHypothesis(t, pWeakHypothesis);

			// Add it to the internal list of weak hypotheses
			_foundHypotheses.push_back(pWeakHypothesis); 

			// check if the time limit has been reached
			if (_maxTime > 0)
			{
				time( &currentTime );
				float diff = difftime(currentTime, startTime); // difftime is in seconds
				diff /= 60; // = minutes

				if (diff > _maxTime)
				{
					if (_verbose > 0)
						cout << "Time limit of " << _maxTime 
						<< " minutes has been reached!" << endl;
					break;     
				}
			} // check for maxtime
			delete pWeakHypothesis;
		}  // loop on iterations
		/////////////////////////////////////////////////////////

		// write the footer of the strong hypothesis file
		ss.writeFooter();

		// write the weights of the instances if the name of weights file isn't empty
		printOutWeights( pTrainingData );


		// Free the two input data objects
		if (pTrainingData)
			delete pTrainingData;
		if (pTestData)
			delete pTestData;

		if (pOutInfo)
			delete pOutInfo;

		if (_verbose > 0)
			cout << "Learning completed." << endl;
	}
示例#12
0
    void SoftCascadeLearner::run(const nor_utils::Args& args)
    {
        // load the arguments
        this->getArgs(args);
        
        //print cascade properties
        if (_verbose > 0) {
            cout    << "[+] Softcascade parameters :" << endl
                    << "\t --> target detection rate = " << _targetDetectionRate << endl
                    << "\t --> alpha (exp param) = " << _alphaExponentialParameter << endl
                    << "\t --> bootstrap rate = " << _bootstrapRate << endl
                    << endl;
        }
        

        // get the registered weak learner (type from name)
        BaseLearner* pWeakHypothesisSource = 
            BaseLearner::RegisteredLearners().getLearner(_baseLearnerName);
        // initialize learning options; normally it's done in the strong loop
        // also, here we do it for Product learners, so input data can be created
        pWeakHypothesisSource->initLearningOptions(args);

        // get the training input data, and load it

        InputData* pTrainingData = pWeakHypothesisSource->createInputData();
        pTrainingData->initOptions(args);
        pTrainingData->load(_trainFileName, IT_TRAIN, 5);

        InputData* pBootstrapData = NULL;
        if (!_bootstrapFileName.empty()) {
            pBootstrapData = pWeakHypothesisSource->createInputData();
            pBootstrapData->initOptions(args);
            pBootstrapData->load(_bootstrapFileName, IT_TRAIN, 5);
        }
        
        // get the testing input data, and load it
        InputData* pTestData = NULL;
        if ( !_testFileName.empty() )
        {
            pTestData = pWeakHypothesisSource->createInputData();
            pTestData->initOptions(args);
            pTestData->load(_testFileName, IT_TEST, 5);
        }

        Serialization ss(_shypFileName, false );
        ss.writeHeader(_baseLearnerName);
        
        
//        outputHeader();
        // The output information object
        OutputInfo* pOutInfo = NULL;

        if ( !_outputInfoFile.empty() ) 
        {
            pOutInfo = new OutputInfo(args, true);
            pOutInfo->setOutputList("sca", &args);
            
            pOutInfo->initialize(pTrainingData);
            
            if (pTestData)
                pOutInfo->initialize(pTestData);
            pOutInfo->outputHeader(pTrainingData->getClassMap(), true, true, false);
            pOutInfo->outputUserHeader("thresh");
            pOutInfo->headerEndLine();
        }
        
        
//        ofstream trainPosteriorsFile;
//        ofstream testPosteriorsFile;
        
        
        const NameMap& namemap = pTrainingData->getClassMap();
        _positiveLabelIndex = namemap.getIdxFromName(_positiveLabelName);

        // FIXME: output posteriors

//        OutputInfo* pTrainPosteriorsOut = NULL;
//        OutputInfo* pTestPosteriorsOut = NULL;
        
//        if (! _trainPosteriorsFileName.empty()) {
//            pTrainPosteriorsOut = new OutputInfo(_trainPosteriorsFileName, "pos", true);
//            pTrainPosteriorsOut->initialize(pTrainingData);
//            dynamic_cast<PosteriorsOutput*>( pTrainPosteriorsOut->getOutputInfoObject("pos") )->addClassIndex(_positiveLabelIndex );
//        }
        
//        if (! _testPosteriorsFileName.empty() && !_testFileName.empty() ) {
//            pTestPosteriorsOut = new OutputInfo(_testPosteriorsFileName, "pos", true);
//            pTestPosteriorsOut->initialize(pTestData);
//            dynamic_cast<PosteriorsOutput*>( pTestPosteriorsOut->getOutputInfoObject("pos") )->addClassIndex(_positiveLabelIndex );            
//        }
        
        const int numExamples = pTrainingData->getNumExamples();

        vector<BaseLearner*> inWeakHypotheses;
        
        if (_fullRun) {            
            // TODO : the full training is implementet, testing is needed
            AdaBoostMHLearner* sHypothesis = new AdaBoostMHLearner();
            sHypothesis->run(args, pTrainingData, _baseLearnerName, _numIterations, inWeakHypotheses );
            delete sHypothesis;
        }
        else { 
            
            cout << "[+] Loading uncalibrated shyp file... ";
            //read the shyp file of the trained classifier
            UnSerialization us;
            us.loadHypotheses(_unCalibratedShypFileName, inWeakHypotheses, pTrainingData);  
            if (_inShypLimit > 0 && _inShypLimit < inWeakHypotheses.size() ) {
                inWeakHypotheses.resize(_inShypLimit);
            }
            if (_numIterations > inWeakHypotheses.size()) {
                _numIterations = inWeakHypotheses.size();
            }
            cout << "weak hypotheses loaded, " << inWeakHypotheses.size() << " retained.\n";
        }
        
        // some initializations
        _foundHypotheses.resize(0);
        double faceRejectionFraction = 0.;
        double estimatedExecutionTime = 0.;
        vector<double> rejectionDistributionVector;

        _rejectionThresholds.resize(0);
        
        
        set<int> trainingIndices;
        for (int i = 0; i < numExamples; i++) {
            trainingIndices.insert(pTrainingData->getRawIndex(i) );
        }
        
        // init v_t (see the paper)
        initializeRejectionDistributionVector(_numIterations, rejectionDistributionVector);

        if (_verbose == 1)
            cout << "Learning in progress..." << endl;

        ///////////////////////////////////////////////////////////////////////
        // Starting the SoftCascade main loop
        ///////////////////////////////////////////////////////////////////////
        for (int t = 0; t < _numIterations; ++t)
        {
            if (_verbose > 0)
                cout << "--------------[ iteration " << (t+1) << " ]--------------" << endl;

            faceRejectionFraction += rejectionDistributionVector[t];
            
            cout << "[+] Face rejection tolerated : " << faceRejectionFraction << " | v[t] = " << rejectionDistributionVector[t] << endl;
            
            int numberOfNegatives = pTrainingData->getNumExamplesPerClass(1 - _positiveLabelIndex);
            
            //vector<BaseLearner*>::const_iterator whyIt;
            int selectedIndex = 0;
            AlphaReal bestGap = 0;
            vector<AlphaReal> posteriors;
            computePosteriors(pTrainingData, _foundHypotheses, posteriors, _positiveLabelIndex);
            
            //should use an iterator instead of i
            
            vector<BaseLearner*>::iterator whyIt;
            int i;
            for (i = 0, whyIt = inWeakHypotheses.begin(); whyIt != inWeakHypotheses.end(); ++whyIt, ++i) {
            
                vector<AlphaReal> temporaryPosteriors = posteriors;
                vector<BaseLearner*> temporaryWeakHyp = _foundHypotheses;
                temporaryWeakHyp.push_back(*whyIt);
                updatePosteriors(pTrainingData, *whyIt, temporaryPosteriors, _positiveLabelIndex);
                
                AlphaReal gap = computeSeparationSpan(pTrainingData, temporaryPosteriors, _positiveLabelIndex );

                if (gap > bestGap) {
                    bestGap = gap;
                    selectedIndex = i;
                }
            }
            
            BaseLearner* selectedWeakHypothesis = inWeakHypotheses[selectedIndex];
            
            cout << "[+] Rank of the selected weak hypothesis : " << selectedIndex << endl
                 << "\t ---> edge gap = " << bestGap << endl
                 << "\t ---> alpha = " << selectedWeakHypothesis->getAlpha() << endl;

            //update the stages
            _foundHypotheses.push_back(selectedWeakHypothesis);
            updatePosteriors(pTrainingData, selectedWeakHypothesis, posteriors, _positiveLabelIndex);
            
            double missesFraction;
            AlphaReal r = findBestRejectionThreshold(pTrainingData, posteriors, faceRejectionFraction, missesFraction);
            _rejectionThresholds.push_back(r);
            
            
            // update the output info object
            dynamic_cast<SoftCascadeOutput*>( pOutInfo->getOutputInfoObject("sca") )->appendRejectionThreshold(r);
            
            cout << "[+] Rejection threshold = " << r << endl;
            
            //some updates
            ss.appendHypothesisWithThreshold(t, selectedWeakHypothesis, r);
            faceRejectionFraction -= missesFraction;
            
            inWeakHypotheses.erase(inWeakHypotheses.begin() + selectedIndex);
            double whypCost = 1; //just in case there are different costs for each whyp
            estimatedExecutionTime += whypCost * numberOfNegatives;
            
            // output perf in file
            vector< vector< AlphaReal> > scores(0);
            _output << t + 1 << setw(_sepWidth + 1) << r << setw(_sepWidth);
            
            // update OutputInfo with the new whyp
//            updateOutputInfo(pOutInfo, pTrainingData, selectedWeakHypothesis);
//            if (pTestData) {
//                updateOutputInfo(pOutInfo, pTestData, selectedWeakHypothesis);
//            }
            

            // output the iteration results
            printOutputInfo(pOutInfo, t, pTrainingData, pTestData, selectedWeakHypothesis, r);
                        
//            if (pTrainPosteriorsOut) {
//                pTrainPosteriorsOut->setTable(pTrainingData, pOutInfo->getTable(pTrainingData));
//                pTrainPosteriorsOut->outputCustom(pTrainingData);
//            }
//
//            if (pTestPosteriorsOut) {
//                pTestPosteriorsOut->setTable(pTestData, pOutInfo->getTable(pTestData));
//                pTestPosteriorsOut->outputCustom(pTestData);
//            }
            
            
            int leftNegatives = filterDataset(pTrainingData, posteriors, r, trainingIndices);
            if (leftNegatives == 0) {
                cout << endl << "[+] No more negatives.\n";
                break;
            }
            
            if (_bootstrapRate != 0) {
                bootstrapTrainingSet(pTrainingData, pBootstrapData, trainingIndices);
            }

        }  // loop on iterations
        /////////////////////////////////////////////////////////

        // write the footer of the strong hypothesis file
        ss.writeFooter();

        // Free the two input data objects
        if (pTrainingData)
            delete pTrainingData;
        if (pBootstrapData) {
            delete pBootstrapData;
        }
        if (pTestData)
            delete pTestData;

        if (_verbose > 0)
            cout << "Learning completed." << endl;
    }