예제 #1
0
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);
}
예제 #2
0
void MDDAGClassifier::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);
}
예제 #3
0
void MDDAGClassifier::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, "err");

    // 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< AlphaReal > votesForExamples( numClasses );
    vector< AlphaReal > 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;
        AlphaReal alpha = currWeakHyp->getAlpha();

        // for every point
        for (int i = 0; i < numExamples; ++i)
        {
            // a reference for clarity and speed
            vector<AlphaReal>& 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->outputCustom(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 );
        AlphaReal lLambda = 0.0;
        for (int i = 0; i < numExamples; ++i)
        {
            // a reference for clarity and speed
            vector<AlphaReal>& currVotesVector = results[i]->getVotesVector();
            AlphaReal 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<AlphaReal>::epsilon() )
            {
                for (int l = 0; l < numClasses; ++l)
                {
                    expVotesForExamples[l] /= sumExp;
                }
            }

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

                        if ( logVal != m ) {
                            lLambda += ( ( 1.0/(AlphaReal)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);
}
예제 #4
0
void MDDAGClassifier::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, (int)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);
}
예제 #5
0
void MDDAGClassifier::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, (int)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);
}
예제 #6
0
	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);
	}
예제 #7
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;
    }
예제 #8
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);
			float constantEnergy = pConstantWeakHypothesis->run();

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

			updateMargins( pTrainingData, pConstantWeakHypothesis );

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

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

			if (pTestData)
				pOutInfo->outputError(pTestData, pConstantWeakHypothesis);
			/*
			pOutInfo->outputMargins(pTrainingData, pConstantWeakHypothesis);
			
			pOutInfo->outputEdge(pTrainingData, pConstantWeakHypothesis);

			if (pTestData)
				pOutInfo->outputMargins(pTestData, pConstantWeakHypothesis);

			pOutInfo->outputMAE(pTrainingData);

			if (pTestData)
				pOutInfo->outputMAE(pTestData);
			*/
			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;

			filter( pTrainingData, (int)(_Cn * log(t+2.0)) );
			if ( pTrainingData->getNumExamples() < 2 ) 
			{
				filter( pTrainingData, (int)(_Cn * log(t+2.0)), false );
			}
			
			if (_verbose > 1)
			{
				cout << "--> Size of training data = " << pTrainingData->getNumExamples() << endl;
			}

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

			BaseLearner* pConstantWeakHypothesis;
			if (_withConstantLearner) // check constant learner if user wants it
			{
				pConstantWeakHypothesis = pConstantWeakHypothesisSource->create() ;
				pConstantWeakHypothesis->initLearningOptions(args);
				pConstantWeakHypothesis->setTrainingData(pTrainingData);
				float constantEnergy = pConstantWeakHypothesis->run();
			}

			//estimate edge
			filter( pTrainingData, (int)(_Cn * log(t+2.0)), false );
			float edge = pWeakHypothesis->getEdge() / 2.0;

			if (_withConstantLearner) // check constant learner if user wants it
			{
				float constantEdge = pConstantWeakHypothesis->getEdge() / 2.0;
				if ( constantEdge > edge )
				{
					delete pWeakHypothesis;
					pWeakHypothesis = pConstantWeakHypothesis;
					edge = constantEdge;
				} else {
					delete pConstantWeakHypothesis;
				}
			}

			// calculate alpha
			float alpha = 0.0;
			alpha = 0.5 * log( ( 0.5 + edge ) / ( 0.5 - edge ) );
			pWeakHypothesis->setAlpha( 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
			float 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
					;
			}

			// update the margins
			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;
	}