C++ TimeSeriesClassificationData::getNumClasses方法代码示例

bool ParticleClassifier::train_(TimeSeriesClassificationData &trainingData){
    
    clear();
    
    numClasses = trainingData.getNumClasses();
    numInputDimensions = trainingData.getNumDimensions();
    ranges = trainingData.getRanges();
    
    //Scale the training data if needed
    if( useScaling ){
        trainingData.scale(0, 1);
    }
    
    //Train the particle filter
    particleFilter.train( numParticles, trainingData, sensorNoise, transitionSigma, phaseSigma, velocitySigma );
    
    classLabels.resize(numClasses);
    classLikelihoods.resize(numClasses,0);
    classDistances.resize(numClasses,0);
    
    for(unsigned int i=0; i<numClasses; i++){
        classLabels[i] = trainingData.getClassTracker()[i].classLabel;
    }
    
    trained = true;
  
    return trained;
}

int main (int argc, const char * argv[])
{
    TimeSeriesClassificationData trainingData;      //This will store our training data

    GestureRecognitionPipeline pipeline;               //This is a wrapper for our classifier and any pre/post processing modules

	string dirPath = "/home/vlad/AndroidStudioProjects/DataCapture/dataSetGenerator/build";

	if (!trainingData.loadDatasetFromFile(dirPath + "/acc-training-set-segmented.data")) {
		printf("Cannot open training segmented set\n");
		return 0;
	}

	printf("Successfully opened training data set ...\n");

    DTW dtw;
//    LowPassFilter lpf(0.1, 1, 1);
//    pipeline.setPreProcessingModule(lpf);

//    DoubleMovingAverageFilter filter( 1000, 3 );
//    pipeline.setPreProcessingModule(filter);

    //dtw.enableNullRejection( true );

    //Set the null rejection coefficient to 3, this controls the thresholds for the automatic null rejection
	//You can increase this value if you find that your real-time gestures are not being recognized
	//If you are getting too many false positives then you should decrease this value
    //dtw.setNullRejectionCoeff( 5 );
    dtw.enableTrimTrainingData(true, 0.1, 90);
//    dtw.setOffsetTimeseriesUsingFirstSample(true);

    pipeline.setClassifier( dtw );

    UINT KFolds = 5;

    /* Separate input dataset using KFold */
    KfoldTimeSeriesData* kFoldTS  = new KfoldTimeSeriesData(trainingData);
	if( !kFoldTS->spiltDataIntoKFolds(KFolds) ) {
		printf("BaseTGTestModel: Failed to spiltDataIntoKFolds!");
		return 0;
	}

	UINT maxTrainigSetSize = trainingData.getNumSamples() * (KFolds - 1) / (KFolds * trainingData.getNumClasses());


	// KFolds


	ofstream myfile;
	  myfile.open ("example.txt");
	Float acc = 0;
	for (GRT::UINT k = 1 ; k < KFolds; k++) {

		printf("Running tests for: %d fold", k);
		//  maxTrainigSetSize
//		for (UINT trainingSetSize = 1; trainingSetSize <= maxTrainigSetSize; trainingSetSize ++) {

			/* Set up training datasets for current fold */
			TimeSeriesClassificationData trainingDataset = kFoldTS->getTrainingFoldData(k, maxTrainigSetSize);

			/* Set up validation datasets for current fold */
			TimeSeriesClassificationDataStream testDataset = kFoldTS->getTestFoldData(k);

			/* Log test dataset size */
			//printf("Data set size: training %d; testing %d",
//					trainingDataset.getNumSamples(), testDataset.getNumSamples());

			/* Run test for current fold */
			pipeline.train(trainingDataset);
			pipeline.test(testDataset);
			myfile << pipeline.getTestAccuracy() << "\n";
//		}
	}

	  myfile.close();

	printf("Accuracy = %f ; %d\n", acc, maxTrainigSetSize);

}

bool HMM::train_continuous(TimeSeriesClassificationData &trainingData){
    
    clear();
    
    if( trainingData.getNumSamples() == 0 ){
        errorLog << "train_continuous(TimeSeriesClassificationData &trainingData) - There are no training samples to train the CHMM classifer!" << endl;
        return false;
    }
    
    //Reset the CHMM
    numInputDimensions = trainingData.getNumDimensions();
    numClasses = trainingData.getNumClasses();
    classLabels.resize( numClasses );
    for(UINT k=0; k<numClasses; k++){
        classLabels[k] = trainingData.getClassTracker()[k].classLabel;
    }
    
    //Scale the training data if needed
    ranges = trainingData.getRanges();
    if( useScaling ){
        trainingData.scale(0, 1);
    }
    
    //Setup the models, there will be 1 model for each training sample
    const UINT numTrainingSamples = trainingData.getNumSamples();
    continuousModels.resize( numTrainingSamples );
    
    //Train each of the models
    for(UINT k=0; k<numTrainingSamples; k++){
        
        //Init the model
        continuousModels[k].setDownsampleFactor( downsampleFactor );
        continuousModels[k].setModelType( modelType );
        continuousModels[k].setDelta( delta );
        continuousModels[k].setSigma( sigma );
        continuousModels[k].setAutoEstimateSigma( autoEstimateSigma );
        continuousModels[k].enableScaling( false ); //Scaling should always off for the models as we do any scaling in the CHMM
        
        //Train the model
        if( !continuousModels[k].train_( trainingData[k] ) ){
            errorLog << "train_continuous(TimeSeriesClassificationData &trainingData) - Failed to train CHMM for sample " << k << endl;
            return false;
        }
    }
    
    if( committeeSize > trainingData.getNumSamples() ){
        committeeSize = trainingData.getNumSamples();
        warningLog << "train_continuous(TimeSeriesClassificationData &trainingData) - The committeeSize is larger than the number of training sample. Setting committeeSize to number of training samples: " << trainingData.getNumSamples() << endl;
    }
    
    //Flag that the model has been trained
    trained = true;
    
    //Compute any null rejection thresholds if needed
    if( useNullRejection ){
        //Compute the rejection thresholds
        nullRejectionThresholds.resize(numClasses);
    }
    
    return true;
}

bool HMM::train_discrete(TimeSeriesClassificationData &trainingData){
    
    clear();
    
    if( trainingData.getNumSamples() == 0 ){
        errorLog << "train_discrete(TimeSeriesClassificationData &trainingData) - There are no training samples to train the HMM classifer!" << endl;
        return false;
    }
    
    if( trainingData.getNumDimensions() != 1 ){
        errorLog << "train_discrete(TimeSeriesClassificationData &trainingData) - The number of dimensions in the training data must be 1. If your training data is not 1 dimensional then you must quantize the training data using one of the GRT quantization algorithms" << endl;
        return false;
    }
    
    //Reset the HMM
    numInputDimensions = trainingData.getNumDimensions();
    numClasses = trainingData.getNumClasses();
    discreteModels.resize( numClasses );
    classLabels.resize( numClasses );
    
    //Init the models
    for(UINT k=0; k<numClasses; k++){
        discreteModels[k].resetModel(numStates,numSymbols,modelType,delta);
        discreteModels[k].setMaxNumEpochs( maxNumEpochs );
        discreteModels[k].setMinChange( minChange );
    }
    
    //Train each of the models
    for(UINT k=0; k<numClasses; k++){
        //Get the class ID of this gesture
        UINT classID = trainingData.getClassTracker()[k].classLabel;
        classLabels[k] = classID;
        
        //Convert this classes training data into a list of observation sequences
        TimeSeriesClassificationData classData = trainingData.getClassData( classID );
        vector< vector< UINT > > observationSequences;
        if( !convertDataToObservationSequence( classData, observationSequences ) ){
            return false;
        }
        
        //Train the model
        if( !discreteModels[k].train( observationSequences ) ){
            errorLog << "train_discrete(TimeSeriesClassificationData &trainingData) - Failed to train HMM for class " << classID << endl;
            return false;
        }
    }
    
    //Compute the rejection thresholds
    nullRejectionThresholds.resize(numClasses);
    
    for(UINT k=0; k<numClasses; k++){
        //Get the class ID of this gesture
        UINT classID = trainingData.getClassTracker()[k].classLabel;
        classLabels[k] = classID;
        
        //Convert this classes training data into a list of observation sequences
        TimeSeriesClassificationData classData = trainingData.getClassData( classID );
        vector< vector< UINT > > observationSequences;
        if( !convertDataToObservationSequence( classData, observationSequences ) ){
            return false;
        }
        
        //Test the model
        double loglikelihood = 0;
        double avgLoglikelihood = 0;
        for(UINT i=0; i<observationSequences.size(); i++){
            loglikelihood = discreteModels[k].predict( observationSequences[i] );
            avgLoglikelihood += fabs( loglikelihood );
        }
        nullRejectionThresholds[k] = -( avgLoglikelihood / double( observationSequences.size() ) );
    }
    
    //Flag that the model has been trained
    trained = true;
    
    return true;
    
}

int main() {
    vector<string> gestures(0,"");
    GetFilesInDirectory(gestures, "rawdata");
    CreateDirectory("processed", NULL);
    sort(gestures.begin(), gestures.end());
    data = vector<vector<vector<double > > >(gestures.size(), vector<vector<double > >(0,vector<double>(0,0)));
    for(size_t i = 0; i < gestures.size(); i++) {
        ifstream fin(gestures[i]);
        int n; fin >> n;
       // cerr << gestures[i] << endl;
       // cerr << n << endl;
        data[i] = vector<vector<double> >(n, vector<double>(NUMPARAM, 0));
        for(int j = 0; j < n; j++) {
            for(int k = 0; k < NUMPARAM; k++) {
                fin >> data[i][j][k];
            }
        }
        fin.close();
    }


    //Create a new instance of the TimeSeriesClassificationDataStream
    TimeSeriesClassificationData trainingData;

    // ax, ay, az
    trainingData.setNumDimensions(3);
    trainingData.setDatasetName("processed\\GestureTrainingData.txt");
    ofstream labelfile("processed\\GestureTrainingDataLabels.txt");
    UINT currLabel = 1;
    Random random;
    map<string, int> gesturenames;
    for(size_t overall = 0; overall < gestures.size(); overall++) {

        string nam = gestures[overall].substr(8,gestures[overall].find_first_of('_')-8);
        if(gesturenames.count(nam)) currLabel = gesturenames[nam];
        else {
            currLabel = gesturenames.size()+1;
            gesturenames[nam] = currLabel;
            labelfile << currLabel << " " << nam << endl;
        }
        MatrixDouble trainingSample;
        VectorDouble currVec( trainingData.getNumDimensions() );
        for(size_t k = 1; k < data[overall].size(); k++) {
            for(UINT j=0; j<currVec.size(); j++){
                currVec[j] = data[overall][k][j];
            }
            trainingSample.push_back(currVec);
        }
        trainingData.addSample(currLabel, trainingSample);

    }
    for(size_t i = 0; i < gestures.size(); i++) {
        MatrixDouble trainingSample;
        VectorDouble currVec(trainingData.getNumDimensions());
        for(UINT j = 0; j < currVec.size(); j++) {
            currVec[j] = random.getRandomNumberUniform(-1.0, 1.0);
        }
        for(size_t k = 0; k < 100; k++) {
            trainingSample.push_back(currVec);
        }
        trainingData.addSample(0, trainingSample);
    }

    //After recording your training data you can then save it to a file
    if( !trainingData.save( "processed\\TrainingData.grt" ) ){
        cout << "ERROR: Failed to save dataset to file!\n";
        return EXIT_FAILURE;
    }

    //This can then be loaded later
    if( !trainingData.load( "processed\\TrainingData.grt" ) ){
        cout << "ERROR: Failed to load dataset from file!\n";
        return EXIT_FAILURE;
    }

    //This is how you can get some stats from the training data
    string datasetName = trainingData.getDatasetName();
    string infoText = trainingData.getInfoText();
    UINT numSamples = trainingData.getNumSamples();
    UINT numDimensions = trainingData.getNumDimensions();
    UINT numClasses = trainingData.getNumClasses();

    cout << "Dataset Name: " << datasetName << endl;
    cout << "InfoText: " << infoText << endl;
    cout << "NumberOfSamples: " << numSamples << endl;
    cout << "NumberOfDimensions: " << numDimensions << endl;
    cout << "NumberOfClasses: " << numClasses << endl;

    //You can also get the minimum and maximum ranges of the data
    vector< MinMax > ranges = trainingData.getRanges();

    cout << "The ranges of the dataset are: \n";
    for(UINT j=0; j<ranges.size(); j++){
        cout << "Dimension: " << j << " Min: " << ranges[j].minValue << " Max: " << ranges[j].maxValue << endl;
    }

    DTW dtw;

    if( !dtw.train( trainingData ) ){
        cerr << "Failed to train classifier!\n";
//.........这里部分代码省略.........

int main (int argc, const char * argv[])
{
    //Create a new instance of the TimeSeriesClassificationData
    TimeSeriesClassificationData trainingData;
    
    //Set the dimensionality of the data (you need to do this before you can add any samples)
    trainingData.setNumDimensions( 3 );
    
    //You can also give the dataset a name (the name should have no spaces)
    trainingData.setDatasetName("DummyData");
    
    //You can also add some info text about the data
    trainingData.setInfoText("This data contains some dummy timeseries data");
    
    //Here you would record a time series, when you have finished recording the time series then add the training sample to the training data
    UINT gestureLabel = 1;
    MatrixDouble trainingSample;
    
    //For now we will just add 10 x 20 random walk data timeseries
    Random random;
    for(UINT k=0; k<10; k++){//For the number of classes
        gestureLabel = k+1;
        
        //Get the init random walk position for this gesture
        VectorDouble startPos( trainingData.getNumDimensions() );
        for(UINT j=0; j<startPos.size(); j++){
            startPos[j] = random.getRandomNumberUniform(-1.0,1.0);
        }
                
        //Generate the 20 time series
        for(UINT x=0; x<20; x++){
            
            //Clear any previous timeseries
            trainingSample.clear();
            
            //Generate the random walk
            UINT randomWalkLength = random.getRandomNumberInt(90, 110);
            VectorDouble sample = startPos;
            for(UINT i=0; i<randomWalkLength; i++){
                for(UINT j=0; j<startPos.size(); j++){
                    sample[j] += random.getRandomNumberUniform(-0.1,0.1);
                }
                
                //Add the sample to the training sample
                trainingSample.push_back( sample );
            }
            
            //Add the training sample to the dataset
            trainingData.addSample( gestureLabel, trainingSample );
            
        }
    }
    
    //After recording your training data you can then save it to a file
    if( !trainingData.saveDatasetToFile( "TrainingData.txt" ) ){
	    cout << "Failed to save dataset to file!\n";
	    return EXIT_FAILURE;
	}
    
    //This can then be loaded later
    if( !trainingData.loadDatasetFromFile( "TrainingData.txt" ) ){
		cout << "Failed to load dataset from file!\n";
		return EXIT_FAILURE;
	}
    
    //This is how you can get some stats from the training data
    string datasetName = trainingData.getDatasetName();
    string infoText = trainingData.getInfoText();
    UINT numSamples = trainingData.getNumSamples();
    UINT numDimensions = trainingData.getNumDimensions();
    UINT numClasses = trainingData.getNumClasses();
    
    cout << "Dataset Name: " << datasetName << endl;
    cout << "InfoText: " << infoText << endl;
    cout << "NumberOfSamples: " << numSamples << endl;
    cout << "NumberOfDimensions: " << numDimensions << endl;
    cout << "NumberOfClasses: " << numClasses << endl;
    
    //You can also get the minimum and maximum ranges of the data
    vector< MinMax > ranges = trainingData.getRanges();
    
    cout << "The ranges of the dataset are: \n";
    for(UINT j=0; j<ranges.size(); j++){
        cout << "Dimension: " << j << " Min: " << ranges[j].minValue << " Max: " << ranges[j].maxValue << endl;
    }
    
    //If you want to partition the dataset into a training dataset and a test dataset then you can use the partition function
    //A value of 80 means that 80% of the original data will remain in the training dataset and 20% will be returned as the test dataset
    TimeSeriesClassificationData testData = trainingData.partition( 80 );
    
    //If you have multiple datasets that you want to merge together then use the merge function
    if( !trainingData.merge( testData ) ){
		cout << "Failed to merge datasets!\n";
		return EXIT_FAILURE;
	}
    
    //If you want to run K-Fold cross validation using the dataset then you should first spilt the dataset into K-Folds
    //A value of 10 splits the dataset into 10 folds and the true parameter signals that stratified sampling should be used
    if( !trainingData.spiltDataIntoKFolds( 10, true ) ){
		cout << "Failed to spiltDataIntoKFolds!\n";
//.........这里部分代码省略.........