bool TimeSeriesClassificationData::loadDatasetFromCSVFile(const string &filename){ numDimensions = 0; datasetName = "NOT_SET"; infoText = ""; //Clear any previous data clear(); //Parse the CSV file FileParser parser; if( !parser.parseCSVFile(filename,true) ){ errorLog << "loadDatasetFromCSVFile(const string &filename) - Failed to parse CSV file!" << endl; return false; } if( !parser.getConsistentColumnSize() ){ errorLog << "loadDatasetFromCSVFile(const string &filename) - The CSV file does not have a consistent number of columns!" << endl; return false; } if( parser.getColumnSize() <= 2 ){ errorLog << "loadDatasetFromCSVFile(const string &filename) - The CSV file does not have enough columns! It should contain at least three columns!" << endl; return false; } //Set the number of dimensions numDimensions = parser.getColumnSize()-2; //Reserve the memory for the data data.reserve( parser.getRowSize() ); UINT sampleCounter = 0; UINT lastSampleCounter = 0; UINT classLabel = 0; UINT j = 0; UINT n = 0; VectorDouble sample(numDimensions); MatrixDouble timeseries; for(UINT i=0; i<parser.getRowSize(); i++){ sampleCounter = Util::stringToInt( parser[i][0] ); //Check to see if a new timeseries has started, if so then add the previous time series as a sample and start recording the new time series if( sampleCounter != lastSampleCounter && i != 0 ){ //Add the labelled sample to the dataset if( !addSample(classLabel, timeseries) ){ warningLog << "loadDatasetFromCSVFile(const string &filename,const UINT classLabelColumnIndex) - Could not add sample " << i << " to the dataset!" << endl; } timeseries.clear(); } lastSampleCounter = sampleCounter; //Get the class label classLabel = Util::stringToInt( parser[i][1] ); //Get the sample data j=0; n=2; while( j != numDimensions ){ sample[j++] = Util::stringToDouble( parser[i][n] ); n++; } //Add the sample to the timeseries timeseries.push_back( sample ); } if ( timeseries.getSize() > 0 ) //Add the labelled sample to the dataset if( !addSample(classLabel, timeseries) ){ warningLog << "loadDatasetFromCSVFile(const string &filename,const UINT classLabelColumnIndex) - Could not add sample " << parser.getRowSize()-1 << " to the dataset!" << endl; } return true; }
int main(int argc, const char * argv[]){ //Load the training data TimeSeriesClassificationData trainingData; if( !trainingData.loadDatasetFromFile("HMMTrainingData.grt") ){ cout << "ERROR: Failed to load training data!\n"; return false; } //Remove 20% of the training data to use as test data TimeSeriesClassificationData testData = trainingData.partition( 80 ); //The input to the HMM must be a quantized discrete value //We therefore use a KMeansQuantizer to covert the N-dimensional continuous data into 1-dimensional discrete data const UINT NUM_SYMBOLS = 10; KMeansQuantizer quantizer( NUM_SYMBOLS ); //Train the quantizer using the training data if( !quantizer.train( trainingData ) ){ cout << "ERROR: Failed to train quantizer!\n"; return false; } //Quantize the training data TimeSeriesClassificationData quantizedTrainingData( 1 ); for(UINT i=0; i<trainingData.getNumSamples(); i++){ UINT classLabel = trainingData[i].getClassLabel(); MatrixDouble quantizedSample; for(UINT j=0; j<trainingData[i].getLength(); j++){ quantizer.quantize( trainingData[i].getData().getRowVector(j) ); quantizedSample.push_back( quantizer.getFeatureVector() ); } if( !quantizedTrainingData.addSample(classLabel, quantizedSample) ){ cout << "ERROR: Failed to quantize training data!\n"; return false; } } //Create a new HMM instance HMM hmm; //Set the number of states in each model hmm.setNumStates( 4 ); //Set the number of symbols in each model, this must match the number of symbols in the quantizer hmm.setNumSymbols( NUM_SYMBOLS ); //Set the HMM model type to LEFTRIGHT with a delta of 1 hmm.setModelType( HiddenMarkovModel::LEFTRIGHT ); hmm.setDelta( 1 ); //Set the training parameters hmm.setMinImprovement( 1.0e-5 ); hmm.setMaxNumIterations( 100 ); hmm.setNumRandomTrainingIterations( 20 ); //Train the HMM model if( !hmm.train( quantizedTrainingData ) ){ cout << "ERROR: Failed to train the HMM model!\n"; return false; } //Save the HMM model to a file if( !hmm.save( "HMMModel.grt" ) ){ cout << "ERROR: Failed to save the model to a file!\n"; return false; } //Load the HMM model from a file if( !hmm.load( "HMMModel.grt" ) ){ cout << "ERROR: Failed to load the model from a file!\n"; return false; } //Quantize the test data TimeSeriesClassificationData quantizedTestData( 1 ); for(UINT i=0; i<testData.getNumSamples(); i++){ UINT classLabel = testData[i].getClassLabel(); MatrixDouble quantizedSample; for(UINT j=0; j<testData[i].getLength(); j++){ quantizer.quantize( testData[i].getData().getRowVector(j) ); quantizedSample.push_back( quantizer.getFeatureVector() ); } if( !quantizedTestData.addSample(classLabel, quantizedSample) ){ cout << "ERROR: Failed to quantize training data!\n"; return false; } } //Compute the accuracy of the HMM models using the test data double numCorrect = 0; double numTests = 0; for(UINT i=0; i<quantizedTestData.getNumSamples(); i++){ UINT classLabel = quantizedTestData[i].getClassLabel(); hmm.predict( quantizedTestData[i].getData() ); if( classLabel == hmm.getPredictedClassLabel() ) numCorrect++; numTests++; VectorDouble classLikelihoods = hmm.getClassLikelihoods(); VectorDouble classDistances = hmm.getClassDistances(); cout << "ClassLabel: " << classLabel; cout << " PredictedClassLabel: " << hmm.getPredictedClassLabel(); cout << " MaxLikelihood: " << hmm.getMaximumLikelihood(); cout << " ClassLikelihoods: "; for(UINT k=0; k<classLikelihoods.size(); k++){ cout << classLikelihoods[k] << "\t"; } cout << "ClassDistances: "; for(UINT k=0; k<classDistances.size(); k++){ cout << classDistances[k] << "\t"; } cout << endl; } cout << "Test Accuracy: " << numCorrect/numTests*100.0 << endl; return true; }
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"; return EXIT_FAILURE; } //After you have called the spilt function you can then get the training and test sets for each fold for(UINT foldIndex=0; foldIndex<10; foldIndex++){ TimeSeriesClassificationData foldTrainingData = trainingData.getTrainingFoldData( foldIndex ); TimeSeriesClassificationData foldTestingData = trainingData.getTestFoldData( foldIndex ); } //If need you can clear any training data that you have recorded trainingData.clear(); return EXIT_SUCCESS; }
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"; exit(EXIT_FAILURE); } dtw.enableNullRejection(true); dtw.setNullRejectionCoeff(4); dtw.enableTrimTrainingData(true, 0.1, 90); //Save the DTW model to a file if( !dtw.saveModelToFile("processed\\DTWModel.txt") ){ cerr << "Failed to save the classifier model!\n"; exit(EXIT_FAILURE); } trainingData.clear(); return EXIT_SUCCESS; }
int main (int argc, const char * argv[]) { //Create an empty matrix double MatrixDouble matrix; //Resize the matrix matrix.resize( 100, 2 ); //Set all the values in the matrix to zero matrix.setAllValues( 0 ); //Loop over the data and set the values to random values UINT counter = 0; for(UINT i=0; i<matrix.getNumRows(); i++){ for(UINT j=0; j<matrix.getNumCols(); j++){ matrix[i][j] = counter++; } } //Add a new row at the very end of the matrix VectorDouble newRow(2); newRow[0] = 1000; newRow[1] = 2000; matrix.push_back( newRow ); //Print the values cout << "Matrix Data: \n"; for(UINT i=0; i<matrix.getNumRows(); i++){ for(UINT j=0; j<matrix.getNumCols(); j++){ cout << matrix[i][j] << "\t"; } cout << endl; } cout << endl; //Get the second row as a vector VectorDouble rowVector = matrix.getRowVector( 1 ); cout << "Row Vector Data: \n"; for(UINT i=0; i<rowVector.size(); i++){ cout << rowVector[i] << "\t"; } cout << endl; //Get the second column as a vector VectorDouble colVector = matrix.getColVector( 1 ); cout << "Column Vector Data: \n"; for(UINT i=0; i<colVector.size(); i++){ cout << colVector[i] << "\n"; } cout << endl; //Get the mean of each column VectorDouble mean = matrix.getMean(); cout << "Mean: \n"; for(UINT i=0; i<mean.size(); i++){ cout << mean[i] << "\n"; } cout << endl; //Get the Standard Deviation of each column VectorDouble stdDev = matrix.getStdDev(); cout << "StdDev: \n"; for(UINT i=0; i<stdDev.size(); i++){ cout << stdDev[i] << "\n"; } cout << endl; //Get the covariance matrix MatrixDouble cov = matrix.getCovarianceMatrix(); cout << "Covariance Matrix: \n"; for(UINT i=0; i<cov.getNumRows(); i++){ for(UINT j=0; j<cov.getNumCols(); j++){ cout << cov[i][j] << "\t"; } cout << endl; } cout << endl; vector< MinMax > ranges = matrix.getRanges(); cout << "Ranges: \n"; for(UINT i=0; i<ranges.size(); i++){ cout << "i: " << i << "\tMinValue: " << ranges[i].minValue << "\tMaxValue:" << ranges[i].maxValue << "\n"; } cout << endl; //Save the matrix data to a csv file matrix.save( "data.csv" ); //load the matrix data from a csv file matrix.load( "data.csv" ); return EXIT_SUCCESS; }