int main (int argc, const char * argv[])
{
//We are going to use the Iris dataset, you can find more about the orginal dataset at: http://en.wikipedia.org/wiki/Iris_flower_data_set
//Create a new instance of LabelledClassificationData to hold the training data
LabelledClassificationData trainingData;
//Load the training dataset from a file, the file should be in the same directory as this program
if( !trainingData.loadDatasetFromFile("IrisData.txt") ){
cout << "Failed to load Iris data from file!\n";
return EXIT_FAILURE;
}
//Print some basic stats about the dataset we have loaded
trainingData.printStats();
//Partition the training dataset into a training dataset and test dataset
//We will use 60% of the data to train the algorithm and 40% of the data to test it
//The true parameter flags that we want to use stratified sampling, which means there
//should be an equal class distribution between the training and test datasets
LabelledClassificationData testData = trainingData.partition( 60, true );
//Setup the gesture recognition pipeline
GestureRecognitionPipeline pipeline;
//Add a KNN classification algorithm as the main classifier with a K value of 10
pipeline.setClassifier( KNN(10) );
//Train the KNN algorithm using the training dataset
if( !pipeline.train( trainingData ) ){
cout << "Failed to train the pipeline!\n";
return EXIT_FAILURE;
}
//Test the KNN model using the test dataset
if( !pipeline.test( testData ) ){
cout << "Failed to test the pipeline!\n";
return EXIT_FAILURE;
}
//Print some metrics about how successful the classification was
//Print the accuracy
cout << "The classification accuracy was: " << pipeline.getTestAccuracy() << "%\n" << endl;
//Print the precision for each class
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
UINT classLabel = pipeline.getClassLabels()[k];
double classPrecision = pipeline.getTestPrecision( classLabel );
cout << "The precision for class " << classLabel << " was " << classPrecision << endl;
}
cout << endl;
//Print the recall for each class
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
UINT classLabel = pipeline.getClassLabels()[k];
double classRecall = pipeline.getTestRecall( classLabel );
cout << "The recall for class " << classLabel << " was " << classRecall << endl;
}
cout << endl;
//Print the confusion matrix
Matrix< double > confusionMatrix = pipeline.getTestConfusionMatrix();
cout << "Confusion Matrix: \n";
for(UINT i=0; i<confusionMatrix.getNumRows(); i++){
for(UINT j=0; j<confusionMatrix.getNumCols(); j++){
cout << confusionMatrix[i][j] << "\t";
}
cout << endl;
}
cout << endl;
return EXIT_SUCCESS;
}
int main (int argc, const char * argv[])
{
//Create a new KNN classifier with a K value of 10
KNN knn(10);
knn.setNullRejectionCoeff( 10 );
knn.enableScaling( true );
knn.enableNullRejection( true );
//Train the classifier with some training data
LabelledClassificationData trainingData;
if( !trainingData.loadDatasetFromFile("KNNTrainingData.txt") ){
cout << "Failed to load training data!\n";
return EXIT_FAILURE;
}
//Use 20% of the training dataset to create a test dataset
LabelledClassificationData testData = trainingData.partition( 80 );
//Train the classifier
bool trainSuccess = knn.train( trainingData );
if( !trainSuccess ){
cout << "Failed to train classifier!\n";
return EXIT_FAILURE;
}
//Save the knn model to a file
bool saveSuccess = knn.saveModelToFile("KNNModel.txt");
if( !saveSuccess ){
cout << "Failed to save the classifier model!\n";
return EXIT_FAILURE;
}
//Load the knn model from a file
bool loadSuccess = knn.loadModelFromFile("KNNModel.txt");
if( !loadSuccess ){
cout << "Failed to load the classifier model!\n";
return EXIT_FAILURE;
}
//Use the test dataset to test the KNN model
double accuracy = 0;
for(UINT i=0; i<testData.getNumSamples(); i++){
//Get the i'th test sample
UINT classLabel = testData[i].getClassLabel();
vector< double > inputVector = testData[i].getSample();
//Perform a prediction using the classifier
bool predictSuccess = knn.predict( inputVector );
if( !predictSuccess ){
cout << "Failed to perform prediction for test sampel: " << i <<"\n";
return EXIT_FAILURE;
}
//Get the predicted class label
UINT predictedClassLabel = knn.getPredictedClassLabel();
vector< double > classLikelihoods = knn.getClassLikelihoods();
vector< double > classDistances = knn.getClassDistances();
//Update the accuracy
if( classLabel == predictedClassLabel ) accuracy++;
cout << "TestSample: " << i << " ClassLabel: " << classLabel << " PredictedClassLabel: " << predictedClassLabel << endl;
}
cout << "Test Accuracy: " << accuracy/double(testData.getNumSamples())*100.0 << "%" << endl;
return EXIT_SUCCESS;
}
int main (int argc, const char * argv[])
{
//Load some training data from a file
LabelledClassificationData trainingData;
if( !trainingData.loadDatasetFromFile("HelloWorldTrainingData.txt") ){
cout << "ERROR: Failed to load training data from file\n";
return EXIT_FAILURE;
}
cout << "Data Loaded\n";
//Print out some stats about the training data
trainingData.printStats();
//Partition the training data into a training dataset and a test dataset. 80 means that 80%
//of the data will be used for the training data and 20% will be returned as the test dataset
LabelledClassificationData testData = trainingData.partition(80);
//Create a new Gesture Recognition Pipeline using an Adaptive Naive Bayes Classifier
GestureRecognitionPipeline pipeline;
pipeline.setClassifier( ANBC() );
//Train the pipeline using the training data
if( !pipeline.train( trainingData ) ){
cout << "ERROR: Failed to train the pipeline!\n";
return EXIT_FAILURE;
}
//Test the pipeline using the test data
if( !pipeline.test( testData ) ){
cout << "ERROR: Failed to test the pipeline!\n";
return EXIT_FAILURE;
}
//Print some stats about the testing
cout << "Test Accuracy: " << pipeline.getTestAccuracy() << endl;
cout << "Precision: ";
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
UINT classLabel = pipeline.getClassLabels()[k];
cout << "\t" << pipeline.getTestPrecision(classLabel);
}cout << endl;
cout << "Recall: ";
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
UINT classLabel = pipeline.getClassLabels()[k];
cout << "\t" << pipeline.getTestRecall(classLabel);
}cout << endl;
cout << "FMeasure: ";
for(UINT k=0; k<pipeline.getNumClassesInModel(); k++){
UINT classLabel = pipeline.getClassLabels()[k];
cout << "\t" << pipeline.getTestFMeasure(classLabel);
}cout << endl;
Matrix< double > confusionMatrix = pipeline.getTestConfusionMatrix();
cout << "ConfusionMatrix: \n";
for(UINT i=0; i<confusionMatrix.getNumRows(); i++){
for(UINT j=0; j<confusionMatrix.getNumCols(); j++){
cout << confusionMatrix[i][j] << "\t";
}cout << endl;
}
return EXIT_SUCCESS;
}