public void SharpLearning_Example()
{
// Load data
var(observations, targets) = DataSetUtilities.LoadWinequalityWhite();
// transform data for neural net
var transform = new MinMaxTransformer(0.0, 1.0);
transform.Transform(observations, observations);
var featureCount = observations.ColumnCount;
// define the neural net.
var net = new NeuralNet();
net.Add(new InputLayer(inputUnits: featureCount));
net.Add(new DenseLayer(32, Activation.Relu));
net.Add(new DenseLayer(32, Activation.Relu));
net.Add(new SquaredErrorRegressionLayer());
// using only 10 iteration to make the example run faster.
// using square error as error metric. This is only used for reporting progress.
var learner = new RegressionNeuralNetLearner(net, iterations: 10, loss: new SquareLoss(),
optimizerMethod: OptimizerMethod.Adam);
var cv = new RandomCrossValidation <double>(10, seed: 232);
var predictions = cv.CrossValidate(learner, observations, targets);
Trace.WriteLine(FormatErrorString(targets, predictions));
}
public void Hyper_Parameter_Tuning()
{
#region Read data
// Use StreamReader(filepath) when running from filesystem
var parser = new CsvParser(() => new StringReader(Resources.winequality_white));
var targetName = "quality";
// read feature matrix
var observations = parser.EnumerateRows(c => c != targetName)
.ToF64Matrix();
// read classification targets
var targets = parser.EnumerateRows(targetName)
.ToF64Vector();
#endregion
// metric to minimize
var metric = new MeanSquaredErrorRegressionMetric();
// Parameter ranges for the optimizer
var paramers = new ParameterBounds[]
{
new ParameterBounds(min: 1, max: 100, transform: Transform.Linear), // maximumTreeDepth
new ParameterBounds(min: 1, max: 16, transform: Transform.Linear), // minimumSplitSize
};
// create random search optimizer
var optimizer = new RandomSearchOptimizer(paramers, iterations: 30, runParallel: true);
// other availible optimizers
// GridSearchOptimizer
// GlobalizedBoundedNelderMeadOptimizer
// ParticleSwarmOptimizer
// BayesianOptimizer
// function to minimize
Func <double[], OptimizerResult> minimize = p =>
{
var cv = new RandomCrossValidation <double>(crossValidationFolds: 5, seed: 42);
var optlearner = new RegressionDecisionTreeLearner(maximumTreeDepth: (int)p[0], minimumSplitSize: (int)p[1]);
var predictions = cv.CrossValidate(optlearner, observations, targets);
var error = metric.Error(targets, predictions);
Trace.WriteLine("Error: " + error);
return(new OptimizerResult(p, error));
};
// run optimizer
var result = optimizer.OptimizeBest(minimize);
var bestParameters = result.ParameterSet;
Trace.WriteLine("Result: " + result.Error);
// create learner with found parameters
var learner = new RegressionDecisionTreeLearner(maximumTreeDepth: (int)bestParameters[0], minimumSplitSize: (int)bestParameters[1]);
// learn model with found parameters
var model = learner.Learn(observations, targets);
}
public void ClassificationModelSelectingEnsembleLearner_Constructor_EnsembleSelection_Null()
{
var learners = new IIndexedLearner <ProbabilityPrediction> [4];
var metric = new LogLossClassificationProbabilityMetric();
var ensembleStrategy = new MeanProbabilityClassificationEnsembleStrategy();
var crossValidation = new RandomCrossValidation <ProbabilityPrediction>(5);
var sut = new ClassificationModelSelectingEnsembleLearner(learners, crossValidation, ensembleStrategy, null);
}
public void ClassificationModelSelectingEnsembleLearner_Constructor_Learners_Null()
{
var metric = new LogLossClassificationProbabilityMetric();
var ensembleStrategy = new MeanProbabilityClassificationEnsembleStrategy();
var ensembleSelection = new ForwardSearchClassificationEnsembleSelection(metric, ensembleStrategy, 5, 1, true);
var crossValidation = new RandomCrossValidation <ProbabilityPrediction>(5);
var sut = new ClassificationModelSelectingEnsembleLearner(null, crossValidation, ensembleStrategy, ensembleSelection);
}
public void RegressionModelSelectingEnsembleLearner_Constructor_EnsembleSelection_Null()
{
var learners = new IIndexedLearner <double> [4];
var metric = new MeanSquaredErrorRegressionMetric();
var ensembleStrategy = new MeanRegressionEnsembleStrategy();
var crossValidation = new RandomCrossValidation <double>(5);
var sut = new RegressionModelSelectingEnsembleLearner(learners, crossValidation, ensembleStrategy, null);
}
public void RegressionModelSelectingEnsembleLearner_Constructor_Learners_Null()
{
var metric = new MeanSquaredErrorRegressionMetric();
var ensembleStrategy = new MeanRegressionEnsembleStrategy();
var ensembleSelection = new ForwardSearchRegressionEnsembleSelection(metric, ensembleStrategy, 5, 1, true);
var crossValidation = new RandomCrossValidation <double>(5);
var sut = new RegressionModelSelectingEnsembleLearner(null, crossValidation, ensembleStrategy, ensembleSelection);
}
double CrossValidate(int folds)
{
var(observations, targets) = DataSetUtilities.LoadDecisionTreeDataSet();
var sut = new RandomCrossValidation <double>(folds, 42);
var predictions = sut.CrossValidate(new RegressionDecisionTreeLearner(), observations, targets);
var metric = new MeanSquaredErrorRegressionMetric();
return(metric.Error(targets, predictions));
}
double CrossValidate(int folds)
{
var targetName = "T";
var parser = new CsvParser(() => new StringReader(Resources.DecisionTreeData));
var observations = parser.EnumerateRows(v => !v.Contains(targetName)).ToF64Matrix();
var targets = parser.EnumerateRows(targetName).ToF64Vector();
var sut = new RandomCrossValidation <double>(folds, 42);
var predictions = sut.CrossValidate(new RegressionDecisionTreeLearner(), observations, targets);
var metric = new MeanSquaredErrorRegressionMetric();
return(metric.Error(targets, predictions));
}
double CrossValidate_Provide_Indices(int folds)
{
var(observations, targets) = DataSetUtilities.LoadDecisionTreeDataSet();
var sut = new RandomCrossValidation <double>(folds, 42);
var rowsToCrossvalidate = targets.Length / 2;
var indices = Enumerable.Range(0, rowsToCrossvalidate).ToArray();
var predictions = new double[rowsToCrossvalidate];
sut.CrossValidate(new RegressionDecisionTreeLearner(), observations, targets, indices, predictions);
var metric = new MeanSquaredErrorRegressionMetric();
return(metric.Error(targets.Take(rowsToCrossvalidate).ToArray(), predictions));
}
double CrossValidate_Provide_Indices(int folds)
{
var targetName = "T";
var parser = new CsvParser(() => new StringReader(Resources.DecisionTreeData));
var observations = parser.EnumerateRows(v => !v.Contains(targetName)).ToF64Matrix();
var targets = parser.EnumerateRows(targetName).ToF64Vector();
var sut = new RandomCrossValidation <double>(folds, 42);
var rowsToCrossvalidate = targets.Length / 2;
var indices = Enumerable.Range(0, rowsToCrossvalidate).ToArray();
var predictions = new double[rowsToCrossvalidate];
sut.CrossValidate(new RegressionDecisionTreeLearner(), observations, targets, indices, predictions);
var metric = new MeanSquaredErrorRegressionMetric();
return(metric.Error(targets.Take(rowsToCrossvalidate).ToArray(), predictions));
}
public void CrossValidation_CrossValidate_ProbabilityPredictions()
{
#region Read data
// Use StreamReader(filepath) when running from filesystem
var parser = new CsvParser(() => new StringReader(Resources.winequality_white));
var targetName = "quality";
// read feature matrix (all columns different from the targetName)
var observations = parser.EnumerateRows(c => c != targetName)
.ToF64Matrix();
// read targets
var targets = parser.EnumerateRows(targetName)
.ToF64Vector();
#endregion
// creates cross validator, observations are shuffled randomly
var cv = new RandomCrossValidation <ProbabilityPrediction>(crossValidationFolds: 5, seed: 42);
// create learner
var learner = new ClassificationDecisionTreeLearner();
// cross-validated predictions
var cvPredictions = cv.CrossValidate(learner, observations, targets);
// metric for measuring model error
var metric = new LogLossClassificationProbabilityMetric();
// cross-validation provides an estimate on how the model will perform on unseen data
Trace.WriteLine("Cross-validation error: " + metric.Error(targets, cvPredictions));
// train and predict training set for comparison
var predictions = learner.Learn(observations, targets).PredictProbability(observations);
// The training set is NOT a good estimate of how well the model will perfrom on unseen data.
Trace.WriteLine("Training error: " + metric.Error(targets, predictions));
}
