private void UpdateVariableImpacts()
{
if (Content == null || replacementComboBox.SelectedIndex < 0 ||
factorVarReplComboBox.SelectedIndex < 0 ||
dataPartitionComboBox.SelectedIndex < 0)
{
return;
}
var mainForm = (MainForm.WindowsForms.MainForm)MainFormManager.MainForm;
variableImactsArrayView.Caption = Content.Name + " Variable Impacts";
var replMethod =
(RegressionSolutionVariableImpactsCalculator.ReplacementMethodEnum)
replacementComboBox.Items[replacementComboBox.SelectedIndex];
var factorReplMethod =
(RegressionSolutionVariableImpactsCalculator.FactorReplacementMethodEnum)
factorVarReplComboBox.Items[factorVarReplComboBox.SelectedIndex];
var dataPartition =
(RegressionSolutionVariableImpactsCalculator.DataPartitionEnum)dataPartitionComboBox.SelectedItem;
Task.Factory.StartNew(() => {
try {
mainForm.AddOperationProgressToView(this, "Calculating variable impacts for " + Content.Name);
var impacts = RegressionSolutionVariableImpactsCalculator.CalculateImpacts(Content, dataPartition, replMethod, factorReplMethod);
var impactArray = new DoubleArray(impacts.Select(i => i.Item2).ToArray());
impactArray.ElementNames = impacts.Select(i => i.Item1);
variableImactsArrayView.Content = (DoubleArray)impactArray.AsReadOnly();
} finally {
mainForm.RemoveOperationProgressFromView(this);
}
});
}
public void WrongDataSetVariableImpactRegressionTest()
{
IRegressionProblemData problemData = LoadDefaultTowerProblem();
double rmsError;
double cvRmsError;
var solution = LinearRegression.CreateSolution(problemData, out rmsError, out cvRmsError);
solution.ProblemData = LoadDefaultMibaProblem();
RegressionSolutionVariableImpactsCalculator.CalculateImpacts(solution);
}
private void CheckDefaultAsserts(IRegressionSolution solution, Dictionary <string, double> expectedImpacts)
{
IRegressionProblemData problemData = solution.ProblemData;
IEnumerable <double> estimatedValues = solution.GetEstimatedValues(solution.ProblemData.TrainingIndices);
var solutionImpacts = RegressionSolutionVariableImpactsCalculator.CalculateImpacts(solution);
var modelImpacts = RegressionSolutionVariableImpactsCalculator.CalculateImpacts(solution.Model, problemData, estimatedValues, problemData.TrainingIndices);
//Both ways should return equal results
Assert.IsTrue(solutionImpacts.SequenceEqual(modelImpacts));
//Check if impacts are as expected
Assert.AreEqual(modelImpacts.Count(), expectedImpacts.Count);
Assert.IsTrue(modelImpacts.All(v => v.Item2.IsAlmost(expectedImpacts[v.Item1])));
}
private List <Tuple <string, double> > CalculateVariableImpacts(List <string> originalVariableOrdering,
IRegressionModel model,
IRegressionProblemData problemData,
IEnumerable <double> estimatedValues,
RegressionSolutionVariableImpactsCalculator.DataPartitionEnum dataPartition,
RegressionSolutionVariableImpactsCalculator.ReplacementMethodEnum replMethod,
RegressionSolutionVariableImpactsCalculator.FactorReplacementMethodEnum factorReplMethod,
CancellationToken token,
IProgress progress)
{
List <Tuple <string, double> > impacts = new List <Tuple <string, double> >();
int count = originalVariableOrdering.Count;
int i = 0;
var modifiableDataset = ((Dataset)(problemData.Dataset).Clone()).ToModifiable();
IEnumerable <int> rows = RegressionSolutionVariableImpactsCalculator.GetPartitionRows(dataPartition, problemData);
//Calculate original quality-values (via calculator, default is R²)
IEnumerable <double> targetValuesPartition = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
IEnumerable <double> estimatedValuesPartition = Content.GetEstimatedValues(rows);
var originalCalculatorValue = RegressionSolutionVariableImpactsCalculator.CalculateQuality(targetValuesPartition, estimatedValuesPartition);
foreach (var variableName in originalVariableOrdering)
{
if (cancellationToken.Token.IsCancellationRequested)
{
return(null);
}
progress.ProgressValue = (double)++i / count;
progress.Message = string.Format("Calculating impact for variable {0} ({1} of {2})", variableName, i, count);
double impact = 0;
//If the variable isn't used for prediction, it has zero impact.
if (model.VariablesUsedForPrediction.Contains(variableName))
{
impact = RegressionSolutionVariableImpactsCalculator.CalculateImpact(variableName, model, problemData, modifiableDataset, rows, replMethod, factorReplMethod, targetValuesPartition, originalCalculatorValue);
}
impacts.Add(new Tuple <string, double>(variableName, impact));
}
return(impacts);
}
public void PerformanceVariableImpactRegressionTest()
{
int rows = 20000;
int columns = 77;
var dataSet = OnlineCalculatorPerformanceTest.CreateRandomDataset(new MersenneTwister(1234), rows, columns);
IRegressionProblemData problemData = new RegressionProblemData(dataSet, dataSet.VariableNames.Except("y".ToEnumerable()), "y");
double rmsError;
double cvRmsError;
var solution = LinearRegression.CreateSolution(problemData, out rmsError, out cvRmsError);
Stopwatch watch = new Stopwatch();
watch.Start();
var results = RegressionSolutionVariableImpactsCalculator.CalculateImpacts(solution);
watch.Stop();
TestContext.WriteLine("");
TestContext.WriteLine("Calculated cells per millisecond: {0}.", rows * columns / watch.ElapsedMilliseconds);
}
protected virtual void btnImpactCalculation_Click(object sender, EventArgs e)
{
var mainForm = (MainForm.WindowsForms.MainForm)MainFormManager.MainForm;
var view = new StringConvertibleArrayView();
view.Caption = Content.Name + " Variable Impacts";
view.Show();
Task.Factory.StartNew(() => {
try {
mainForm.AddOperationProgressToView(view, "Calculating variable impacts for " + Content.Name);
var impacts = RegressionSolutionVariableImpactsCalculator.CalculateImpacts(Content);
var impactArray = new DoubleArray(impacts.Select(i => i.Item2).ToArray());
impactArray.ElementNames = impacts.Select(i => i.Item1);
view.Content = (DoubleArray)impactArray.AsReadOnly();
}
finally {
mainForm.RemoveOperationProgressFromView(view);
}
});
}
