public static IEnumerable <Tuple <string, double> > CalculateImpacts(IRegressionSolution solution,
DataPartitionEnum data = DataPartitionEnum.Training,
ReplacementMethodEnum replacement = ReplacementMethodEnum.Median)
{
var problemData = solution.ProblemData;
var dataset = problemData.Dataset;
IEnumerable <int> rows;
IEnumerable <double> targetValues;
double originalR2 = -1;
OnlineCalculatorError error;
switch (data)
{
case DataPartitionEnum.All:
rows = solution.ProblemData.AllIndices;
targetValues = problemData.TargetVariableValues.ToList();
originalR2 = OnlinePearsonsRCalculator.Calculate(problemData.TargetVariableValues, solution.EstimatedValues, out error);
if (error != OnlineCalculatorError.None)
{
throw new InvalidOperationException("Error during R² calculation.");
}
originalR2 = originalR2 * originalR2;
break;
case DataPartitionEnum.Training:
rows = problemData.TrainingIndices;
targetValues = problemData.TargetVariableTrainingValues.ToList();
originalR2 = solution.TrainingRSquared;
break;
case DataPartitionEnum.Test:
rows = problemData.TestIndices;
targetValues = problemData.TargetVariableTestValues.ToList();
originalR2 = solution.TestRSquared;
break;
default: throw new ArgumentException(string.Format("DataPartition {0} cannot be handled.", data));
}
var impacts = new Dictionary <string, double>();
var modifiableDataset = ((Dataset)dataset).ToModifiable();
foreach (var inputVariable in problemData.AllowedInputVariables)
{
var newEstimates = EvaluateModelWithReplacedVariable(solution.Model, inputVariable, modifiableDataset, rows, replacement);
var newR2 = OnlinePearsonsRCalculator.Calculate(targetValues, newEstimates, out error);
if (error != OnlineCalculatorError.None)
{
throw new InvalidOperationException("Error during R² calculation with replaced inputs.");
}
newR2 = newR2 * newR2;
var impact = originalR2 - newR2;
impacts[inputVariable] = impact;
}
return(impacts.OrderByDescending(i => i.Value).Select(i => Tuple.Create(i.Key, i.Value)));
}
public static IEnumerable <Tuple <string, double> > CalculateImpacts(
IRegressionSolution solution,
ReplacementMethodEnum replacementMethod = ReplacementMethodEnum.Shuffle,
FactorReplacementMethodEnum factorReplacementMethod = FactorReplacementMethodEnum.Best,
DataPartitionEnum dataPartition = DataPartitionEnum.Training)
{
IEnumerable <int> rows = GetPartitionRows(dataPartition, solution.ProblemData);
IEnumerable <double> estimatedValues = solution.GetEstimatedValues(rows);
return(CalculateImpacts(solution.Model, solution.ProblemData, estimatedValues, rows, replacementMethod, factorReplacementMethod));
}
public static IEnumerable <Tuple <string, double> > CalculateImpacts(
IClassificationSolution solution,
ReplacementMethodEnum replacementMethod = ReplacementMethodEnum.Shuffle,
FactorReplacementMethodEnum factorReplacementMethod = FactorReplacementMethodEnum.Best,
DataPartitionEnum dataPartition = DataPartitionEnum.Training)
{
IEnumerable <int> rows = GetPartitionRows(dataPartition, solution.ProblemData);
IEnumerable <double> estimatedClassValues = solution.GetEstimatedClassValues(rows);
var model = (IClassificationModel)solution.Model.Clone(); //mkommend: clone of model is necessary, because the thresholds for IDiscriminantClassificationModels are updated
return(CalculateImpacts(model, solution.ProblemData, estimatedClassValues, rows, replacementMethod, factorReplacementMethod));
}
public static IEnumerable <int> GetPartitionRows(DataPartitionEnum dataPartition, IRegressionProblemData problemData)
{
IEnumerable <int> rows;
switch (dataPartition)
{
case DataPartitionEnum.All:
rows = problemData.AllIndices;
break;
case DataPartitionEnum.Test:
rows = problemData.TestIndices;
break;
case DataPartitionEnum.Training:
rows = problemData.TrainingIndices;
break;
default:
throw new NotSupportedException("DataPartition not supported");
}
return(rows);
}
public static IEnumerable <Tuple <string, double> > CalculateImpacts(
IRegressionSolution solution,
DataPartitionEnum data = DataPartitionEnum.Training,
ReplacementMethodEnum replacementMethod = ReplacementMethodEnum.Median,
FactorReplacementMethodEnum factorReplacementMethod = FactorReplacementMethodEnum.Best)
{
var problemData = solution.ProblemData;
var dataset = problemData.Dataset;
IEnumerable <int> rows;
IEnumerable <double> targetValues;
double originalR2 = -1;
OnlineCalculatorError error;
switch (data)
{
case DataPartitionEnum.All:
rows = solution.ProblemData.AllIndices;
targetValues = problemData.TargetVariableValues.ToList();
originalR2 = OnlinePearsonsRCalculator.Calculate(problemData.TargetVariableValues, solution.EstimatedValues, out error);
if (error != OnlineCalculatorError.None)
{
throw new InvalidOperationException("Error during R² calculation.");
}
originalR2 = originalR2 * originalR2;
break;
case DataPartitionEnum.Training:
rows = problemData.TrainingIndices;
targetValues = problemData.TargetVariableTrainingValues.ToList();
originalR2 = solution.TrainingRSquared;
break;
case DataPartitionEnum.Test:
rows = problemData.TestIndices;
targetValues = problemData.TargetVariableTestValues.ToList();
originalR2 = solution.TestRSquared;
break;
default: throw new ArgumentException(string.Format("DataPartition {0} cannot be handled.", data));
}
var impacts = new Dictionary <string, double>();
var modifiableDataset = ((Dataset)dataset).ToModifiable();
var inputvariables = new HashSet <string>(problemData.AllowedInputVariables.Union(solution.Model.VariablesUsedForPrediction));
var allowedInputVariables = dataset.VariableNames.Where(v => inputvariables.Contains(v)).ToList();
// calculate impacts for double variables
foreach (var inputVariable in allowedInputVariables.Where(problemData.Dataset.VariableHasType <double>))
{
var newEstimates = EvaluateModelWithReplacedVariable(solution.Model, inputVariable, modifiableDataset, rows, replacementMethod);
var newR2 = OnlinePearsonsRCalculator.Calculate(targetValues, newEstimates, out error);
if (error != OnlineCalculatorError.None)
{
throw new InvalidOperationException("Error during R² calculation with replaced inputs.");
}
newR2 = newR2 * newR2;
var impact = originalR2 - newR2;
impacts[inputVariable] = impact;
}
// calculate impacts for string variables
foreach (var inputVariable in allowedInputVariables.Where(problemData.Dataset.VariableHasType <string>))
{
if (factorReplacementMethod == FactorReplacementMethodEnum.Best)
{
// try replacing with all possible values and find the best replacement value
var smallestImpact = double.PositiveInfinity;
foreach (var repl in problemData.Dataset.GetStringValues(inputVariable, rows).Distinct())
{
var newEstimates = EvaluateModelWithReplacedVariable(solution.Model, inputVariable, modifiableDataset, rows,
Enumerable.Repeat(repl, dataset.Rows));
var newR2 = OnlinePearsonsRCalculator.Calculate(targetValues, newEstimates, out error);
if (error != OnlineCalculatorError.None)
{
throw new InvalidOperationException("Error during R² calculation with replaced inputs.");
}
newR2 = newR2 * newR2;
var impact = originalR2 - newR2;
if (impact < smallestImpact)
{
smallestImpact = impact;
}
}
impacts[inputVariable] = smallestImpact;
}
else
{
// for replacement methods shuffle and mode
// calculate impacts for factor variables
var newEstimates = EvaluateModelWithReplacedVariable(solution.Model, inputVariable, modifiableDataset, rows,
factorReplacementMethod);
var newR2 = OnlinePearsonsRCalculator.Calculate(targetValues, newEstimates, out error);
if (error != OnlineCalculatorError.None)
{
throw new InvalidOperationException("Error during R² calculation with replaced inputs.");
}
newR2 = newR2 * newR2;
var impact = originalR2 - newR2;
impacts[inputVariable] = impact;
}
} // foreach
return(impacts.OrderByDescending(i => i.Value).Select(i => Tuple.Create(i.Key, i.Value)));
}
public static IEnumerable<Tuple<string, double>> CalculateImpacts(IRegressionSolution solution,
DataPartitionEnum data = DataPartitionEnum.Training,
ReplacementMethodEnum replacement = ReplacementMethodEnum.Median) {
var problemData = solution.ProblemData;
var dataset = problemData.Dataset;
IEnumerable<int> rows;
IEnumerable<double> targetValues;
double originalR2 = -1;
OnlineCalculatorError error;
switch (data) {
case DataPartitionEnum.All:
rows = solution.ProblemData.AllIndices;
targetValues = problemData.TargetVariableValues.ToList();
originalR2 = OnlinePearsonsRCalculator.Calculate(problemData.TargetVariableValues, solution.EstimatedValues, out error);
if (error != OnlineCalculatorError.None) throw new InvalidOperationException("Error during R² calculation.");
originalR2 = originalR2 * originalR2;
break;
case DataPartitionEnum.Training:
rows = problemData.TrainingIndices;
targetValues = problemData.TargetVariableTrainingValues.ToList();
originalR2 = solution.TrainingRSquared;
break;
case DataPartitionEnum.Test:
rows = problemData.TestIndices;
targetValues = problemData.TargetVariableTestValues.ToList();
originalR2 = solution.TestRSquared;
break;
default: throw new ArgumentException(string.Format("DataPartition {0} cannot be handled.", data));
}
var impacts = new Dictionary<string, double>();
var modifiableDataset = ((Dataset)dataset).ToModifiable();
foreach (var inputVariable in problemData.AllowedInputVariables) {
var newEstimates = EvaluateModelWithReplacedVariable(solution.Model, inputVariable, modifiableDataset, rows, replacement);
var newR2 = OnlinePearsonsRCalculator.Calculate(targetValues, newEstimates, out error);
if (error != OnlineCalculatorError.None) throw new InvalidOperationException("Error during R² calculation with replaced inputs.");
newR2 = newR2 * newR2;
var impact = originalR2 - newR2;
impacts[inputVariable] = impact;
}
return impacts.OrderByDescending(i => i.Value).Select(i => Tuple.Create(i.Key, i.Value));
}
