private static double CalculateQualityForReplacement(
IClassificationModel model,
ModifiableDataset modifiableDataset,
string variableName,
IList originalValues,
IEnumerable <int> rows,
IList replacementValues,
IEnumerable <double> targetValues)
{
modifiableDataset.ReplaceVariable(variableName, replacementValues);
var discModel = model as IDiscriminantFunctionClassificationModel;
if (discModel != null)
{
var problemData = new ClassificationProblemData(modifiableDataset, modifiableDataset.VariableNames, model.TargetVariable);
discModel.RecalculateModelParameters(problemData, rows);
}
//mkommend: ToList is used on purpose to avoid lazy evaluation that could result in wrong estimates due to variable replacements
var estimates = model.GetEstimatedClassValues(modifiableDataset, rows).ToList();
var ret = CalculateQuality(targetValues, estimates);
modifiableDataset.ReplaceVariable(variableName, originalValues);
return(ret);
}
private static IEnumerable <double> EvaluateModelWithReplacedVariable(IRegressionModel model, string variable,
ModifiableDataset dataset, IEnumerable <int> rows, IEnumerable <string> replacementValues)
{
var originalValues = dataset.GetReadOnlyStringValues(variable).ToList();
dataset.ReplaceVariable(variable, replacementValues.ToList());
//mkommend: ToList is used on purpose to avoid lazy evaluation that could result in wrong estimates due to variable replacements
var estimates = model.GetEstimatedValues(dataset, rows).ToList();
dataset.ReplaceVariable(variable, originalValues);
return(estimates);
}
private static double CalculateQualityForReplacement(
IRegressionModel model,
ModifiableDataset modifiableDataset,
string variableName,
IList originalValues,
IEnumerable <int> rows,
IList replacementValues,
IEnumerable <double> targetValues)
{
modifiableDataset.ReplaceVariable(variableName, replacementValues);
//mkommend: ToList is used on purpose to avoid lazy evaluation that could result in wrong estimates due to variable replacements
var estimates = model.GetEstimatedValues(modifiableDataset, rows).ToList();
var ret = CalculateQuality(targetValues, estimates);
modifiableDataset.ReplaceVariable(variableName, originalValues);
return(ret);
}
private static IEnumerable <double> EvaluateModelWithReplacedVariable(IRegressionModel model, string variable, ModifiableDataset dataset, IEnumerable <int> rows, ReplacementMethodEnum replacement = ReplacementMethodEnum.Median)
{
var originalValues = dataset.GetReadOnlyDoubleValues(variable).ToList();
double replacementValue;
List <double> replacementValues;
IRandom rand;
switch (replacement)
{
case ReplacementMethodEnum.Median:
replacementValue = rows.Select(r => originalValues[r]).Median();
replacementValues = Enumerable.Repeat(replacementValue, dataset.Rows).ToList();
break;
case ReplacementMethodEnum.Average:
replacementValue = rows.Select(r => originalValues[r]).Average();
replacementValues = Enumerable.Repeat(replacementValue, dataset.Rows).ToList();
break;
case ReplacementMethodEnum.Shuffle:
// new var has same empirical distribution but the relation to y is broken
rand = new FastRandom(31415);
replacementValues = rows.Select(r => originalValues[r]).Shuffle(rand).ToList();
break;
case ReplacementMethodEnum.Noise:
var avg = rows.Select(r => originalValues[r]).Average();
var stdDev = rows.Select(r => originalValues[r]).StandardDeviation();
rand = new FastRandom(31415);
replacementValues = rows.Select(_ => NormalDistributedRandom.NextDouble(rand, avg, stdDev)).ToList();
break;
default:
throw new ArgumentException(string.Format("ReplacementMethod {0} cannot be handled.", replacement));
}
dataset.ReplaceVariable(variable, replacementValues);
//mkommend: ToList is used on purpose to avoid lazy evaluation that could result in wrong estimates due to variable replacements
var estimates = model.GetEstimatedValues(dataset, rows).ToList();
dataset.ReplaceVariable(variable, originalValues);
return(estimates);
}
