private static IList GetReplacementValues(ModifiableDataset modifiableDataset,
string variableName,
IRegressionModel model,
IEnumerable <int> rows,
IEnumerable <double> targetValues,
out IList originalValues,
ReplacementMethodEnum replacementMethod = ReplacementMethodEnum.Shuffle,
FactorReplacementMethodEnum factorReplacementMethod = FactorReplacementMethodEnum.Best)
{
IList replacementValues = null;
if (modifiableDataset.VariableHasType <double>(variableName))
{
originalValues = modifiableDataset.GetReadOnlyDoubleValues(variableName).ToList();
replacementValues = GetReplacementValuesForDouble(modifiableDataset, rows, (List <double>)originalValues, replacementMethod);
}
else if (modifiableDataset.VariableHasType <string>(variableName))
{
originalValues = modifiableDataset.GetReadOnlyStringValues(variableName).ToList();
replacementValues = GetReplacementValuesForString(model, modifiableDataset, variableName, rows, (List <string>)originalValues, targetValues, factorReplacementMethod);
}
else
{
throw new NotSupportedException("Variable not supported");
}
return(replacementValues);
}
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);
// prepare a complete column for the dataset
replacementValues = Enumerable.Repeat(double.NaN, dataset.Rows).ToList();
// shuffle only the selected rows
var shuffledValues = rows.Select(r => originalValues[r]).Shuffle(rand).ToList();
int i = 0;
// update column values
foreach (var r in rows)
{
replacementValues[r] = shuffledValues[i++];
}
break;
case ReplacementMethodEnum.Noise:
var avg = rows.Select(r => originalValues[r]).Average();
var stdDev = rows.Select(r => originalValues[r]).StandardDeviation();
rand = new FastRandom(31415);
// prepare a complete column for the dataset
replacementValues = Enumerable.Repeat(double.NaN, dataset.Rows).ToList();
// update column values
foreach (var r in rows)
{
replacementValues[r] = NormalDistributedRandom.NextDouble(rand, avg, stdDev);
}
break;
default:
throw new ArgumentException(string.Format("ReplacementMethod {0} cannot be handled.", replacement));
}
return(EvaluateModelWithReplacedVariable(model, variable, dataset, rows, replacementValues));
}
private static IEnumerable <double> EvaluateModelWithReplacedVariable(IRegressionModel model, string variable,
ModifiableDataset dataset, IEnumerable <int> rows, IEnumerable <double> replacementValues)
{
var originalValues = dataset.GetReadOnlyDoubleValues(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 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);
}