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);
}
public static double Calculate(IClassificationModel model, IClassificationProblemData problemData, IEnumerable<int> rows) {
var estimations = model.GetEstimatedClassValues(problemData.Dataset, rows).GetEnumerator();
if (!estimations.MoveNext()) return double.NaN;
var penalty = 0.0;
var count = 0;
foreach (var r in rows) {
var actualClass = problemData.Dataset.GetDoubleValue(problemData.TargetVariable, r);
penalty += problemData.GetClassificationPenalty(actualClass, estimations.Current);
estimations.MoveNext();
count++;
}
return penalty / count;
}
public static double Calculate(IClassificationModel model, IClassificationProblemData problemData, IEnumerable <int> rows)
{
var estimations = model.GetEstimatedClassValues(problemData.Dataset, rows).GetEnumerator();
if (!estimations.MoveNext())
{
return(double.NaN);
}
var penalty = 0.0;
var count = 0;
foreach (var r in rows)
{
var actualClass = problemData.Dataset.GetDoubleValue(problemData.TargetVariable, r);
penalty += problemData.GetClassificationPenalty(actualClass, estimations.Current);
estimations.MoveNext();
count++;
}
return(penalty / count);
}
public static double CalculateImpact(string variableName,
IClassificationModel model,
IClassificationProblemData problemData,
ModifiableDataset modifiableDataset,
IEnumerable <int> rows,
ReplacementMethodEnum replacementMethod = ReplacementMethodEnum.Shuffle,
FactorReplacementMethodEnum factorReplacementMethod = FactorReplacementMethodEnum.Best,
IEnumerable <double> targetValues = null,
double quality = double.NaN)
{
if (!model.VariablesUsedForPrediction.Contains(variableName))
{
return(0.0);
}
if (!problemData.Dataset.VariableNames.Contains(variableName))
{
throw new InvalidOperationException(string.Format("Can not calculate variable impact, because the model uses inputs missing in the dataset ({0})", variableName));
}
if (targetValues == null)
{
targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
}
if (quality == double.NaN)
{
quality = CalculateQuality(model.GetEstimatedClassValues(modifiableDataset, rows), targetValues);
}
IList originalValues = null;
IList replacementValues = GetReplacementValues(modifiableDataset, variableName, model, rows, targetValues, out originalValues, replacementMethod, factorReplacementMethod);
double newValue = CalculateQualityForReplacement(model, modifiableDataset, variableName, originalValues, rows, replacementValues, targetValues);
double impact = quality - newValue;
return(impact);
}
