protected override OvaPredictor TrainCore(TrainContext trainContext)
{
var trainRoles = trainContext.TrainingSet;
trainRoles.CheckMultiClassLabel(out var numClasses);
var predictors = new IPredictorTransformer <TScalarPredictor> [numClasses];
for (int iClass = 0; iClass < numClasses; iClass++)
{
var data = new LabelIndicatorTransform(_env, trainRoles.Data, iClass, "Label");
predictors[iClass] = _binaryEstimator.Fit(data);
}
var prs = predictors.Select(x => x.InnerModel);
var finalPredictor = OvaPredictor.Create(_env.Register("ova"), prs.ToArray());
return(finalPredictor);
}
private void TestFeatureContribution(
ITrainerEstimator <ISingleFeaturePredictionTransformer <ICalculateFeatureContribution>, ICalculateFeatureContribution> trainer,
IDataView data,
string testFile,
int precision = 6)
{
// Train the model.
var model = trainer.Fit(data);
// Calculate feature contributions.
var est = ML.Transforms.CalculateFeatureContribution(model, numberOfPositiveContributions: 3, numberOfNegativeContributions: 0)
.Append(ML.Transforms.CalculateFeatureContribution(model, numberOfPositiveContributions: 0, numberOfNegativeContributions: 3))
.Append(ML.Transforms.CalculateFeatureContribution(model, numberOfPositiveContributions: 1, numberOfNegativeContributions: 1))
.Append(ML.Transforms.CalculateFeatureContribution(model, numberOfPositiveContributions: 1, numberOfNegativeContributions: 1, normalize: false));
TestEstimatorCore(est, data);
// Verify output.
CheckOutput(est, data, testFile, precision);
Done();
}
private void TestFeatureContribution(
ITrainerEstimator <ISingleFeaturePredictionTransformer <IPredictor>, IPredictor> trainer,
IDataView data,
string testFile,
int precision = 6)
{
// Train the model.
var model = trainer.Fit(data);
// Extract the predictor, check that it supports feature contribution.
var predictor = model.Model as ICalculateFeatureContribution;
Assert.NotNull(predictor);
// Calculate feature contributions.
var est = new FeatureContributionCalculatingEstimator(ML, predictor, "Features", numPositiveContributions: 3, numNegativeContributions: 0)
.Append(new FeatureContributionCalculatingEstimator(ML, predictor, "Features", numPositiveContributions: 0, numNegativeContributions: 3))
.Append(new FeatureContributionCalculatingEstimator(ML, predictor, "Features", numPositiveContributions: 1, numNegativeContributions: 1))
.Append(new FeatureContributionCalculatingEstimator(ML, predictor, "Features", numPositiveContributions: 1, numNegativeContributions: 1, normalize: false));
TestEstimatorCore(est, data);
// Verify output.
var outputPath = GetOutputPath("FeatureContribution", testFile + ".tsv");
using (var ch = Env.Start("save"))
{
var saver = new TextSaver(ML, new TextSaver.Arguments {
Silent = true, OutputHeader = false
});
IDataView savedData = TakeFilter.Create(ML, est.Fit(data).Transform(data), 4);
using (var fs = File.Create(outputPath))
DataSaverUtils.SaveDataView(ch, saver, savedData, fs, keepHidden: true);
}
CheckEquality("FeatureContribution", testFile + ".tsv", digitsOfPrecision: precision);
Done();
}
/// <summary>
/// Features: x1, x2, x3, xRand; y = 10*x1 + 20x2 + 5.5x3 + e, xRand- random, Label y is dependant on xRand.
/// Test verifies that feature contribution scores are outputted along with a score for predicted data.
/// </summary>
private void TestFeatureContribution(
ITrainerEstimator <ISingleFeaturePredictionTransformer <IPredictor>, IPredictor> trainer,
List <float[]> expectedValues,
int precision = 6)
{
// Setup synthetic dataset.
const int numInstances = 1000;
const int numFeatures = 4;
var rand = new Random(10);
float[] yArray = new float[numInstances];
float[][] xArray = new float[numFeatures][];
int[] xRangeArray = new[] { 1000, 10000, 5000, 1000 };
float[] xWeightArray = new[] {
10,
20, // Most important feature with high weight. Should have the highest contribution.
5.5f,
0, // Least important feature. Should have the least contribution.
};
for (var instanceIndex = 0; instanceIndex < numInstances; instanceIndex++)
{
for (int featureIndex = 0; featureIndex < numFeatures; featureIndex++)
{
if (xArray[featureIndex] == null)
{
xArray[featureIndex] = new float[numInstances];
}
xArray[featureIndex][instanceIndex] = rand.Next(xRangeArray[featureIndex]);
yArray[instanceIndex] += xArray[featureIndex][instanceIndex] * xWeightArray[featureIndex];
}
var noise = rand.Next(50);
yArray[instanceIndex] += noise;
}
// Create data view.
var bldr = new ArrayDataViewBuilder(Env);
bldr.AddColumn("X1", NumberType.Float, xArray[0]);
bldr.AddColumn("X2Important", NumberType.Float, xArray[1]);
bldr.AddColumn("X3", NumberType.Float, xArray[2]);
bldr.AddColumn("X4Rand", NumberType.Float, xArray[3]);
bldr.AddColumn("Label", NumberType.Float, yArray);
var srcDV = bldr.GetDataView();
var pipeline = ML.Transforms.Concatenate("Features", "X1", "X2Important", "X3", "X4Rand")
.AppendCacheCheckpoint(ML)
.Append(ML.Transforms.Normalize("Features"));
var data = pipeline.Fit(srcDV).Transform(srcDV);
var model = trainer.Fit(data);
var args = new FeatureContributionCalculationTransform.Arguments()
{
Bottom = 10,
Top = 10
};
var output = FeatureContributionCalculationTransform.Create(Env, args, data, model.Model, model.FeatureColumn);
var transformedOutput = output.AsEnumerable <ScoreAndContribution>(Env, true);
int rowIndex = 0;
foreach (var row in transformedOutput.Take(expectedValues.Count))
{
var expectedValue = expectedValues[rowIndex++];
for (int i = 0; i < numFeatures; i++)
{
Assert.Equal(expectedValue[i], row.FeatureContributions[i], precision);
}
}
Done();
}
