public void Test_GetSubset_ByRows_UsingRowIndices()
{
// Given
var newDataTable = new DataTable
{
Columns =
{
new DataColumn("Col1", typeof(string)),
new DataColumn("Col2", typeof(int)),
new DataColumn("Col3", typeof(string)),
new DataColumn("Col4", typeof(int))
},
Rows =
{
new object[] { "a1.1", 1, "b1.2", 2 },
new object[] { "a3.1", 5, "b3.2", 6 }
}
};
var expectedDataFrame = new DataFrame(newDataTable, new[] { 100, 102 });
// When
var actualDataFrame = _subject.GetSubsetByRows(new[] { 0, 2 });
// Then
Assert.IsTrue(expectedDataFrame.Equals(actualDataFrame));
}
public IList <IDataQualityReport <TPredictionResult> > CrossValidate(
IPredictionModelBuilder modelBuilder,
IModelBuilderParams modelBuilderParams,
IPredictor <TPredictionResult> predictor,
IDataQualityMeasure <TPredictionResult> qualityMeasure,
IDataFrame dataFrame,
string dependentFeatureName,
double percetnagOfTrainData,
int folds)
{
var trainingDataCount = (int)Math.Round(percetnagOfTrainData * dataFrame.RowCount);
var testDataCount = dataFrame.RowCount - trainingDataCount;
var shuffledAllIndices = dataFrame.RowIndices.Shuffle(_randomizer);
var maxWindowsCount = dataFrame.RowCount / testDataCount;
var iterationAccuracies = new List <IDataQualityReport <TPredictionResult> >();
var currentWindowNo = 0;
for (var i = 0; i < folds; i++)
{
if (currentWindowNo == maxWindowsCount)
{
currentWindowNo = 0;
shuffledAllIndices = shuffledAllIndices.Shuffle();
}
var offset = currentWindowNo * testDataCount;
var trainingIndices = shuffledAllIndices.Skip(offset).Take(trainingDataCount).ToList();
var trainingData = dataFrame.GetSubsetByRows(trainingIndices);
var testIndices = shuffledAllIndices.Except(trainingIndices).ToList();
var testData = dataFrame.GetSubsetByRows(testIndices);
IPredictionModel model = modelBuilder.BuildModel(trainingData, dependentFeatureName, modelBuilderParams);
IList <TPredictionResult> predictions = predictor.Predict(testData, model, dependentFeatureName);
IList <TPredictionResult> expected = testData.GetColumnVector <TPredictionResult>(dependentFeatureName);
IDataQualityReport <TPredictionResult> qualityReport = qualityMeasure.GetReport(expected, predictions);
iterationAccuracies.Add(qualityReport);
currentWindowNo++;
}
return(iterationAccuracies);
}