public void Test_GetSubset_ByColumns_UsingColumnIndices()
{
// Given
var newDataTable = new DataTable
{
Columns =
{
new DataColumn("Col1", typeof(string)),
new DataColumn("Col3", typeof(string))
},
Rows =
{
new object[] { "a1.1", "b1.2" },
new object[] { "a2.1", "b2.2" },
new object[] { "a3.1", "b3.2" }
}
};
var expectedDataFrame = new DataFrame(newDataTable, new[] { 100, 101, 102, 103 });
// When
var actualDataFrame = _subject.GetSubsetByColumns(new[] { 0, 2 });
// Then
Assert.IsTrue(expectedDataFrame.Equals(actualDataFrame));
}
public IDecisionTreeLeaf BuildLeaf(IDataFrame finalData, string dependentFeatureName)
{
var vectorY = finalData.GetNumericColumnVector(dependentFeatureName);
var featureNames = finalData.ColumnNames.Except(new[] { dependentFeatureName }).ToList();
var subset = finalData.GetSubsetByColumns(featureNames);
var matrixX = finalData.GetSubsetByColumns(featureNames).GetAsMatrixWithIntercept();
Vector <double> fittedWeights = null;
try
{
fittedWeights = MultipleRegression.DirectMethod(matrixX, vectorY);
}
catch (Exception)
{
fittedWeights = regressionModelBuilder.BuildModel(matrixX, vectorY, regressionParams).Weights;
}
return(new RegressionAndModelLeaf(dependentFeatureName, fittedWeights, vectorY.Mean()));
}
public IDecisionTreeLeaf BuildLeaf(IDataFrame finalData, string dependentFeatureName)
{
var vectorY = finalData.GetNumericColumnVector(dependentFeatureName);
var featureNames = finalData.ColumnNames.Except(new[] { dependentFeatureName }).ToList();
var subset = finalData.GetSubsetByColumns(featureNames);
var matrixX = finalData.GetSubsetByColumns(featureNames).GetAsMatrixWithIntercept();
Vector<double> fittedWeights = null;
try
{
fittedWeights = MultipleRegression.DirectMethod(matrixX, vectorY);
}
catch (Exception)
{
fittedWeights = regressionModelBuilder.BuildModel(matrixX, vectorY, regressionParams).Weights;
}
return new RegressionAndModelLeaf(dependentFeatureName, fittedWeights, vectorY.Mean());
}
protected virtual Tuple <Matrix <double>, IList <TPredictionResult>, IList <string> > PrepareTrainingData(
IDataFrame dataFrame,
string dependentFeatureName)
{
var dataColumns = dataFrame.ColumnNames.Where(col => col != dependentFeatureName).ToList();
var trainingData = dataFrame.GetSubsetByColumns(dataColumns).GetAsMatrix();
IDataVector <TPredictionResult> expectedOutcomes = dataFrame.GetColumnVector <TPredictionResult>(dependentFeatureName);
return(new Tuple <Matrix <double>, IList <TPredictionResult>, IList <string> >(trainingData, expectedOutcomes, dataColumns));
}
public IPredictionModel BuildModel(IDataFrame dataFrame, string dependentFeatureName, IModelBuilderParams additionalParams)
{
if (!(additionalParams is ILinearRegressionParams))
{
throw new ArgumentException("Invalid parameters passed to Regularized Linear Regression model builder!");
}
var linearRegressionParams = additionalParams as ILinearRegressionParams;
var matrixX = dataFrame.GetSubsetByColumns(dataFrame.ColumnNames.Except(new[] { dependentFeatureName }).ToList()).GetAsMatrixWithIntercept();
var vectorY = dataFrame.GetNumericColumnVector(dependentFeatureName);
return BuildModel(matrixX, vectorY, linearRegressionParams);
}
/// <summary>
/// 提取被预测数据的非特征矩阵
/// </summary>
/// <param name="queryDataFrame">被预测数据</param>
/// <param name="knnModel">knn 预测模型</param>
/// <param name="dependentFeatureIdx">依赖特征索引</param>
/// <returns></returns>
protected virtual Matrix <double> ExtractQueryDataAsMatrix(IDataFrame queryDataFrame, IKnnPredictionModel <TPredictionResult> knnModel, int dependentFeatureIdx)
{
// 获取被预测模型的 特征列
var dependentFetureName = (dependentFeatureIdx < queryDataFrame.ColumnsCount && dependentFeatureIdx >= 0)
? queryDataFrame.ColumnNames[dependentFeatureIdx]
: string.Empty;
// 获取被预测模型的子集（排除特征列）
var queryMatrix = queryDataFrame.GetSubsetByColumns(
queryDataFrame.ColumnNames.Where(colName => colName != dependentFetureName).ToList()).GetAsMatrix();
return(queryMatrix);
}
public IPredictionModel BuildModel(IDataFrame dataFrame, string dependentFeatureName, IModelBuilderParams additionalParams)
{
if (!(additionalParams is ILinearRegressionParams))
{
throw new ArgumentException("Invalid parameters passed to Gradient Desccent model builder!");
}
var linearRegressionParams = additionalParams as ILinearRegressionParams;
var matrixX = dataFrame.GetSubsetByColumns(dataFrame.ColumnNames.Except(new[] { dependentFeatureName }).ToList()).GetAsMatrixWithIntercept();
var vectorY = dataFrame.GetNumericColumnVector(dependentFeatureName);
return(BuildModel(matrixX, vectorY, linearRegressionParams));
}
protected override Tuple <Matrix <double>, Matrix <double> > NormalizeData(IDataFrame queryDataFrame, IKnnPredictionModel <TPredictionResult> knnModel, int dependentFeatureIdx)
{
var backwardsEliminationModel = knnModel as IBackwardsEliminationKnnModel <TPredictionResult>;
var featureIndicesToRemove = backwardsEliminationModel.RemovedFeaturesData.Select(f => queryDataFrame.ColumnNames.IndexOf(f.FeatureName)).OrderBy(i => i).ToList();
var relevantFeatures =
queryDataFrame.ColumnNames.Where((colName, colIdx) => !featureIndicesToRemove.Contains(colIdx) && colIdx != dependentFeatureIdx).ToList();
var modelMatrix = GetModelMatrixWithOnlyRelevantColumns(knnModel.TrainingData, featureIndicesToRemove);
var queryDataFrameWithoutRedundantColumns = queryDataFrame.GetSubsetByColumns(relevantFeatures).GetAsMatrix();
return(base.PerformNormalization(modelMatrix, queryDataFrameWithoutRedundantColumns));
}
public IList<double> Predict(IDataFrame queryDataFrame, IPredictionModel model, string dependentFeatureName)
{
if (!(model is ILinearRegressionModel))
{
throw new ArgumentException("Invalid model passed to Linear Regression predictor!");
}
var linearRegressionModel = model as ILinearRegressionModel;
var xMatrix = queryDataFrame.GetSubsetByColumns(
queryDataFrame.ColumnNames.Except(new[] { dependentFeatureName }).ToList())
.GetAsMatrixWithIntercept();
var results = new List<double>();
for (int rowIdx = 0; rowIdx < xMatrix.RowCount; rowIdx++)
{
var queryRow = xMatrix.Row(rowIdx);
var result = linearRegressionModel.Weights.DotProduct(queryRow);
results.Add(result);
}
return results;
}
public IList <TDecisionValue> Predict(IDataFrame queryDataFrame, IPredictionModel model, string dependentFeatureName)
{
if (!(model is IDecisionTreeNode))
{
throw new ArgumentException("Invalid model passed to Decision Tree Predictor");
}
var results = new ConcurrentBag <Tuple <int, TDecisionValue> >();
var queryDataFrameWithoutDependentFeature =
queryDataFrame.GetSubsetByColumns(
queryDataFrame.ColumnNames.Except(new[] { dependentFeatureName }).ToList());
for (int rowIdx = 0; rowIdx < queryDataFrameWithoutDependentFeature.RowCount; rowIdx++)
{
IDataVector <TDecisionValue> dataVector = queryDataFrameWithoutDependentFeature.GetRowVector <TDecisionValue>(rowIdx);
Tuple <TDecisionValue, double> predictionResults = ProcessInstance(dataVector, (IDecisionTreeNode)model, 1.0);
results.Add(new Tuple <int, TDecisionValue>(rowIdx, predictionResults.Item1));
}
return(results.OrderBy(tpl => tpl.Item1).Select(tpl => tpl.Item2).ToList());
}
public IList <double> Predict(IDataFrame queryDataFrame, IPredictionModel model, string dependentFeatureName)
{
if (!(model is ILinearRegressionModel))
{
throw new ArgumentException("Invalid model passed to Linear Regression predictor!");
}
var linearRegressionModel = model as ILinearRegressionModel;
var xMatrix = queryDataFrame.GetSubsetByColumns(
queryDataFrame.ColumnNames.Except(new[] { dependentFeatureName }).ToList())
.GetAsMatrixWithIntercept();
var results = new List <double>();
for (int rowIdx = 0; rowIdx < xMatrix.RowCount; rowIdx++)
{
var queryRow = xMatrix.Row(rowIdx);
var result = linearRegressionModel.Weights.DotProduct(queryRow);
results.Add(result);
}
return(results);
}
