public IPredictionModel BuildModel(
IDataFrame dataFrame,
int dependentFeatureIndex,
IModelBuilderParams additionalParams)
{
return BuildModel(dataFrame, dataFrame.ColumnNames[dependentFeatureIndex], additionalParams);
}
protected virtual void ValidateAdditionalParams(IModelBuilderParams additionalParams)
{
if (!(additionalParams is IKnnAdditionalParams))
{
throw new ArgumentException("Invalid parameters type!");
}
}
public IPredictionModel BuildModel(
IDataFrame dataFrame,
int dependentFeatureIndex,
IModelBuilderParams additionalParams)
{
return(BuildModel(dataFrame, dataFrame.ColumnNames[dependentFeatureIndex], additionalParams));
}
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);
}
public IPredictionModel BuildModel(
IDataFrame dataFrame,
string dependentFeatureName,
IModelBuilderParams additionalParams)
{
if (!(additionalParams is IDecisionTreeModelBuilderParams))
{
throw new ArgumentException("Invalid params passed for Decision Tree Model Builder!");
}
if (ShouldStopRecusrsiveBuilding(dataFrame, dependentFeatureName))
{
return BuildLeaf(dataFrame, dependentFeatureName);
}
var decisionTreeParams = (IDecisionTreeModelBuilderParams)additionalParams;
var useParallelProcessing = decisionTreeParams.ProcessSubtreesCreationInParallel;
var alreadyUsedAttributesInfo = new AlreadyUsedAttributesInfo();
//TODO: reduce the number of parameters - maybe some nicer DTO?
var node = this.BuildDecisionNode(dataFrame, dependentFeatureName, decisionTreeParams, alreadyUsedAttributesInfo, 0, useParallelProcessing);
return node;
}
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);
}
public IPredictionModel BuildModel(
IDataFrame dataFrame,
string dependentFeatureName,
IModelBuilderParams additionalParams)
{
if (!(additionalParams is IDecisionTreeModelBuilderParams))
{
throw new ArgumentException("Invalid params passed for Decision Tree Model Builder!");
}
if (ShouldStopRecusrsiveBuilding(dataFrame, dependentFeatureName))
{
return(BuildLeaf(dataFrame, dependentFeatureName));
}
var decisionTreeParams = (IDecisionTreeModelBuilderParams)additionalParams;
var useParallelProcessing = decisionTreeParams.ProcessSubtreesCreationInParallel;
var alreadyUsedAttributesInfo = new AlreadyUsedAttributesInfo();
//TODO: reduce the number of parameters - maybe some nicer DTO?
var node = this.BuildDecisionNode(dataFrame, dependentFeatureName, decisionTreeParams, alreadyUsedAttributesInfo, 0, useParallelProcessing);
return(node);
}
public override IPredictionModel BuildModel(IDataFrame dataFrame, string dependentFeatureName, IModelBuilderParams additionalParams)
{
ValidateAdditionalParams(additionalParams);
return(PerformBackwardsElimination(dataFrame, dependentFeatureName, additionalParams as IKnnAdditionalParams));
}
public IPredictionModel BuildModel(IDataFrame dataFrame, int dependentFeatureIndex, IModelBuilderParams additionalParams)
{
if (!(additionalParams is IRandomForestModelBuilderParams))
{
throw new ArgumentException("Invalid parameters passed to Random Forest Model builder!");
}
return(BuildModel(dataFrame, dataFrame.ColumnNames[dependentFeatureIndex], additionalParams));
}
public IPredictionModel BuildModel(IDataFrame dataFrame, string dependentFeatureName, IModelBuilderParams additionalParams)
{
if (!(additionalParams is IRandomForestModelBuilderParams))
{
throw new ArgumentException("Invalid parameters passed to Random Forest Model builder!");
}
var randomForestParams = additionalParams as IRandomForestModelBuilderParams;
var trees = new IDecisionTreeNode[randomForestParams.TreesCount];
var oobErrors = new double[randomForestParams.TreesCount];
var columnsCountToTake = featuresToUseCountCalculator(dataFrame.ColumnsCount - 1);
var featureColumns = dataFrame.ColumnNames.Except(new[] { dependentFeatureName }).ToList();
var randomizer = new Random();
var locker = new object();
Parallel.For(
0,
randomForestParams.TreesCount,
i =>
{
var localRandomizer = new Random(i.GetHashCode());
var randomlySelectedIndices =
Enumerable.Range(0, dataFrame.RowCount)
.Select(_ => localRandomizer.Next(0, dataFrame.RowCount))
.ToList();
var outOfBagIndices =
Enumerable.Range(0, dataFrame.RowCount).Except(randomlySelectedIndices).ToList();
var columnsToTake = new List <string>();
columnsToTake = featureColumns.Shuffle(localRandomizer).Take(columnsCountToTake).ToList();
columnsToTake.Add(dependentFeatureName);
var baggedTestData = dataFrame.Slice(randomlySelectedIndices, columnsToTake);
var oobTestData = dataFrame.Slice(outOfBagIndices, columnsToTake);
var oobExpected = oobTestData.GetColumnVector <TPredictionVal>(dependentFeatureName).Values;
var decisionTree = decisionTreeModelBuilder.BuildModel(
baggedTestData,
dependentFeatureName,
decisionTreeModelBuilderParamsFactory());
var prediction = decisionTreePredictor.Predict(oobTestData, decisionTree, dependentFeatureName);
//TODO: AAA !!! Later on add support for calculating variable importance!!!
var oobError = dataQualityMeasure.CalculateError(oobExpected, prediction);
trees[i] = decisionTree as IDecisionTreeNode;
oobErrors[i] = oobError;
});
return(new RandomForestModel(trees, oobErrors));
}
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));
}
public virtual IPredictionModel BuildModel(IDataFrame dataFrame, string dependentFeatureName, IModelBuilderParams additionalParams)
{
ValidateAdditionalParams(additionalParams);
var knnParams = (IKnnAdditionalParams)additionalParams;
Tuple <Matrix <double>, IList <TPredictionResult>, IList <string> > preparedData = PrepareTrainingData(dataFrame, dependentFeatureName);
return(new KnnPredictionModel <TPredictionResult>(preparedData.Item1, preparedData.Item2, preparedData.Item3, knnParams.KNeighbors, knnParams.UseWeightedDistances));
}
