C# IDataset.GetDoubleValues方法代码示例

 public Scaling(IDataset ds, IEnumerable<string> variables, IEnumerable<int> rows) {
   foreach (var variable in variables) {
     var values = ds.GetDoubleValues(variable, rows);
     var min = values.Where(x => !double.IsNaN(x)).Min();
     var max = values.Where(x => !double.IsNaN(x)).Max();
     scalingParameters[variable] = Tuple.Create(min, max);
   }
 }

    public static double[,] PrepareInputMatrix(IDataset dataset, IEnumerable<string> variables, IEnumerable<int> rows) {
      List<string> variablesList = variables.ToList();
      List<int> rowsList = rows.ToList();

      double[,] matrix = new double[rowsList.Count, variablesList.Count];

      int col = 0;
      foreach (string column in variables) {
        var values = dataset.GetDoubleValues(column, rows);
        int row = 0;
        foreach (var value in values) {
          matrix[row, col] = value;
          row++;
        }
        col++;
      }

      return matrix;
    }

    public IEnumerable<IEnumerable<double>> GetSymbolicExpressionTreeValues(ISymbolicExpressionTree tree, IDataset dataset, IEnumerable<int> rows, IEnumerable<int> horizons) {
      if (CheckExpressionsWithIntervalArithmetic.Value)
        throw new NotSupportedException("Interval arithmetic is not yet supported in the symbolic data analysis interpreter.");
      if (targetVariableCache == null || targetVariableCache.GetLength(0) < dataset.Rows)
        targetVariableCache = dataset.GetDoubleValues(TargetVariable).ToArray();
      if (invalidateCacheIndexes == null)
        invalidateCacheIndexes = new List<int>(10);

      string targetVariable = TargetVariable;
      lock (EvaluatedSolutions) {
        EvaluatedSolutions.Value++; // increment the evaluated solutions counter
      }
      var state = PrepareInterpreterState(tree, dataset, targetVariableCache, TargetVariable);
      var rowsEnumerator = rows.GetEnumerator();
      var horizonsEnumerator = horizons.GetEnumerator();

      // produce a n-step forecast for all rows
      while (rowsEnumerator.MoveNext() & horizonsEnumerator.MoveNext()) {
        int row = rowsEnumerator.Current;
        int horizon = horizonsEnumerator.Current;
        double[] vProgs = new double[horizon];

        for (int i = 0; i < horizon; i++) {
          int localRow = i + row; // create a local variable for the ref parameter
          vProgs[i] = Evaluate(dataset, ref localRow, state);
          targetVariableCache[localRow] = vProgs[i];
          invalidateCacheIndexes.Add(localRow);
          state.Reset();
        }
        yield return vProgs;

        int j = 0;
        foreach (var targetValue in dataset.GetDoubleValues(targetVariable, invalidateCacheIndexes)) {
          targetVariableCache[invalidateCacheIndexes[j]] = targetValue;
          j++;
        }
        invalidateCacheIndexes.Clear();
      }

      if (rowsEnumerator.MoveNext() || horizonsEnumerator.MoveNext())
        throw new ArgumentException("Number of elements in rows and horizon enumerations doesn't match.");
    }

 // uses sorting to return the values in the order of rows, instead of using nested for loops
 // to avoid O(n²) runtime
 public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
   var values = dataset.GetDoubleValues(Variable, rows).ToArray();
   var rowsArray = rows.ToArray();
   var order = Enumerable.Range(0, rowsArray.Length).ToArray();
   double[] estimated = new double[rowsArray.Length];
   Array.Sort(rowsArray, order);
   Array.Sort(values, rowsArray);
   int curSplit = 0, curIndex = 0;
   while (curIndex < values.Length && Double.IsNaN(values[curIndex])) {
     estimated[curIndex] = MissingValuesClass;
     curIndex++;
   }
   while (curSplit < Splits.Length) {
     while (curIndex < values.Length && Splits[curSplit] > values[curIndex]) {
       estimated[curIndex] = classes[curSplit];
       curIndex++;
     }
     curSplit++;
   }
   Array.Sort(rowsArray, estimated);
   Array.Sort(order, estimated);
   return estimated;
 }

    private void CalculateModel(IDataset ds, IEnumerable<int> rows, bool scaleInputs = true) {
      this.trainingDataset = (IDataset)ds.Clone();
      this.trainingRows = rows.ToArray();
      this.inputScaling = scaleInputs ? new Scaling(ds, allowedInputVariables, rows) : null;

      x = GetData(ds, this.allowedInputVariables, this.trainingRows, this.inputScaling);

      IEnumerable<double> y;
      y = ds.GetDoubleValues(TargetVariable, rows);

      int n = x.GetLength(0);

      var columns = Enumerable.Range(0, x.GetLength(1)).ToArray();
      // calculate cholesky decomposed (lower triangular) covariance matrix
      var cov = covarianceFunction.GetParameterizedCovarianceFunction(covarianceParameter, columns);
      this.l = CalculateL(x, cov, sqrSigmaNoise);

      // calculate mean
      var mean = meanFunction.GetParameterizedMeanFunction(meanParameter, columns);
      double[] m = Enumerable.Range(0, x.GetLength(0))
        .Select(r => mean.Mean(x, r))
        .ToArray();

      // calculate sum of diagonal elements for likelihood
      double diagSum = Enumerable.Range(0, n).Select(i => Math.Log(l[i, i])).Sum();

      // solve for alpha
      double[] ym = y.Zip(m, (a, b) => a - b).ToArray();

      int info;
      alglib.densesolverreport denseSolveRep;

      alglib.spdmatrixcholeskysolve(l, n, false, ym, out info, out denseSolveRep, out alpha);
      for (int i = 0; i < alpha.Length; i++)
        alpha[i] = alpha[i] / sqrSigmaNoise;
      negativeLogLikelihood = 0.5 * Util.ScalarProd(ym, alpha) + diagSum + (n / 2.0) * Math.Log(2.0 * Math.PI * sqrSigmaNoise);

      // derivatives
      int nAllowedVariables = x.GetLength(1);

      alglib.matinvreport matInvRep;
      double[,] lCopy = new double[l.GetLength(0), l.GetLength(1)];
      Array.Copy(l, lCopy, lCopy.Length);

      alglib.spdmatrixcholeskyinverse(ref lCopy, n, false, out info, out matInvRep);
      if (info != 1) throw new ArgumentException("Can't invert matrix to calculate gradients.");
      for (int i = 0; i < n; i++) {
        for (int j = 0; j <= i; j++)
          lCopy[i, j] = lCopy[i, j] / sqrSigmaNoise - alpha[i] * alpha[j];
      }

      double noiseGradient = sqrSigmaNoise * Enumerable.Range(0, n).Select(i => lCopy[i, i]).Sum();

      double[] meanGradients = new double[meanFunction.GetNumberOfParameters(nAllowedVariables)];
      for (int k = 0; k < meanGradients.Length; k++) {
        var meanGrad = new double[alpha.Length];
        for (int g = 0; g < meanGrad.Length; g++)
          meanGrad[g] = mean.Gradient(x, g, k);
        meanGradients[k] = -Util.ScalarProd(meanGrad, alpha);
      }

      double[] covGradients = new double[covarianceFunction.GetNumberOfParameters(nAllowedVariables)];
      if (covGradients.Length > 0) {
        for (int i = 0; i < n; i++) {
          for (int j = 0; j < i; j++) {
            var g = cov.CovarianceGradient(x, i, j);
            for (int k = 0; k < covGradients.Length; k++) {
              covGradients[k] += lCopy[i, j] * g[k];
            }
          }

          var gDiag = cov.CovarianceGradient(x, i, i);
          for (int k = 0; k < covGradients.Length; k++) {
            // diag
            covGradients[k] += 0.5 * lCopy[i, i] * gDiag[k];
          }
        }
      }

      hyperparameterGradients =
        meanGradients
        .Concat(covGradients)
        .Concat(new double[] { noiseGradient }).ToArray();

    }

    public double[,] Reduce(IDataset dataset, IEnumerable<int> rows) {
      var data = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);

      var targets = dataset.GetDoubleValues(targetVariable, rows).ToArray();
      var result = new double[data.GetLength(0), transformationMatrix.GetLength(1) + 1];
      for (int i = 0; i < data.GetLength(0); i++)
        for (int j = 0; j < data.GetLength(1); j++) {
          for (int x = 0; x < transformationMatrix.GetLength(1); x++) {
            result[i, x] += data[i, j] * transformationMatrix[j, x];
          }
          result[i, transformationMatrix.GetLength(1)] = targets[i];
        }
      return result;
    }

 public IEnumerable<double> GetScaledValues(IDataset ds, string variable, IEnumerable<int> rows) {
   double min = scalingParameters[variable].Item1;
   double max = scalingParameters[variable].Item2;
   if (min.IsAlmost(max)) return rows.Select(i => 0.0); // return enumerable of zeros
   return ds.GetDoubleValues(variable, rows).Select(x => (x - min) / (max - min));  // scale to range [0..1]
 }

    private static double[,] PCAReduce(IDataset dataset, IEnumerable<int> rows, IEnumerable<string> variables) {
      var instances = rows.ToArray();
      var attributes = variables.ToArray();
      var data = new double[instances.Length, attributes.Length + 1];

      for (int j = 0; j < attributes.Length; j++) {
        int i = 0;
        var values = dataset.GetDoubleValues(attributes[j], instances);
        foreach (var v in values) {
          data[i++, j] = v;
        }
      }
      int info;
      double[] variances;
      var matrix = new double[0, 0];
      alglib.pcabuildbasis(data, instances.Length, attributes.Length, out info, out variances, out matrix);

      var result = new double[instances.Length, matrix.GetLength(1)];
      int r = 0;
      foreach (var inst in instances) {
        int i = 0;
        foreach (var attrib in attributes) {
          double val = dataset.GetDoubleValue(attrib, inst);
          for (int j = 0; j < result.GetLength(1); j++)
            result[r, j] += val * matrix[i, j];
          i++;
        }
        r++;
      }

      return result;
    }

    public static IEnumerable<string> CheckVariablesForPossibleTargetVariables(IDataset dataset) {
      int maxSamples = Math.Min(InspectedRowsToDetermineTargets, dataset.Rows);
      var validTargetVariables = (from v in dataset.DoubleVariables
                                  let distinctValues = dataset.GetDoubleValues(v)
                                    .Take(maxSamples)
                                    .Distinct()
                                    .Count()
                                  where distinctValues <= MaximumNumberOfClasses
                                  select v).ToArray();

      if (!validTargetVariables.Any())
        throw new ArgumentException("Import of classification problem data was not successful, because no target variable was found." +
          " A target variable must have at most " + MaximumNumberOfClasses + " distinct values to be applicable to classification.");
      return validTargetVariables;
    }