/// <summary>
/// Makes a PCA (a principal component analysis) of the table or the selected columns / rows and stores the results in a newly created table.
/// </summary>
/// <param name="mainDocument">The main document of the application.</param>
/// <param name="srctable">The table where the data come from.</param>
/// <param name="selectedColumns">The selected columns.</param>
/// <param name="selectedRows">The selected rows.</param>
/// <param name="bHorizontalOrientedSpectrum">True if a spectrum is a single row, False if a spectrum is a single column.</param>
/// <param name="maxNumberOfFactors">The maximum number of factors to calculate.</param>
/// <returns></returns>
public static string PrincipalComponentAnalysis(
Altaxo.AltaxoDocument mainDocument,
Altaxo.Data.DataTable srctable,
IAscendingIntegerCollection selectedColumns,
IAscendingIntegerCollection selectedRows,
bool bHorizontalOrientedSpectrum,
int maxNumberOfFactors
)
{
bool bUseSelectedColumns = (null != selectedColumns && 0 != selectedColumns.Count);
int prenumcols = bUseSelectedColumns ? selectedColumns.Count : srctable.DataColumns.ColumnCount;
// check for the number of numeric columns
int numcols = 0;
for (int i = 0; i < prenumcols; i++)
{
int idx = bUseSelectedColumns ? selectedColumns[i] : i;
if (srctable[i] is Altaxo.Data.INumericColumn)
{
numcols++;
}
}
// check the number of rows
bool bUseSelectedRows = (null != selectedRows && 0 != selectedRows.Count);
int numrows;
if (bUseSelectedRows)
{
numrows = selectedRows.Count;
}
else
{
numrows = 0;
for (int i = 0; i < numcols; i++)
{
int idx = bUseSelectedColumns ? selectedColumns[i] : i;
numrows = Math.Max(numrows, srctable[idx].Count);
}
}
// check that both dimensions are at least 2 - otherwise PCA is not possible
if (numrows < 2)
{
return("At least two rows are neccessary to do Principal Component Analysis!");
}
if (numcols < 2)
{
return("At least two numeric columns are neccessary to do Principal Component Analysis!");
}
// Create a matrix of appropriate dimensions and fill it
MatrixMath.BEMatrix matrixX;
if (bHorizontalOrientedSpectrum)
{
matrixX = new MatrixMath.BEMatrix(numrows, numcols);
int ccol = 0; // current column in the matrix
for (int i = 0; i < prenumcols; i++)
{
int colidx = bUseSelectedColumns ? selectedColumns[i] : i;
Altaxo.Data.INumericColumn col = srctable[colidx] as Altaxo.Data.INumericColumn;
if (null != col)
{
for (int j = 0; j < numrows; j++)
{
int rowidx = bUseSelectedRows ? selectedRows[j] : j;
matrixX[j, ccol] = col[rowidx];
}
++ccol;
}
}
} // end if it was a horizontal oriented spectrum
else // if it is a vertical oriented spectrum
{
matrixX = new MatrixMath.BEMatrix(numcols, numrows);
int ccol = 0; // current column in the matrix
for (int i = 0; i < prenumcols; i++)
{
int colidx = bUseSelectedColumns ? selectedColumns[i] : i;
Altaxo.Data.INumericColumn col = srctable[colidx] as Altaxo.Data.INumericColumn;
if (null != col)
{
for (int j = 0; j < numrows; j++)
{
int rowidx = bUseSelectedRows ? selectedRows[j] : j;
matrixX[ccol, j] = col[rowidx];
}
++ccol;
}
}
} // if it was a vertical oriented spectrum
// now do PCA with the matrix
MatrixMath.REMatrix factors = new MatrixMath.REMatrix(0, 0);
MatrixMath.BEMatrix loads = new MatrixMath.BEMatrix(0, 0);
MatrixMath.BEMatrix residualVariances = new MatrixMath.BEMatrix(0, 0);
MatrixMath.HorizontalVector meanX = new MatrixMath.HorizontalVector(matrixX.Columns);
// first, center the matrix
MatrixMath.ColumnsToZeroMean(matrixX, meanX);
MatrixMath.NIPALS_HO(matrixX, maxNumberOfFactors, 1E-9, factors, loads, residualVariances);
// now we have to create a new table where to place the calculated factors and loads
// we will do that in a vertical oriented manner, i.e. even if the loads are
// here in horizontal vectors: in our table they are stored in (vertical) columns
Altaxo.Data.DataTable table = new Altaxo.Data.DataTable("PCA of " + srctable.Name);
// Fill the Table
table.Suspend();
// first of all store the meanscore
{
double meanScore = MatrixMath.LengthOf(meanX);
MatrixMath.NormalizeRows(meanX);
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for (int i = 0; i < factors.Rows; i++)
{
col[i] = meanScore;
}
table.DataColumns.Add(col, "MeanFactor", Altaxo.Data.ColumnKind.V, 0);
}
// first store the factors
for (int i = 0; i < factors.Columns; i++)
{
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for (int j = 0; j < factors.Rows; j++)
{
col[j] = factors[j, i];
}
table.DataColumns.Add(col, "Factor" + i.ToString(), Altaxo.Data.ColumnKind.V, 1);
}
// now store the mean of the matrix
{
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for (int j = 0; j < meanX.Columns; j++)
{
col[j] = meanX[0, j];
}
table.DataColumns.Add(col, "MeanLoad", Altaxo.Data.ColumnKind.V, 2);
}
// now store the loads - careful - they are horizontal in the matrix
for (int i = 0; i < loads.Rows; i++)
{
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for (int j = 0; j < loads.Columns; j++)
{
col[j] = loads[i, j];
}
table.DataColumns.Add(col, "Load" + i.ToString(), Altaxo.Data.ColumnKind.V, 3);
}
// now store the residual variances, they are vertical in the vector
{
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for (int i = 0; i < residualVariances.Rows; i++)
{
col[i] = residualVariances[i, 0];
}
table.DataColumns.Add(col, "ResidualVariance", Altaxo.Data.ColumnKind.V, 4);
}
table.Resume();
mainDocument.DataTableCollection.Add(table);
// create a new worksheet without any columns
Current.ProjectService.CreateNewWorksheet(table);
return(null);
}
/// <summary>
/// Multiplies selected columns to form a matrix.
/// </summary>
/// <param name="mainDocument"></param>
/// <param name="srctable"></param>
/// <param name="selectedColumns"></param>
/// <returns>Null if successful, else the description of the error.</returns>
/// <remarks>The user must select an even number of columns. All columns of the first half of the selection
/// must have the same number of rows, and all columns of the second half of selection must also have the same
/// number of rows. The first half of selected columns form a matrix of dimensions(firstrowcount,halfselected), and the second half
/// of selected columns form a matrix of dimension(halfselected, secondrowcount). The resulting matrix has dimensions (firstrowcount,secondrowcount) and is
/// stored in a separate worksheet.</remarks>
public static string MultiplyColumnsToMatrix(
Altaxo.AltaxoDocument mainDocument,
Altaxo.Data.DataTable srctable,
IAscendingIntegerCollection selectedColumns
)
{
// check that there are columns selected
if (0 == selectedColumns.Count)
{
return("You must select at least two columns to multiply!");
}
// selected columns must contain an even number of columns
if (0 != selectedColumns.Count % 2)
{
return("You selected an odd number of columns. Please select an even number of columns to multiply!");
}
// all selected columns must be numeric columns
for (int i = 0; i < selectedColumns.Count; i++)
{
if (!(srctable[selectedColumns[i]] is Altaxo.Data.INumericColumn))
{
return(string.Format("The column[{0}] (name:{1}) is not a numeric column!", selectedColumns[i], srctable[selectedColumns[i]].Name));
}
}
int halfselect = selectedColumns.Count / 2;
// check that all columns from the first half of selected colums contain the same
// number of rows
int rowsfirsthalf = int.MinValue;
for (int i = 0; i < halfselect; i++)
{
int idx = selectedColumns[i];
if (rowsfirsthalf < 0)
{
rowsfirsthalf = srctable[idx].Count;
}
else if (rowsfirsthalf != srctable[idx].Count)
{
return("The first half of selected columns have not all the same length!");
}
}
int rowssecondhalf = int.MinValue;
for (int i = halfselect; i < selectedColumns.Count; i++)
{
int idx = selectedColumns[i];
if (rowssecondhalf < 0)
{
rowssecondhalf = srctable[idx].Count;
}
else if (rowssecondhalf != srctable[idx].Count)
{
return("The second half of selected columns have not all the same length!");
}
}
// now create the matrices to multiply from the
MatrixMath.REMatrix firstMat = new MatrixMath.REMatrix(rowsfirsthalf, halfselect);
for (int i = 0; i < halfselect; i++)
{
Altaxo.Data.INumericColumn col = (Altaxo.Data.INumericColumn)srctable[selectedColumns[i]];
for (int j = 0; j < rowsfirsthalf; j++)
{
firstMat[j, i] = col[j];
}
}
MatrixMath.BEMatrix secondMat = new MatrixMath.BEMatrix(halfselect, rowssecondhalf);
for (int i = 0; i < halfselect; i++)
{
Altaxo.Data.INumericColumn col = (Altaxo.Data.INumericColumn)srctable[selectedColumns[i + halfselect]];
for (int j = 0; j < rowssecondhalf; j++)
{
secondMat[i, j] = col[j];
}
}
// now multiply the two matrices
MatrixMath.BEMatrix resultMat = new MatrixMath.BEMatrix(rowsfirsthalf, rowssecondhalf);
MatrixMath.Multiply(firstMat, secondMat, resultMat);
// and store the result in a new worksheet
Altaxo.Data.DataTable table = new Altaxo.Data.DataTable("ResultMatrix of " + srctable.Name);
table.Suspend();
// first store the factors
for (int i = 0; i < resultMat.Columns; i++)
{
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for (int j = 0; j < resultMat.Rows; j++)
{
col[j] = resultMat[j, i];
}
table.DataColumns.Add(col, i.ToString());
}
table.Resume();
mainDocument.DataTableCollection.Add(table);
// create a new worksheet without any columns
Current.ProjectService.CreateNewWorksheet(table);
return(null);
}
/// <summary>
/// Multiplies selected columns to form a matrix.
/// </summary>
/// <param name="mainDocument"></param>
/// <param name="srctable"></param>
/// <param name="selectedColumns"></param>
/// <returns>Null if successful, else the description of the error.</returns>
/// <remarks>The user must select an even number of columns. All columns of the first half of the selection
/// must have the same number of rows, and all columns of the second half of selection must also have the same
/// number of rows. The first half of selected columns form a matrix of dimensions(firstrowcount,halfselected), and the second half
/// of selected columns form a matrix of dimension(halfselected, secondrowcount). The resulting matrix has dimensions (firstrowcount,secondrowcount) and is
/// stored in a separate worksheet.</remarks>
public static string MultiplyColumnsToMatrix(
Altaxo.AltaxoDocument mainDocument,
Altaxo.Data.DataTable srctable,
IAscendingIntegerCollection selectedColumns
)
{
// check that there are columns selected
if(0==selectedColumns.Count)
return "You must select at least two columns to multiply!";
// selected columns must contain an even number of columns
if(0!=selectedColumns.Count%2)
return "You selected an odd number of columns. Please select an even number of columns to multiply!";
// all selected columns must be numeric columns
for(int i=0;i<selectedColumns.Count;i++)
{
if(!(srctable[selectedColumns[i]] is Altaxo.Data.INumericColumn))
return string.Format("The column[{0}] (name:{1}) is not a numeric column!",selectedColumns[i],srctable[selectedColumns[i]].Name);
}
int halfselect = selectedColumns.Count/2;
// check that all columns from the first half of selected colums contain the same
// number of rows
int rowsfirsthalf=int.MinValue;
for(int i=0;i<halfselect;i++)
{
int idx = selectedColumns[i];
if(rowsfirsthalf<0)
rowsfirsthalf = srctable[idx].Count;
else if(rowsfirsthalf != srctable[idx].Count)
return "The first half of selected columns have not all the same length!";
}
int rowssecondhalf=int.MinValue;
for(int i=halfselect;i<selectedColumns.Count;i++)
{
int idx = selectedColumns[i];
if(rowssecondhalf<0)
rowssecondhalf = srctable[idx].Count;
else if(rowssecondhalf != srctable[idx].Count)
return "The second half of selected columns have not all the same length!";
}
// now create the matrices to multiply from the
MatrixMath.REMatrix firstMat = new MatrixMath.REMatrix(rowsfirsthalf,halfselect);
for(int i=0;i<halfselect;i++)
{
Altaxo.Data.INumericColumn col = (Altaxo.Data.INumericColumn)srctable[selectedColumns[i]];
for(int j=0;j<rowsfirsthalf;j++)
firstMat[j,i] = col[j];
}
MatrixMath.BEMatrix secondMat = new MatrixMath.BEMatrix(halfselect,rowssecondhalf);
for(int i=0;i<halfselect;i++)
{
Altaxo.Data.INumericColumn col = (Altaxo.Data.INumericColumn)srctable[selectedColumns[i+halfselect]];
for(int j=0;j<rowssecondhalf;j++)
secondMat[i,j] = col[j];
}
// now multiply the two matrices
MatrixMath.BEMatrix resultMat = new MatrixMath.BEMatrix(rowsfirsthalf,rowssecondhalf);
MatrixMath.Multiply(firstMat,secondMat,resultMat);
// and store the result in a new worksheet
Altaxo.Data.DataTable table = new Altaxo.Data.DataTable("ResultMatrix of " + srctable.Name);
table.Suspend();
// first store the factors
for(int i=0;i<resultMat.Columns;i++)
{
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for(int j=0;j<resultMat.Rows;j++)
col[j] = resultMat[j,i];
table.DataColumns.Add(col,i.ToString());
}
table.Resume();
mainDocument.DataTableCollection.Add(table);
// create a new worksheet without any columns
Current.ProjectService.CreateNewWorksheet(table);
return null;
}
/// <summary>
/// Makes a PCA (a principal component analysis) of the table or the selected columns / rows and stores the results in a newly created table.
/// </summary>
/// <param name="mainDocument">The main document of the application.</param>
/// <param name="srctable">The table where the data come from.</param>
/// <param name="selectedColumns">The selected columns.</param>
/// <param name="selectedRows">The selected rows.</param>
/// <param name="bHorizontalOrientedSpectrum">True if a spectrum is a single row, False if a spectrum is a single column.</param>
/// <param name="maxNumberOfFactors">The maximum number of factors to calculate.</param>
/// <returns></returns>
public static string PrincipalComponentAnalysis(
Altaxo.AltaxoDocument mainDocument,
Altaxo.Data.DataTable srctable,
IAscendingIntegerCollection selectedColumns,
IAscendingIntegerCollection selectedRows,
bool bHorizontalOrientedSpectrum,
int maxNumberOfFactors
)
{
bool bUseSelectedColumns = (null!=selectedColumns && 0!=selectedColumns.Count);
int prenumcols = bUseSelectedColumns ? selectedColumns.Count : srctable.DataColumns.ColumnCount;
// check for the number of numeric columns
int numcols = 0;
for(int i=0;i<prenumcols;i++)
{
int idx = bUseSelectedColumns ? selectedColumns[i] : i;
if(srctable[i] is Altaxo.Data.INumericColumn)
numcols++;
}
// check the number of rows
bool bUseSelectedRows = (null!=selectedRows && 0!=selectedRows.Count);
int numrows;
if(bUseSelectedRows)
numrows = selectedRows.Count;
else
{
numrows = 0;
for(int i=0;i<numcols;i++)
{
int idx = bUseSelectedColumns ? selectedColumns[i] : i;
numrows = Math.Max(numrows,srctable[idx].Count);
}
}
// check that both dimensions are at least 2 - otherwise PCA is not possible
if(numrows<2)
return "At least two rows are neccessary to do Principal Component Analysis!";
if(numcols<2)
return "At least two numeric columns are neccessary to do Principal Component Analysis!";
// Create a matrix of appropriate dimensions and fill it
MatrixMath.BEMatrix matrixX;
if(bHorizontalOrientedSpectrum)
{
matrixX = new MatrixMath.BEMatrix(numrows,numcols);
int ccol = 0; // current column in the matrix
for(int i=0;i<prenumcols;i++)
{
int colidx = bUseSelectedColumns ? selectedColumns[i] : i;
Altaxo.Data.INumericColumn col = srctable[colidx] as Altaxo.Data.INumericColumn;
if(null!=col)
{
for(int j=0;j<numrows;j++)
{
int rowidx = bUseSelectedRows ? selectedRows[j] : j;
matrixX[j,ccol] = col[rowidx];
}
++ccol;
}
}
} // end if it was a horizontal oriented spectrum
else // if it is a vertical oriented spectrum
{
matrixX = new MatrixMath.BEMatrix(numcols,numrows);
int ccol = 0; // current column in the matrix
for(int i=0;i<prenumcols;i++)
{
int colidx = bUseSelectedColumns ? selectedColumns[i] : i;
Altaxo.Data.INumericColumn col = srctable[colidx] as Altaxo.Data.INumericColumn;
if(null!=col)
{
for(int j=0;j<numrows;j++)
{
int rowidx = bUseSelectedRows ? selectedRows[j] : j;
matrixX[ccol,j] = col[rowidx];
}
++ccol;
}
}
} // if it was a vertical oriented spectrum
// now do PCA with the matrix
MatrixMath.REMatrix factors = new MatrixMath.REMatrix(0,0);
MatrixMath.BEMatrix loads = new MatrixMath.BEMatrix(0,0);
MatrixMath.BEMatrix residualVariances = new MatrixMath.BEMatrix(0,0);
MatrixMath.HorizontalVector meanX = new MatrixMath.HorizontalVector(matrixX.Columns);
// first, center the matrix
MatrixMath.ColumnsToZeroMean(matrixX,meanX);
MatrixMath.NIPALS_HO(matrixX,maxNumberOfFactors,1E-9,factors,loads,residualVariances);
// now we have to create a new table where to place the calculated factors and loads
// we will do that in a vertical oriented manner, i.e. even if the loads are
// here in horizontal vectors: in our table they are stored in (vertical) columns
Altaxo.Data.DataTable table = new Altaxo.Data.DataTable("PCA of " + srctable.Name);
// Fill the Table
table.Suspend();
// first of all store the meanscore
{
double meanScore = MatrixMath.LengthOf(meanX);
MatrixMath.NormalizeRows(meanX);
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for(int i=0;i<factors.Rows;i++)
col[i] = meanScore;
table.DataColumns.Add(col,"MeanFactor",Altaxo.Data.ColumnKind.V,0);
}
// first store the factors
for(int i=0;i<factors.Columns;i++)
{
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for(int j=0;j<factors.Rows;j++)
col[j] = factors[j,i];
table.DataColumns.Add(col,"Factor"+i.ToString(),Altaxo.Data.ColumnKind.V,1);
}
// now store the mean of the matrix
{
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for(int j=0;j<meanX.Columns;j++)
col[j] = meanX[0,j];
table.DataColumns.Add(col,"MeanLoad",Altaxo.Data.ColumnKind.V,2);
}
// now store the loads - careful - they are horizontal in the matrix
for(int i=0;i<loads.Rows;i++)
{
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for(int j=0;j<loads.Columns;j++)
col[j] = loads[i,j];
table.DataColumns.Add(col,"Load"+i.ToString(),Altaxo.Data.ColumnKind.V,3);
}
// now store the residual variances, they are vertical in the vector
{
Altaxo.Data.DoubleColumn col = new Altaxo.Data.DoubleColumn();
for(int i=0;i<residualVariances.Rows;i++)
col[i] = residualVariances[i,0];
table.DataColumns.Add(col,"ResidualVariance",Altaxo.Data.ColumnKind.V,4);
}
table.Resume();
mainDocument.DataTableCollection.Add(table);
// create a new worksheet without any columns
Current.ProjectService.CreateNewWorksheet(table);
return null;
}
public static void StatisticsOnRows(
Altaxo.AltaxoDocument mainDocument,
Altaxo.Data.DataTable srctable,
IAscendingIntegerCollection selectedColumns,
IAscendingIntegerCollection selectedRows
)
{
bool bUseSelectedColumns = (null != selectedColumns && 0 != selectedColumns.Count);
int numcols = bUseSelectedColumns ? selectedColumns.Count : srctable.DataColumns.ColumnCount;
if (numcols == 0)
{
return; // nothing selected
}
bool bUseSelectedRows = (null != selectedRows && 0 != selectedRows.Count);
int numrows = bUseSelectedRows ? selectedRows.Count : srctable.DataColumns.RowCount;
if (numrows == 0)
{
return;
}
Altaxo.Data.DataTable table = new Altaxo.Data.DataTable();
// add a text column and some double columns
// note: statistics is only possible for numeric columns since
// otherwise in one column doubles and i.e. dates are mixed, which is not possible
// 1st column is the mean, and holds the sum during the calculation
Data.DoubleColumn c1 = new Data.DoubleColumn();
// 2rd column is the standard deviation, and holds the square sum during calculation
Data.DoubleColumn c2 = new Data.DoubleColumn();
// 3th column is the standard e (N)
Data.DoubleColumn c3 = new Data.DoubleColumn();
// 4th column is the sum
Data.DoubleColumn c4 = new Data.DoubleColumn();
// 5th column is the number of items for statistics
Data.DoubleColumn c5 = new Data.DoubleColumn();
table.DataColumns.Add(c1, "Mean");
table.DataColumns.Add(c2, "sd");
table.DataColumns.Add(c3, "se");
table.DataColumns.Add(c4, "Sum");
table.DataColumns.Add(c5, "N");
table.Suspend();
// first fill the cols c1, c2, c5 with zeros because we want to sum up
for (int i = 0; i < numrows; i++)
{
c1[i] = 0;
c2[i] = 0;
c5[i] = 0;
}
for (int si = 0; si < numcols; si++)
{
Altaxo.Data.DataColumn col = bUseSelectedColumns ? srctable[selectedColumns[si]] : srctable[si];
if (!(col is Altaxo.Data.INumericColumn))
{
continue;
}
// now do the statistics
Data.INumericColumn ncol = (Data.INumericColumn)col;
for (int i = 0; i < numrows; i++)
{
double val = bUseSelectedRows ? ncol[selectedRows[i]] : ncol[i];
if (Double.IsNaN(val))
{
continue;
}
c1[i] += val;
c2[i] += val * val;
c5[i] += 1;
}
} // for all selected columns
// now calculate the statistics
for (int i = 0; i < numrows; i++)
{
// now fill a new row in the worksheet
double NN = c5[i];
double sum = c1[i];
double sumsqr = c2[i];
if (NN > 0)
{
double mean = c1[i] / NN;
double ymy0sqr = sumsqr - sum * sum / NN;
if (ymy0sqr < 0)
{
ymy0sqr = 0; // if this is lesser zero, it is a rounding error, so set it to zero
}
double sd = NN > 1 ? Math.Sqrt(ymy0sqr / (NN - 1)) : 0;
double se = sd / Math.Sqrt(NN);
c1[i] = mean; // mean
c2[i] = sd;
c3[i] = se;
c4[i] = sum;
c5[i] = NN;
}
} // for all rows
// if a table was created, we add the table to the data set and
// create a worksheet
if (null != table)
{
table.Resume();
mainDocument.DataTableCollection.Add(table);
// create a new worksheet without any columns
Current.ProjectService.CreateNewWorksheet(table);
}
}
/// <summary>
/// Makes a PLS (a partial least squares) analysis of the table or the selected columns / rows and stores the results in a newly created table.
/// </summary>
/// <param name="mainDocument">The main document of the application.</param>
/// <param name="srctable">The table where the data come from.</param>
/// <param name="selectedColumns">The selected columns.</param>
/// <param name="selectedRows">The selected rows.</param>
/// <param name="selectedPropertyColumns">The selected property column(s).</param>
/// <param name="bHorizontalOrientedSpectrum">True if a spectrum is a single row, False if a spectrum is a single column.</param>
/// <param name="plsOptions">Provides information about the max number of factors and the calculation of cross PRESS value.</param>
/// <param name="preprocessOptions">Provides information about how to preprocess the spectra.</param>
/// <returns></returns>
public virtual string ExecuteAnalysis(
Altaxo.AltaxoDocument mainDocument,
Altaxo.Data.DataTable srctable,
IAscendingIntegerCollection selectedColumns,
IAscendingIntegerCollection selectedRows,
IAscendingIntegerCollection selectedPropertyColumns,
bool bHorizontalOrientedSpectrum,
MultivariateAnalysisOptions plsOptions,
SpectralPreprocessingOptions preprocessOptions
)
{
IMatrix matrixX, matrixY;
IROVector xOfX;
MultivariateContentMemento plsContent = new MultivariateContentMemento();
plsContent.Analysis = this;
// now we have to create a new table where to place the calculated factors and loads
// we will do that in a vertical oriented manner, i.e. even if the loads are
// here in horizontal vectors: in our table they are stored in (vertical) columns
Altaxo.Data.DataTable table = new Altaxo.Data.DataTable(this.AnalysisName + " of " + srctable.Name);
// Fill the Table
table.Suspend();
table.SetTableProperty("Content",plsContent);
plsContent.TableName = srctable.Name;
// Get matrices
GetXYMatrices(
srctable,
selectedColumns,
selectedRows,
selectedPropertyColumns,
bHorizontalOrientedSpectrum,
plsContent,
out matrixX, out matrixY, out xOfX );
StoreXOfX(xOfX,table);
// Preprocess
plsContent.SpectralPreprocessing = preprocessOptions;
IVector meanX,scaleX,meanY,scaleY;
MultivariateRegression.PreprocessForAnalysis(preprocessOptions,xOfX,matrixX,matrixY,
out meanX, out scaleX, out meanY, out scaleY);
StorePreprocessedData(meanX,scaleX,meanY,scaleY,table);
// Analyze and Store
IROVector press;
ExecuteAnalysis(
matrixX,
matrixY,
plsOptions,
plsContent,
table, out press);
this.StorePRESSData(press,table);
if(plsOptions.CrossPRESSCalculation!=CrossPRESSCalculationType.None)
CalculateCrossPRESS(xOfX,matrixX,matrixY,plsOptions,plsContent,table);
StoreFRatioData(table,plsContent);
StoreOriginalY(table,plsContent);
table.Resume();
Current.Project.DataTableCollection.Add(table);
// create a new worksheet without any columns
Current.ProjectService.CreateNewWorksheet(table);
return null;
}
public static void StatisticsOnRows(
Altaxo.AltaxoDocument mainDocument,
Altaxo.Data.DataTable srctable,
IAscendingIntegerCollection selectedColumns,
IAscendingIntegerCollection selectedRows
)
{
bool bUseSelectedColumns = (null!=selectedColumns && 0!=selectedColumns.Count);
int numcols = bUseSelectedColumns ? selectedColumns.Count : srctable.DataColumns.ColumnCount;
if(numcols==0)
return; // nothing selected
bool bUseSelectedRows = (null!=selectedRows && 0!=selectedRows.Count);
int numrows = bUseSelectedRows ? selectedRows.Count : srctable.DataColumns.RowCount;
if(numrows==0)
return;
Altaxo.Data.DataTable table = new Altaxo.Data.DataTable();
// add a text column and some double columns
// note: statistics is only possible for numeric columns since
// otherwise in one column doubles and i.e. dates are mixed, which is not possible
// 1st column is the mean, and holds the sum during the calculation
Data.DoubleColumn c1 = new Data.DoubleColumn();
// 2rd column is the standard deviation, and holds the square sum during calculation
Data.DoubleColumn c2 = new Data.DoubleColumn();
// 3th column is the standard e (N)
Data.DoubleColumn c3 = new Data.DoubleColumn();
// 4th column is the sum
Data.DoubleColumn c4 = new Data.DoubleColumn();
// 5th column is the number of items for statistics
Data.DoubleColumn c5 = new Data.DoubleColumn();
table.DataColumns.Add(c1,"Mean");
table.DataColumns.Add(c2,"sd");
table.DataColumns.Add(c3,"se");
table.DataColumns.Add(c4,"Sum");
table.DataColumns.Add(c5,"N");
table.Suspend();
// first fill the cols c1, c2, c5 with zeros because we want to sum up
for(int i=0;i<numrows;i++)
{
c1[i]=0;
c2[i]=0;
c5[i]=0;
}
for(int si=0;si<numcols;si++)
{
Altaxo.Data.DataColumn col = bUseSelectedColumns ? srctable[selectedColumns[si]] : srctable[si];
if(!(col is Altaxo.Data.INumericColumn))
continue;
// now do the statistics
Data.INumericColumn ncol = (Data.INumericColumn)col;
for(int i=0;i<numrows;i++)
{
double val = bUseSelectedRows ? ncol[selectedRows[i]] : ncol[i];
if(Double.IsNaN(val))
continue;
c1[i] += val;
c2[i] += val*val;
c5[i] += 1;
}
} // for all selected columns
// now calculate the statistics
for(int i=0;i<numrows;i++)
{
// now fill a new row in the worksheet
double NN=c5[i];
double sum=c1[i];
double sumsqr=c2[i];
if(NN>0)
{
double mean = c1[i]/NN;
double ymy0sqr = sumsqr - sum*sum/NN;
if(ymy0sqr<0) ymy0sqr=0; // if this is lesser zero, it is a rounding error, so set it to zero
double sd = NN>1 ? Math.Sqrt(ymy0sqr/(NN-1)) : 0;
double se = sd/Math.Sqrt(NN);
c1[i] = mean; // mean
c2[i] = sd;
c3[i] = se;
c4[i] = sum;
c5[i] = NN;
}
} // for all rows
// if a table was created, we add the table to the data set and
// create a worksheet
if(null!=table)
{
table.Resume();
mainDocument.DataTableCollection.Add(table);
// create a new worksheet without any columns
Current.ProjectService.CreateNewWorksheet(table);
}
}