private static void AddCategoricalColumns(IDataWithAnnotationColumns mdata1, IDataWithAnnotationColumns mdata2,
Parameters parameters, IList <int[]> indexMap, IDataWithAnnotationColumns result)
{
int[] catCols = parameters.GetParam <int[]>("Categorical columns").Value;
string[][][] newCatColumns = new string[catCols.Length][][];
string[] newCatColNames = new string[catCols.Length];
for (int i = 0; i < catCols.Length; i++)
{
string[][] oldCol = mdata2.GetCategoryColumnAt(catCols[i]);
newCatColNames[i] = mdata2.CategoryColumnNames[catCols[i]];
newCatColumns[i] = new string[mdata1.RowCount][];
for (int j = 0; j < mdata1.RowCount; j++)
{
int[] inds = indexMap[j];
List <string[]> values = new List <string[]>();
foreach (int ind in inds)
{
string[] v = oldCol[ind];
if (v.Length > 0)
{
values.Add(v);
}
}
newCatColumns[i][j] = values.Count == 0
? new string[0]
: ArrayUtils.UniqueValues(ArrayUtils.Concat(values.ToArray()));
}
}
for (int i = 0; i < catCols.Length; i++)
{
result.AddCategoryColumn(newCatColNames[i], "", newCatColumns[i]);
}
}
public static void CombineRows(this IDataWithAnnotationColumns mdata, List <int> rowIdxs, Func <double[], double> combineNumeric, Func <string[], string> combineString, Func <string[][], string[]> combineCategory, Func <double[][], double[]> combineMultiNumeric)
{
if (!rowIdxs.Any())
{
return;
}
var resultRow = rowIdxs[0];
for (int i = 0; i < mdata.NumericColumnCount; i++)
{
var column = mdata.NumericColumns[i];
var values = ArrayUtils.SubArray(column, rowIdxs);
column[resultRow] = combineNumeric(values);
}
for (int i = 0; i < mdata.StringColumnCount; i++)
{
var column = mdata.StringColumns[i];
var values = ArrayUtils.SubArray(column, rowIdxs);
column[resultRow] = combineString(values);
}
for (int i = 0; i < mdata.CategoryColumnCount; i++)
{
var column = mdata.GetCategoryColumnAt(i);
var values = ArrayUtils.SubArray(column, rowIdxs);
column[resultRow] = combineCategory(values);
mdata.SetCategoryColumnAt(column, i);
}
for (int i = 0; i < mdata.MultiNumericColumnCount; i++)
{
var column = mdata.MultiNumericColumns[i];
var values = ArrayUtils.SubArray(column, rowIdxs);
column[resultRow] = combineMultiNumeric(values);
}
}
private static List <string[][]> GetCategoryColumns(IDataWithAnnotationColumns mdata)
{
List <string[][]> result = new List <string[][]>();
for (int i = 0; i < mdata.CategoryColumnCount; i++)
{
result.Add(mdata.GetCategoryColumnAt(i));
}
return(result);
}
/// <summary>
/// Add a number of empty rows to the table
/// </summary>
public static void AddEmptyRows(this IDataWithAnnotationColumns mdata, int length)
{
for (int i = 0; i < mdata.StringColumnCount; i++)
{
mdata.StringColumns[i] = mdata.StringColumns[i].Concat(Enumerable.Repeat(String.Empty, length)).ToArray();
}
for (int i = 0; i < mdata.NumericColumnCount; i++)
{
mdata.NumericColumns[i] = mdata.NumericColumns[i].Concat(Enumerable.Repeat(Double.NaN, length)).ToArray();
}
for (int i = 0; i < mdata.MultiNumericColumnCount; i++)
{
mdata.MultiNumericColumns[i] = mdata.MultiNumericColumns[i].Concat(Enumerable.Range(0, length).Select(_ => new double[0])).ToArray();
}
for (int i = 0; i < mdata.CategoryColumnCount; i++)
{
mdata.SetCategoryColumnAt(mdata.GetCategoryColumnAt(i).Concat(Enumerable.Repeat(new string[0], length)).ToArray(), i);
}
}
private static List<string[][]> GetCategoryColumns(IDataWithAnnotationColumns mdata)
{
List<string[][]> result = new List<string[][]>();
for (int i = 0; i < mdata.CategoryColumnCount; i++){
result.Add(mdata.GetCategoryColumnAt(i));
}
return result;
}
