/// <summary>
/// Create a new Classification by randomly selecting a subset of the points in the current Classification.
/// </summary>
/// <param name="sampleSize">Number of points to include in the new Classification.</param>
/// <returns>A new Classification that has the given number of points.</returns>
public Classification <TPoint, TLabel> Sample(int sampleSize)
{
var subset = new Classification <TPoint, TLabel>();
foreach (var point in Points().TakeRandom(sampleSize, NumPoints))
{
subset.Add(point, GetClassLabel(point));
}
return(subset);
}
/// <summary>
/// Clone the Classification, using the same Points and labels (semi-shallow copy).
/// </summary>
public object Clone()
{
var copy = new Classification <TPoint, TLabel>();
foreach (var point in Points())
{
copy.Add(point, GetClassLabel(point));
}
return(copy);
}
/// <summary>
/// Load the data from a file or standard input unless it has already been loaded into InitialClassification.
///
/// It must have a header row if Configuration.Data.ReadHeader is true.
/// Field values may be separated by commas or tabs.
/// </summary>
void LoadData()
{
if (IsDataLoaded)
{
return;
}
Timer.Start("Load data");
InitialClassification = new Classification <UnsignedPoint, string>();
InputOrder = new List <UnsignedPoint>();
InputDataIds = new Dictionary <UnsignedPoint, string>();
IEnumerable <string> lines;
if (Configuration.Data.ReadFromStandardIn())
{
lines = ReadLinesFromConsole();
}
else
{
lines = File.ReadLines(Configuration.Data.InputDataFile);
}
var idPosition = -1;
var categoryPosition = -1;
if (!Configuration.Data.ReadHeader)
{
idPosition = SafeParseInt(Configuration.Data.IdField, -1);
categoryPosition = SafeParseInt(Configuration.Data.CategoryField, -1);
}
var rownum = Configuration.Data.ReadHeader ? 0 : 1;
string[] header = null;
foreach (var values in lines.Select(line => line.Split(new [] { ',', '\t' })))
{
// Skip blank lines and comments
if (values.Length < 2)
{
continue;
}
if (rownum == 0 && Configuration.Data.ReadHeader)
{
// Identify which columns hold the Id and the Category, if any.
// If no column holds the Id, then the one-based row number will be used.
// Regardless of whether the file has a header row, row number one
// is the first row with data, not column headings.
header = values;
var tryIdPosition = Array.FindIndex(
header,
heading => heading.ToUpperInvariant().Equals(Configuration.Data.IdField.ToUpperInvariant())
);
if (tryIdPosition != -1)
{
idPosition = tryIdPosition;
}
var tryCategoryPosition = Array.FindIndex(
header,
heading => heading.ToUpperInvariant().Equals(Configuration.Data.CategoryField.ToUpperInvariant())
);
if (tryCategoryPosition != -1)
{
categoryPosition = tryCategoryPosition;
}
}
else
{
int id;
string idString;
if (idPosition == -1)
{
id = rownum;
idString = rownum.ToString();
}
else
{
// If the id is not a number, we use the rownum in the points we create as the id, but
// make a correspondence between the string and the point.
id = SafeParseInt(values[idPosition], rownum);
idString = values[idPosition];
}
string categoryString;
if (categoryPosition == -1)
{
categoryString = rownum.ToString(); // Unclassified - all points in their own cluster.
}
else
{
categoryString = values[categoryPosition];
}
var coordinates = new List <uint>();
foreach (var pair in values.Select((v, i) => new { Value = v, Position = i }))
{
//TODO: Reject negative values and log.
if (pair.Position != idPosition && pair.Position != categoryPosition)
{
coordinates.Add((uint)SafeParseInt(pair.Value, 0));
}
}
var point = new UnsignedPoint(coordinates, id);
//TODO: Check for duplicate ids and log.
InputDataIds[point] = idString;
InitialClassification.Add(point, categoryString);
InputOrder.Add(point);
}
rownum++;
}
Timer.Stop("Load data");
}
