#region License Information
/* HeuristicLab
* Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
*
* This file is part of HeuristicLab.
*
* HeuristicLab is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* HeuristicLab is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with HeuristicLab. If not, see .
*/
#endregion
using System;
using System.Collections.Generic;
using System.Linq;
using HeuristicLab.Problems.DataAnalysis;
namespace HeuristicLab.Algorithms.DataAnalysis {
public static class AlglibUtil {
public static double[,] PrepareInputMatrix(IDataset dataset, IEnumerable variables, IEnumerable rows) {
// check input variables. Only double variables are allowed.
var invalidInputs =
variables.Where(name => !dataset.VariableHasType(name));
if (invalidInputs.Any())
throw new NotSupportedException("Unsupported inputs: " + string.Join(", ", invalidInputs));
List rowsList = rows.ToList();
double[,] matrix = new double[rowsList.Count, variables.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 static double[,] PrepareAndScaleInputMatrix(IDataset dataset, IEnumerable variables, IEnumerable rows, Scaling scaling) {
// check input variables. Only double variables are allowed.
var invalidInputs =
variables.Where(name => !dataset.VariableHasType(name));
if (invalidInputs.Any())
throw new NotSupportedException("Unsupported inputs: " + string.Join(", ", invalidInputs));
List variablesList = variables.ToList();
List rowsList = rows.ToList();
double[,] matrix = new double[rowsList.Count, variablesList.Count];
int col = 0;
foreach (string column in variables) {
var values = scaling.GetScaledValues(dataset, column, rows);
int row = 0;
foreach (var value in values) {
matrix[row, col] = value;
row++;
}
col++;
}
return matrix;
}
///
/// Prepares a binary data matrix from a number of factors and specified factor values
///
/// A dataset that contains the variable values
/// An enumerable of categorical variables (factors). For each variable an enumerable of values must be specified.
/// An enumerable of row indices for the dataset
///
/// Factor variables (categorical variables) are split up into multiple binary variables one for each specified value.
public static double[,] PrepareInputMatrix(
IDataset dataset,
IEnumerable>> factorVariables,
IEnumerable rows) {
// check input variables. Only string variables are allowed.
var invalidInputs =
factorVariables.Select(kvp => kvp.Key).Where(name => !dataset.VariableHasType(name));
if (invalidInputs.Any())
throw new NotSupportedException("Unsupported inputs: " + string.Join(", ", invalidInputs));
int numBinaryColumns = factorVariables.Sum(kvp => kvp.Value.Count());
List rowsList = rows.ToList();
double[,] matrix = new double[rowsList.Count, numBinaryColumns];
int col = 0;
foreach (var kvp in factorVariables) {
var varName = kvp.Key;
var cats = kvp.Value;
if (!cats.Any()) continue;
foreach (var cat in cats) {
var values = dataset.GetStringValues(varName, rows);
int row = 0;
foreach (var value in values) {
matrix[row, col] = value == cat ? 1 : 0;
row++;
}
col++;
}
}
return matrix;
}
public static IEnumerable>> GetFactorVariableValues(IDataset ds, IEnumerable factorVariables, IEnumerable rows) {
return from factor in factorVariables
let distinctValues = ds.GetStringValues(factor, rows).Distinct().ToArray()
// 1 distinct value => skip (constant)
// 2 distinct values => only take one of the two values
// >=3 distinct values => create a binary value for each value
let reducedValues = distinctValues.Length <= 2
? distinctValues.Take(distinctValues.Length - 1)
: distinctValues
select new KeyValuePair>(factor, reducedValues);
}
}
}