source: trunk/yat/normalizer/Zscore.h @ 2202

#ifndef _theplu_yat_normalizer_z_score_
#define _theplu_yat_normalizer_z_score_

// $Id: Zscore.h 2202 2010-02-21 18:39:13Z peter $

/*
  Copyright (C) 2008 Jari Häkkinen, Peter Johansson
  Copyright (C) 2009, 2010 Peter Johansson

  This file is part of the yat library, http://dev.thep.lu.se/yat

  The yat library 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.

  The yat library 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 yat. If not, see <http://www.gnu.org/licenses/>.
*/

#include "utility.h"

#include "yat/statistics/Averager.h"
#include "yat/statistics/AveragerWeighted.h"

#include "yat/utility/iterator_traits.h"

#include <boost/concept_check.hpp>

namespace theplu {
namespace yat {
namespace normalizer {

  /**
     \brief Zero mean and unity variance

     Shift and scale the values in a range as: \f$ y_i =
     \frac{x_i-m}{s} \f$ where \a m is the mean and \a s is the
     standard deviation. After normalization, the range will have zero
     mean and unity variance.

     \since New in yat 0.5
   */
  class Zscore
  {
  public:
    /**
       The element in range [result, result + (last-first)) is
       calculated as result[i] = (first[i] - m) / s where m and std
       are the mean and standard deviation, respectively, of the range
       [first, last).

       It is possible to centralize a range "in place"; it is
       permissible for the iterators \a first and \a result to be the
       same. \see std::transform
     */
    template<class ForwardIter1, class ForwardIter2>
    void operator()(ForwardIter1 first, ForwardIter1 last,
                    ForwardIter2 result) const
    {
      typename utility::weighted_if_any2<ForwardIter1, ForwardIter2>::type tag;
      normalize(first, last, result, tag);
    }

  private:
    template<class ForwardIterator, class OutputIterator>
    void normalize(ForwardIterator first, ForwardIterator last,
                   OutputIterator result,
                   utility::unweighted_iterator_tag tag) const
    {
      // we requre forward iterator since we iterate through the range
      // multiple times.
      BOOST_CONCEPT_ASSERT((boost::ForwardIterator<ForwardIterator>));
      BOOST_CONCEPT_ASSERT((boost::OutputIterator<OutputIterator, double>));
      statistics::Averager a;
      add(a, first, last);
      double m = a.mean();
      double std = a.std();
      while (first!=last) {
        *result = (*first - m) / std;
        ++first;
        ++result;
      }
    }

    template<class ForwardIter1, class ForwardIter2>
    void normalize(ForwardIter1 first, ForwardIter1 last, ForwardIter2 result,
                   utility::weighted_iterator_tag tag) const
    {
      // we requre forward iterator since we iterate through the range
      // multiple times.
      BOOST_CONCEPT_ASSERT((boost::ForwardIterator<ForwardIter1>));
      BOOST_CONCEPT_ASSERT((boost::Mutable_ForwardIterator<ForwardIter2>));
      detail::copy_weight_if_weighted(first, last, result);
      statistics::AveragerWeighted a;
      add(a, first, last);
      double m = a.mean();
      double std = a.std();
      utility::iterator_traits<ForwardIter1> in_trait;
      utility::iterator_traits<ForwardIter2> out_trait;
      while (first!=last) {
        out_trait.data(result) = (in_trait.data(first) - m) / std;
        ++first;
        ++result;
      }
    }
  };

}}} // end of namespace normalizer, yat and thep
#endif