StatisticFunctions.h

Go to the documentation of this file.

// --------------------------------------------------------------------------
//                   OpenMS -- Open-Source Mass Spectrometry
// --------------------------------------------------------------------------
// Copyright The OpenMS Team -- Eberhard Karls University Tuebingen,
// ETH Zurich, and Freie Universitaet Berlin 2002-2017.
//
// This software is released under a three-clause BSD license:
//  * Redistributions of source code must retain the above copyright
//    notice, this list of conditions and the following disclaimer.
//  * Redistributions in binary form must reproduce the above copyright
//    notice, this list of conditions and the following disclaimer in the
//    documentation and/or other materials provided with the distribution.
//  * Neither the name of any author or any participating institution
//    may be used to endorse or promote products derived from this software
//    without specific prior written permission.
// For a full list of authors, refer to the file AUTHORS.
// --------------------------------------------------------------------------
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
// ARE DISCLAIMED. IN NO EVENT SHALL ANY OF THE AUTHORS OR THE CONTRIBUTING
// INSTITUTIONS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
// EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
// OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
// WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
// OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
// ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// --------------------------------------------------------------------------
// $Maintainer: Timo Sachsenberg $
// $Authors: Clemens Groepl, Johannes Junker, Mathias Walzer, Chris Bielow $
// --------------------------------------------------------------------------
#ifndef OPENMS_MATH_STATISTICS_STATISTICFUNCTIONS_H
#define OPENMS_MATH_STATISTICS_STATISTICFUNCTIONS_H

#include <vector>
#include <OpenMS/CONCEPT/Exception.h>
#include <OpenMS/CONCEPT/Types.h>

// array_wrapper needs to be included before it is used
// only in boost1.64+. See issue #2790
#if OPENMS_BOOST_VERSION_MINOR >= 64
#include <boost/serialization/array_wrapper.hpp>
#endif
#include <boost/accumulators/accumulators.hpp>
#include <boost/accumulators/statistics/covariance.hpp>
#include <boost/accumulators/statistics/mean.hpp>
#include <boost/accumulators/statistics/stats.hpp>
#include <boost/accumulators/statistics/variance.hpp>
#include <boost/accumulators/statistics/variates/covariate.hpp>
#include <boost/function/function_base.hpp>
#include <boost/lambda/casts.hpp>
#include <boost/lambda/lambda.hpp>

#include <iterator>
#include <algorithm>

using std::iterator_traits;

namespace OpenMS
{

  namespace Math
  {
    template <typename IteratorType>
    static void checkIteratorsNotNULL(IteratorType begin, IteratorType end)
    {
      if (begin == end)
      {
        throw Exception::InvalidRange(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION);
      }
    }

    template <typename IteratorType>
    static void checkIteratorsEqual(IteratorType begin, IteratorType end)
    {
      if (begin != end)
      {
        throw Exception::InvalidRange(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION);
      }
    }

    template <typename IteratorType1, typename IteratorType2>
    static void checkIteratorsAreValid(
      IteratorType1 begin_b, IteratorType1 end_b,
      IteratorType2 begin_a, IteratorType2 end_a)
    {
      if (begin_b != end_b && begin_a == end_a)
      {
        throw Exception::InvalidRange(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION);
      }
    }

    template <typename IteratorType>
    static double sum(IteratorType begin, IteratorType end)
    {
      return std::accumulate(begin, end, 0.0);
    }

    template <typename IteratorType>
    static double mean(IteratorType begin, IteratorType end)
    {
      checkIteratorsNotNULL(begin, end);
      return sum(begin, end) / std::distance(begin, end);
    }

    template <typename IteratorType>
    static double median(IteratorType begin, IteratorType end, 
                         bool sorted = false)
    {
      checkIteratorsNotNULL(begin, end);
      if (!sorted)
      {
        std::sort(begin, end);
      }
      
      Size size = std::distance(begin, end);
      if (size % 2 == 0) // even size => average two middle values
      {
        IteratorType it1 = begin;
        std::advance(it1, size / 2 - 1);
        IteratorType it2 = it1;
        std::advance(it2, 1);
        return (*it1 + *it2) / 2.0;
      }
      else
      {
        IteratorType it = begin;
        std::advance(it, (size - 1) / 2);
        return *it;
      }
    }

  
    template <typename IteratorType>
    double MAD(IteratorType begin, IteratorType end, double median_of_numbers)
    {
      std::vector<double> diffs;
      diffs.reserve(std::distance(begin, end));
      for (IteratorType it = begin; it != end; ++it)
      {
        diffs.push_back(fabs(*it - median_of_numbers));
      }
      return median(diffs.begin(), diffs.end(), false);
    }

    template <typename IteratorType>
    static double quantile1st(IteratorType begin, IteratorType end, 
                              bool sorted = false)
    {
      checkIteratorsNotNULL(begin, end);

      if (!sorted)
      {
        std::sort(begin, end);
      }

      Size size = std::distance(begin, end);
      if (size % 2 == 0)
      {
        return median(begin, begin + (size/2)-1, true); //-1 to exclude median values
      }
      return median(begin, begin + (size/2), true);
    }

    template <typename IteratorType>
    static double quantile3rd(
      IteratorType begin, IteratorType end, bool sorted = false)
    {
      checkIteratorsNotNULL(begin, end);
      if (!sorted)
      {
        std::sort(begin, end);
      }

      Size size = std::distance(begin, end);
      return median(begin + (size/2)+1, end, true); //+1 to exclude median values
    }

    template <typename IteratorType>
    static double variance(IteratorType begin, IteratorType end,
                           double mean = std::numeric_limits<double>::max())
    {
      checkIteratorsNotNULL(begin, end);
      double sum = 0.0;
      if (mean == std::numeric_limits<double>::max())
      {
        mean = Math::mean(begin, end);
      }
      for (IteratorType iter=begin; iter!=end; ++iter)
      {
        double diff = *iter - mean;
        sum += diff * diff;
      }
      return sum / (std::distance(begin, end)-1);
    }

    template <typename IteratorType>
    static double sd(IteratorType begin, IteratorType end,
                     double mean = std::numeric_limits<double>::max())
    {
      checkIteratorsNotNULL(begin, end);
      return std::sqrt( variance(begin, end, mean) );
    }

    template <typename IteratorType>
    static double absdev(IteratorType begin, IteratorType end,
                         double mean = std::numeric_limits<double>::max())
    {
      checkIteratorsNotNULL(begin, end);
      double sum = 0.0;
      if (mean == std::numeric_limits<double>::max())
      {
        mean = Math::mean(begin, end);
      }
      for (IteratorType iter=begin; iter!=end; ++iter)
      {
        sum += *iter - mean;
      }
      return sum / std::distance(begin, end);
    }

    template <typename IteratorType1, typename IteratorType2>
    static double covariance(IteratorType1 begin_a, IteratorType1 end_a,
                             IteratorType2 begin_b, IteratorType2 end_b)
    {
      //no data or different lengths
      checkIteratorsNotNULL(begin_a, end_a);

      double sum = 0.0;
      double mean_a = Math::mean(begin_a, end_a);
      double mean_b = Math::mean(begin_b, end_b);
      IteratorType1 iter_a = begin_a;
      IteratorType2 iter_b = begin_b;
      for (; iter_a != end_a; ++iter_a, ++iter_b)
      {
        /* assure both ranges have the same number of elements */
        checkIteratorsAreValid(begin_b, end_b, begin_a, end_a);
        sum += (*iter_a - mean_a) * (*iter_b - mean_b);
      }
      /* assure both ranges have the same number of elements */
      checkIteratorsEqual(iter_b, end_b);
      Size n = std::distance(begin_a, end_a);
      return sum / (n-1);
    }




    template <typename IteratorType1, typename IteratorType2>
    static double meanSquareError(IteratorType1 begin_a, IteratorType1 end_a,
                                  IteratorType2 begin_b, IteratorType2 end_b)
    {
      //no data or different lengths
      checkIteratorsNotNULL(begin_a, end_a);

      SignedSize dist = std::distance(begin_a, end_a);
      double error = 0;
      IteratorType1 iter_a = begin_a;
      IteratorType2 iter_b = begin_b;
      for (; iter_a != end_a; ++iter_a, ++iter_b)
      {
        /* assure both ranges have the same number of elements */
        checkIteratorsAreValid(iter_b, end_b, iter_a, end_a);

        double tmp(*iter_a - *iter_b);
        error += tmp * tmp;
      }
      /* assure both ranges have the same number of elements */
      checkIteratorsEqual(iter_b, end_b);

      return error / dist;
    }

    template <typename IteratorType1, typename IteratorType2>
    static double classificationRate(IteratorType1 begin_a, IteratorType1 end_a,
                                     IteratorType2 begin_b, IteratorType2 end_b)
    {
      //no data or different lengths
      checkIteratorsNotNULL(begin_a, end_a);

      SignedSize dist = std::distance(begin_a, end_a);
      SignedSize correct = dist;
      IteratorType1 iter_a = begin_a;
      IteratorType2 iter_b = begin_b;
      for (; iter_a != end_a; ++iter_a, ++iter_b)
      {
        /* assure both ranges have the same number of elements */
        checkIteratorsAreValid(iter_b, end_b, iter_a, end_a);
        if ((*iter_a < 0 && *iter_b >= 0) || (*iter_a >= 0 && *iter_b < 0))
        {
          --correct;
        }

      }
      /* assure both ranges have the same number of elements */
      checkIteratorsEqual(iter_b, end_b);

      return double(correct) / dist;
    }

    template <typename IteratorType1, typename IteratorType2>
    static double matthewsCorrelationCoefficient(
      IteratorType1 begin_a, IteratorType1 end_a,
      IteratorType2 begin_b, IteratorType2 end_b)
    {
      //no data or different lengths
      checkIteratorsNotNULL(begin_a, end_b);

      double tp = 0;
      double fp = 0;
      double tn = 0;
      double fn = 0;
      IteratorType1 iter_a = begin_a;
      IteratorType2 iter_b = begin_b;
      for (; iter_a != end_a; ++iter_a, ++iter_b)
      {
        /* assure both ranges have the same number of elements */
        checkIteratorsAreValid(iter_b, end_b, iter_a, end_a);

        if (*iter_a < 0 && *iter_b >= 0)
        {
          ++fn;
        }
        else if (*iter_a < 0 && *iter_b < 0)
        {
          ++tn;
        }
        else if (*iter_a >= 0 && *iter_b >= 0)
        {
          ++tp;
        }
        else if (*iter_a >= 0 && *iter_b < 0)
        {
          ++fp;
        }
      }
      /* assure both ranges have the same number of elements */
      checkIteratorsEqual(iter_b, end_b);

      return (tp * tn - fp * fn) / sqrt((tp + fp) * (tp + fn) * (tn + fp) * (tn + fn));
    }

    template <typename IteratorType1, typename IteratorType2>
    static double pearsonCorrelationCoefficient(
      IteratorType1 begin_a, IteratorType1 end_a,
      IteratorType2 begin_b, IteratorType2 end_b)
    {
      //no data or different lengths
      checkIteratorsNotNULL(begin_a, end_a);

      //calculate average
      SignedSize dist = std::distance(begin_a, end_a);
      double avg_a = std::accumulate(begin_a, end_a, 0.0) / dist;
      double avg_b = std::accumulate(begin_b, end_b, 0.0) / dist;

      double numerator = 0;
      double denominator_a = 0;
      double denominator_b = 0;
      IteratorType1 iter_a = begin_a;
      IteratorType2 iter_b = begin_b;
      for (; iter_a != end_a; ++iter_a, ++iter_b)
      {
        /* assure both ranges have the same number of elements */
        checkIteratorsAreValid(iter_b, end_b, iter_a, end_a);
        double temp_a = *iter_a - avg_a;
        double temp_b = *iter_b - avg_b;
        numerator += (temp_a * temp_b);
        denominator_a += (temp_a * temp_a);
        denominator_b += (temp_b * temp_b);
      }
      /* assure both ranges have the same number of elements */
      checkIteratorsEqual(iter_b, end_b);
      return numerator / sqrt(denominator_a * denominator_b);
    }

    template <typename Value>
    static void computeRank(std::vector<Value> & w)
    {
      Size i = 0; // main index
      Size z  = 0;  // "secondary" index
      Value rank = 0;
      Size n = (w.size() - 1);
      //store original indices for later
      std::vector<std::pair<Size, Value> > w_idx;
      for (Size j = 0; j < w.size(); ++j)
      {
        w_idx.push_back(std::make_pair(j, w[j]));
      }
      //sort
      std::sort(w_idx.begin(), w_idx.end(),
                boost::lambda::ret<bool>((&boost::lambda::_1->*& std::pair<Size, Value>::second) < 
                                         (&boost::lambda::_2->*& std::pair<Size, Value>::second)));
      //replace pairs <orig_index, value> in w_idx by pairs <orig_index, rank>
      while (i < n)
      {
        // test for equality with tolerance:
        if (fabs(w_idx[i + 1].second - w_idx[i].second) > 0.0000001 * fabs(w_idx[i + 1].second)) // no tie
        {
          w_idx[i].second = Value(i + 1);
          ++i;
        }
        else // tie, replace by mean rank
        {
          // count number of ties
          for (z = i + 1; (z <= n) && fabs(w_idx[z].second - w_idx[i].second) <= 0.0000001 * fabs(w_idx[z].second); ++z)
          {
          }
          // compute mean rank of tie
          rank = 0.5 * (i + z + 1);
          // replace intensities by rank
          for (Size v = i; v <= z - 1; ++v)
          {
            w_idx[v].second = rank;
          }
          i = z;
        }
      }
      if (i == n)
        w_idx[n].second = Value(n + 1);
      //restore original order and replace elements of w with their ranks
      for (Size j = 0; j < w.size(); ++j)
      {
        w[w_idx[j].first] = w_idx[j].second;
      }
    }

    template <typename IteratorType1, typename IteratorType2>
    static double rankCorrelationCoefficient(
      IteratorType1 begin_a, IteratorType1 end_a,
      IteratorType2 begin_b, IteratorType2 end_b)
    {
      //no data or different lengths
      checkIteratorsNotNULL(begin_a, end_a);

      // store and sort intensities of model and data
      SignedSize dist = std::distance(begin_a, end_a);
      std::vector<double> ranks_data;
      ranks_data.reserve(dist);
      std::vector<double> ranks_model;
      ranks_model.reserve(dist);
      IteratorType1 iter_a = begin_a;
      IteratorType2 iter_b = begin_b;
      for (; iter_a != end_a; ++iter_a, ++iter_b)
      {
        /* assure both ranges have the same number of elements */
        checkIteratorsAreValid(iter_b, end_b, iter_a, end_a);

        ranks_model.push_back(*iter_a);
        ranks_data.push_back(*iter_b);
      }
      /* assure both ranges have the same number of elements */
      checkIteratorsEqual(iter_b, end_b);

      // replace entries by their ranks
      computeRank(ranks_data);
      computeRank(ranks_model);

      double mu = double(ranks_data.size() + 1) / 2.; // mean of ranks
      // Was the following, but I think the above is more correct ... (Clemens)
      // double mu = (ranks_data.size() + 1) / 2;

      double sum_model_data = 0;
      double sqsum_data = 0;
      double sqsum_model = 0;

      for (Int i = 0; i < dist; ++i)
      {
        sum_model_data += (ranks_data[i] - mu) * (ranks_model[i] - mu);
        sqsum_data += (ranks_data[i] - mu) * (ranks_data[i] - mu);
        sqsum_model += (ranks_model[i] - mu) * (ranks_model[i] - mu);
      }

      // check for division by zero
      if (!sqsum_data || !sqsum_model)
      {
        return 0;
      }

      return sum_model_data / (sqrt(sqsum_data) * sqrt(sqsum_model));
    }

    template<typename T>
    struct SummaryStatistics
    {
      SummaryStatistics()
        :mean(0), variance(0), min(0), lowerq(0), median(0), upperq(0), max(0)
      {
      }

      // Ctor with data
      SummaryStatistics(T& data)
      {
        count = data.size();
        // Sanity check: avoid core dump if no data points present.
        if (data.empty())
        {
          mean = variance = min = lowerq = median = upperq = max = 0.0;
        }
        else
        {
          sort(data.begin(), data.end());
          mean = Math::mean(data.begin(), data.end());
          variance = Math::variance(data.begin(), data.end(), mean);
          min = data.front();
          lowerq = Math::quantile1st(data.begin(), data.end(), true);
          median = Math::median(data.begin(), data.end(), true);
          upperq = Math::quantile3rd(data.begin(), data.end(), true);
          max = data.back();
        }
      }

      double mean, variance, lowerq, median, upperq;
      typename T::value_type min, max;
      size_t count;
    };

  }   // namespace Math
} // namespace OpenMS

#endif // OPENMS_MATH_STATISTICS_STATISTICFUNCTIONS_H