FM / statistics

/usr/include/boost/accumulators/statistics/

/usr/include/boost/accumulators/statistics

Name	Size	Mode	Actions
parameters/	-	0755	rm
variates/	-	0755	rm
count.hpp	2013	0644	edit dl rm
covariance.hpp	7137	0644	edit dl rm
density.hpp	10007	0644	edit dl rm
error_of.hpp	2588	0644	edit dl rm
error_of_mean.hpp	2193	0644	edit dl rm
extended_p_square.hpp	11633	0644	edit dl rm
extended_p_square_quantile.hpp	12522	0644	edit dl rm
kurtosis.hpp	3864	0644	edit dl rm
max.hpp	2294	0644	edit dl rm
mean.hpp	9334	0644	edit dl rm
median.hpp	10242	0644	edit dl rm
min.hpp	2294	0644	edit dl rm
moment.hpp	3436	0644	edit dl rm
peaks_over_threshold.hpp	17525	0644	edit dl rm
pot_quantile.hpp	7336	0644	edit dl rm
pot_tail_mean.hpp	7802	0644	edit dl rm
p_square_cumulative_distribution.hpp	955	0644	edit dl rm
p_square_cumul_dist.hpp	10365	0644	edit dl rm
p_square_quantile.hpp	10086	0644	edit dl rm
rolling_count.hpp	2574	0644	edit dl rm
rolling_mean.hpp	6753	0644	edit dl rm
rolling_moment.hpp	3741	0644	edit dl rm
rolling_sum.hpp	2871	0644	edit dl rm
rolling_variance.hpp	9486	0644	edit dl rm
rolling_window.hpp	7254	0644	edit dl rm
skewness.hpp	3691	0644	edit dl rm
stats.hpp	972	0644	edit dl rm
sum.hpp	3884	0644	edit dl rm
sum_kahan.hpp	5104	0644	edit dl rm
tail.hpp	11012	0644	edit dl rm
tail_mean.hpp	9158	0644	edit dl rm
tail_quantile.hpp	5535	0644	edit dl rm
tail_variate.hpp	4504	0644	edit dl rm
tail_variate_means.hpp	10463	0644	edit dl rm
times2_iterator.hpp	1965	0644	edit dl rm
variance.hpp	7522	0644	edit dl rm
weighted_covariance.hpp	5244	0644	edit dl rm
weighted_density.hpp	9518	0644	edit dl rm
weighted_extended_p_square.hpp	12842	0644	edit dl rm
weighted_kurtosis.hpp	4147	0644	edit dl rm
weighted_mean.hpp	6637	0644	edit dl rm
weighted_median.hpp	8667	0644	edit dl rm
weighted_moment.hpp	3384	0644	edit dl rm
weighted_peaks_over_threshold.hpp	12352	0644	edit dl rm
weighted_p_square_cumulative_distribution.hpp	1009	0644	edit dl rm
weighted_p_square_cumul_dist.hpp	11058	0644	edit dl rm
weighted_p_square_quantile.hpp	11110	0644	edit dl rm
weighted_skewness.hpp	3844	0644	edit dl rm
weighted_sum.hpp	3639	0644	edit dl rm
weighted_sum_kahan.hpp	4559	0644	edit dl rm
weighted_tail_mean.hpp	5788	0644	edit dl rm
weighted_tail_quantile.hpp	5135	0644	edit dl rm
weighted_tail_variate_means.hpp	10052	0644	edit dl rm
weighted_variance.hpp	6774	0644	edit dl rm
with_error.hpp	1277	0644	edit dl rm

Edit: /usr/include/boost/accumulators/statistics/weighted_p_square_cumul_dist.hpp (11058B)

///////////////////////////////////////////////////////////////////////////////
// weighted_p_square_cumul_dist.hpp
//
//  Copyright 2006 Daniel Egloff, Olivier Gygi. Distributed under the Boost
//  Software License, Version 1.0. (See accompanying file
//  LICENSE_1_0.txt or copy at http://www.boost.org/LICENSE_1_0.txt)

#ifndef BOOST_ACCUMULATORS_STATISTICS_WEIGHTED_P_SQUARE_CUMUL_DIST_HPP_DE_01_01_2006
#define BOOST_ACCUMULATORS_STATISTICS_WEIGHTED_P_SQUARE_CUMUL_DIST_HPP_DE_01_01_2006

#include <vector>
#include <functional>
#include <boost/parameter/keyword.hpp>
#include <boost/mpl/placeholders.hpp>
#include <boost/range.hpp>
#include <boost/accumulators/framework/accumulator_base.hpp>
#include <boost/accumulators/framework/extractor.hpp>
#include <boost/accumulators/numeric/functional.hpp>
#include <boost/accumulators/framework/parameters/sample.hpp>
#include <boost/accumulators/statistics_fwd.hpp>
#include <boost/accumulators/statistics/count.hpp>
#include <boost/accumulators/statistics/sum.hpp>
#include <boost/accumulators/statistics/p_square_cumul_dist.hpp> // for named parameter p_square_cumulative_distribution_num_cells

namespace boost { namespace accumulators
{

namespace impl
{
    ///////////////////////////////////////////////////////////////////////////////
    // weighted_p_square_cumulative_distribution_impl
    //  cumulative distribution calculation (as histogram)
    /**
        @brief Histogram calculation of the cumulative distribution with the \f$P^2\f$ algorithm for weighted samples

A histogram of the sample cumulative distribution is computed dynamically without storing samples
        based on the \f$ P^2 \f$ algorithm for weighted samples. The returned histogram has a specifiable
        amount (num_cells) equiprobable (and not equal-sized) cells.

Note that applying importance sampling results in regions to be more and other regions to be less
        accurately estimated than without importance sampling, i.e., with unweighted samples.

For further details, see

R. Jain and I. Chlamtac, The P^2 algorithm for dynamic calculation of quantiles and
        histograms without storing observations, Communications of the ACM,
        Volume 28 (October), Number 10, 1985, p. 1076-1085.

@param p_square_cumulative_distribution_num_cells
    */
    template<typename Sample, typename Weight>
    struct weighted_p_square_cumulative_distribution_impl
      : accumulator_base
    {
        typedef typename numeric::functional::multiplies<Sample, Weight>::result_type weighted_sample;
        typedef typename numeric::functional::fdiv<weighted_sample, std::size_t>::result_type float_type;
        typedef std::vector<std::pair<float_type, float_type> > histogram_type;
        typedef std::vector<float_type> array_type;
        // for boost::result_of
        typedef iterator_range<typename histogram_type::iterator> result_type;

template<typename Args>
        weighted_p_square_cumulative_distribution_impl(Args const &args)
          : num_cells(args[p_square_cumulative_distribution_num_cells])
          , heights(num_cells + 1)
          , actual_positions(num_cells + 1)
          , desired_positions(num_cells + 1)
          , histogram(num_cells + 1)
          , is_dirty(true)
        {
        }

template<typename Args>
        void operator ()(Args const &args)
        {
            this->is_dirty = true;

std::size_t cnt = count(args);
            std::size_t sample_cell = 1; // k
            std::size_t b = this->num_cells;

// accumulate num_cells + 1 first samples
            if (cnt <= b + 1)
            {
                this->heights[cnt - 1] = args[sample];
                this->actual_positions[cnt - 1] = args[weight];

// complete the initialization of heights by sorting
                if (cnt == b + 1)
                {
                    //std::sort(this->heights.begin(), this->heights.end());

// TODO: we need to sort the initial samples (in heights) in ascending order and
                    // sort their weights (in actual_positions) the same way. The following lines do
                    // it, but there must be a better and more efficient way of doing this.
                    typename array_type::iterator it_begin, it_end, it_min;

it_begin = this->heights.begin();
                    it_end   = this->heights.end();

std::size_t pos = 0;

while (it_begin != it_end)
                    {
                        it_min = std::min_element(it_begin, it_end);
                        std::size_t d = std::distance(it_begin, it_min);
                        std::swap(*it_begin, *it_min);
                        std::swap(this->actual_positions[pos], this->actual_positions[pos + d]);
                        ++it_begin;
                        ++pos;
                    }

// calculate correct initial actual positions
                    for (std::size_t i = 1; i < b; ++i)
                    {
                        this->actual_positions[i] += this->actual_positions[i - 1];
                    }
                }
            }
            else
            {
                // find cell k such that heights[k-1] <= args[sample] < heights[k] and adjust extreme values
                if (args[sample] < this->heights[0])
                {
                    this->heights[0] = args[sample];
                    this->actual_positions[0] = args[weight];
                    sample_cell = 1;
                }
                else if (this->heights[b] <= args[sample])
                {
                    this->heights[b] = args[sample];
                    sample_cell = b;
                }
                else
                {
                    typename array_type::iterator it;
                    it = std::upper_bound(
                        this->heights.begin()
                      , this->heights.end()
                      , args[sample]
                    );

sample_cell = std::distance(this->heights.begin(), it);
                }

// increment positions of markers above sample_cell
                for (std::size_t i = sample_cell; i < b + 1; ++i)
                {
                    this->actual_positions[i] += args[weight];
                }

// determine desired marker positions
                for (std::size_t i = 1; i < b + 1; ++i)
                {
                    this->desired_positions[i] = this->actual_positions[0]
                                               + numeric::fdiv((i-1) * (sum_of_weights(args) - this->actual_positions[0]), b);
                }

// adjust heights of markers 2 to num_cells if necessary
                for (std::size_t i = 1; i < b; ++i)
                {
                    // offset to desire position
                    float_type d = this->desired_positions[i] - this->actual_positions[i];

// offset to next position
                    float_type dp = this->actual_positions[i + 1] - this->actual_positions[i];

// offset to previous position
                    float_type dm = this->actual_positions[i - 1] - this->actual_positions[i];

// height ds
                    float_type hp = (this->heights[i + 1] - this->heights[i]) / dp;
                    float_type hm = (this->heights[i - 1] - this->heights[i]) / dm;

if ( ( d >= 1. && dp > 1. ) || ( d <= -1. && dm < -1. ) )
                    {
                        short sign_d = static_cast<short>(d / std::abs(d));

// try adjusting heights[i] using p-squared formula
                        float_type h = this->heights[i] + sign_d / (dp - dm) * ( (sign_d - dm) * hp + (dp - sign_d) * hm );

if ( this->heights[i - 1] < h && h < this->heights[i + 1] )
                        {
                            this->heights[i] = h;
                        }
                        else
                        {
                            // use linear formula
                            if (d>0)
                            {
                                this->heights[i] += hp;
                            }
                            if (d<0)
                            {
                                this->heights[i] -= hm;
                            }
                        }
                        this->actual_positions[i] += sign_d;
                    }
                }
            }
        }

template<typename Args>
        result_type result(Args const &args) const
        {
            if (this->is_dirty)
            {
                this->is_dirty = false;

// creates a vector of std::pair where each pair i holds
                // the values heights[i] (x-axis of histogram) and
                // actual_positions[i] / sum_of_weights (y-axis of histogram)

for (std::size_t i = 0; i < this->histogram.size(); ++i)
                {
                    this->histogram[i] = std::make_pair(this->heights[i], numeric::fdiv(this->actual_positions[i], sum_of_weights(args)));
                }
            }

return make_iterator_range(this->histogram);
        }

// make this accumulator serializeable
        // TODO split to save/load and check on parameters provided in ctor
        template<class Archive>
        void serialize(Archive & ar, const unsigned int file_version)
        {
            ar & num_cells;
            ar & heights;
            ar & actual_positions;
            ar & desired_positions;
            ar & histogram;
            ar & is_dirty; 
        }

private:
        std::size_t num_cells;            // number of cells b
        array_type  heights;              // q_i
        array_type  actual_positions;     // n_i
        array_type  desired_positions;    // n'_i
        mutable histogram_type histogram; // histogram
        mutable bool is_dirty;
    };

} // namespace detail

///////////////////////////////////////////////////////////////////////////////
// tag::weighted_p_square_cumulative_distribution
//
namespace tag
{
    struct weighted_p_square_cumulative_distribution
      : depends_on<count, sum_of_weights>
      , p_square_cumulative_distribution_num_cells
    {
        typedef accumulators::impl::weighted_p_square_cumulative_distribution_impl<mpl::_1, mpl::_2> impl;
    };
}

///////////////////////////////////////////////////////////////////////////////
// extract::weighted_p_square_cumulative_distribution
//
namespace extract
{
    extractor<tag::weighted_p_square_cumulative_distribution> const weighted_p_square_cumulative_distribution = {};

BOOST_ACCUMULATORS_IGNORE_GLOBAL(weighted_p_square_cumulative_distribution)
}

using extract::weighted_p_square_cumulative_distribution;

}} // namespace boost::accumulators

#endif

cmd: