generalstatistics.hpp

/* -*- mode: c++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
 
/*
 Copyright (C) 2003 Ferdinando Ametrano
 Copyright (C) 2003 RiskMap srl
 
 This file is part of QuantLib, a free-software/open-source library
 for financial quantitative analysts and developers - http://quantlib.org/
 
 QuantLib is free software: you can redistribute it and/or modify it
 under the terms of the QuantLib license.  You should have received a
 copy of the license along with this program; if not, please email
 <quantlib-dev@lists.sf.net>. The license is also available online at
 <http://quantlib.org/license.shtml>.
 
 This program 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 license for more details.
*/
 
#ifndef quantlib_general_statistics_hpp
#define quantlib_general_statistics_hpp
 
#include <ql/utilities/null.hpp>
#include <ql/errors.hpp>
#include <vector>
#include <algorithm>
#include <utility>
 
namespace QuantLib {
 
 
    class GeneralStatistics {
      public:
        typedef Real value_type;
        GeneralStatistics();
 
 
        Size samples() const;
 
        const std::vector<std::pair<Real,Real> >& data() const;
 
        Real weightSum() const;
 
        Real mean() const;
 
        Real variance() const;
 
        Real standardDeviation() const;
 
        Real errorEstimate() const;
 
        Real skewness() const;
 
        Real kurtosis() const;
 
        Real min() const;
 
        Real max() const;
 
        template <class Func, class Predicate>
        std::pair<Real,Size> expectationValue(const Func& f,
                                              const Predicate& inRange) const {
            Real num = 0.0, den = 0.0;
            Size N = 0;
            std::vector<std::pair<Real,Real> >::const_iterator i;
            for (i=samples_.begin(); i!=samples_.end(); ++i) {
                Real x = i->first, w = i->second;
                if (inRange(x)) {
                    num += f(x)*w;
                    den += w;
                    N += 1;
                }
            }
            if (N == 0)
                return std::make_pair<Real,Size>(Null<Real>(),0);
            else
                return std::make_pair(num/den,N);
        }
 
        template <class Func>
        std::pair<Real,Size> expectationValue(const Func& f) const {
            return expectationValue(f, [](Real x) { return true; });
        }
        
        Real percentile(Real y) const;
 
        Real topPercentile(Real y) const;
 
 
 
        void add(Real value, Real weight = 1.0);
        template <class DataIterator>
        void addSequence(DataIterator begin, DataIterator end) {
            for (;begin!=end;++begin)
                add(*begin);
        }
        template <class DataIterator, class WeightIterator>
        void addSequence(DataIterator begin, DataIterator end,
                         WeightIterator wbegin) {
            for (;begin!=end;++begin,++wbegin)
                add(*begin, *wbegin);
        }
 
        void reset();
 
        void reserve(Size n) const;
 
        void sort() const;
      private:
        mutable std::vector<std::pair<Real,Real> > samples_;
        mutable bool sorted_;
    };
 
 
    // inline definitions
 
    inline GeneralStatistics::GeneralStatistics() {
        reset();
    }
 
    inline Size GeneralStatistics::samples() const {
        return samples_.size();
    }
 
    inline const std::vector<std::pair<Real,Real> >&
    GeneralStatistics::data() const {
        return samples_;
    }
 
    inline Real GeneralStatistics::standardDeviation() const {
        return std::sqrt(variance());
    }
 
    inline Real GeneralStatistics::errorEstimate() const {
        return std::sqrt(variance()/samples());
    }
 
    inline Real GeneralStatistics::min() const {
        QL_REQUIRE(samples() > 0, "empty sample set");
        return std::min_element(samples_.begin(),
                                samples_.end())->first;
    }
 
    inline Real GeneralStatistics::max() const {
        QL_REQUIRE(samples() > 0, "empty sample set");
        return std::max_element(samples_.begin(),
                                samples_.end())->first;
    }
 
    inline void GeneralStatistics::add(Real value, Real weight) {
        QL_REQUIRE(weight>=0.0, "negative weight not allowed");
        samples_.emplace_back(value, weight);
        sorted_ = false;
    }
 
    inline void GeneralStatistics::reset() {
        samples_ = std::vector<std::pair<Real,Real> >();
        sorted_ = true;
    }
 
    inline void GeneralStatistics::reserve(Size n) const {
        samples_.reserve(n);
    }
 
    inline void GeneralStatistics::sort() const {
        if (!sorted_) {
            std::sort(samples_.begin(), samples_.end());
            sorted_ = true;
        }
    }
 
}
 
 
#endif