#include <iostream>
#include <vector>
#include <gsl/gsl_cdf.h>
#include <gsl/gsl_math.h>
#include "stratified_sampling.hpp"
#include <cmath>
#include <algorithm>
#include "opti.hpp"
#include "option.hpp"

using namespace std;

void exemple1_stratified() {
    vector<double> q = quantile_norm(10, 1);
    vector<double> p(10, 0.1);
    vector<gaussian_truncated> rvar;
    rvar.push_back(gaussian_truncated(GSL_NEGINF, q[0]));
    for (int i=1; i<10; i++){
        rvar.push_back(gaussian_truncated(q[i-1], q[i]));
    };
    stratified_sampling<gaussian_truncated> S(p,rvar);
    S.draw(100);
    double x = 1.64*S.estimator().second;
        cout<<"l'estimateur de la moyenne est :"<<S.estimator().first<<endl;
        cout<<"Son intervalle de confiance à 95% est :"<<"["<<S.estimator().first-(x/10)<<" ,"<<S.estimator().first+(x/10)<<"]"<<endl;
    S.draw(1000);
    x = 1.64*S.estimator().second;
        cout<<"l'estimateur de la moyenne est :"<<S.estimator().first<<endl;
        cout<<"Son intervalle de confiance à 95% est :"<<"["<<S.estimator().first-(x/sqrt(1100))<<" ,"<<S.estimator().first+(x/sqrt(1100))<<"]"<<endl;
    S.draw(10000);
    x = 1.64*S.estimator().second;
        cout<<"l'estimateur de la moyenne est :"<<S.estimator().first<<endl;
        cout<<"Son intervalle de confiance à 95% est :"<<"["<<S.estimator().first-(x/sqrt(11100))<<" ,"<<S.estimator().first+(x/sqrt(11100))<<"]"<<endl;
    
};


 void exemple2_stratified (){
     int d= 16;
     std::vector<double> mu(d);
     mu = argmax(0.05, 1.0, 50, 0.1, 45, d);
     double norm_mu = 0;
     std::vector<double> u(d);
     for(int i=0; i<d; i++) {
         norm_mu += mu[i]*mu[i];
     }
     for(int i=0; i<d; i++) {
         u[i] = mu[i]/sqrt(norm_mu);
     }
     vector<double> q = quantile_norm(100, 1);
     vector<double> p(100, 0.01);
     asian_option A(0.05, 1.0, 50, 0.1, d, 45);
     exponential_tilt<asian_option> G(mu, A);
     typedef compose_t<exponential_tilt<asian_option>, multi_gaussian_truncated> tilted_option;
     std::vector<tilted_option> X;
     X.push_back(compose(G, multi_gaussian_truncated(GSL_NEGINF,q[0], u)));
     for(int i=1; i<100; i++) {
         X.push_back(compose(G, multi_gaussian_truncated(q[i-1],q[i], u)));
     }
     for(int i=0; i<100; i=i+10){
         std::cout<<X[i]()<<endl;
     }
     stratified_sampling<tilted_option> S(p, X);
     S.draw(1000);
     cout<<"l'estimateur de la moyenne est :"<<S.estimator().first<<endl;
}

void exemple2_rqmc() {
    asian_option A(0.05, 1.0, 50.0, 0.1, 16, 45);
    int N= 10000;
    
    int d =16; 

    
    std::vector<double> result(3);
    result = monte_carlo(100, quasi_mean<asian_option, sobol> (N, d, A));
    for(int i =0; i<3; i++){
        std::cout<<result[i]<<std::endl;
    }
    
    std::vector<double> result2(3);
    result2 = monte_carlo(100, quasi_mean<asian_option, halton> (N, d, A));
    for(int i =0; i<3; i++){
        std::cout<<result2[i]<<std::endl;
    }
};


void exemple1_rqmc(){
    int N = 100;
    //comme quasi_gaussian retourne un vecteur, on doit composer avec f pour avoir le double QG()[0]
    std::function<double(std::vector<double>)> f = [](std::vector<double> x){return x[0];};
    std::vector<double> result(3);
    result = monte_carlo (100, quasi_mean<decltype(f), sobol> (N, 1, f));
    for(int i =0; i<3; i++){
        std::cout<<result[i]<<std::endl;
    }
};

int main()
{   
    init_alea(1);
    //exemple2_rqmc();
    //exemple1_stratified();
    exemple1_rqmc();  
    return 0;
    
}