ErrorFunctions.cpp

//
// Created by martin on 7/15/18.
//

#include <vector>
#include <cmath>
#include <boost/random/mersenne_twister.hpp>
#include <boost/random/uniform_int_distribution.hpp>

#include "ErrorFunctions.h"

namespace lib4neuro {

    size_t ErrorFunction::get_dimension() {
        return this->dimension;
    }

    NeuralNetwork* ErrorFunction::get_network_instance() {
        return this->net;
    }

    void ErrorFunction::divide_data_train_test(double percent_test) {
        size_t ds_size = this->ds->get_n_elements();

        /* Store the full data set */
        this->ds_full = this->ds;

        /* Choose random subset of the DataSet for training and the remaining part for validation */
        boost::random::mt19937 gen;
        boost::random::uniform_int_distribution<> dist(0, ds_size - 1);

        size_t test_set_size = ceil(ds_size * percent_test);

        std::vector<unsigned int> test_indices;
        test_indices.reserve(test_set_size);
        for (unsigned int i = 0; i < test_set_size; i++) {
            test_indices.emplace_back(dist(gen));
        }
        std::sort(test_indices.begin(), test_indices.end(), std::greater<unsigned int>());

        std::vector<std::pair<std::vector<double>, std::vector<double>>> test_data, train_data;

        /* Copy all the data to train_data */
        for(auto e : *this->ds_full->get_data()) {
            train_data.emplace_back(e);
        }

        /* Move the testing data from train_data to test_data */
        for(auto ind : test_indices) {
            test_data.emplace_back(train_data.at(ind));
            train_data.erase(train_data.begin() + ind);
        }

        /* Re-initialize data set for training */
        this->ds = new DataSet(&train_data, this->ds_full->get_normalization_strategy());

        /* Initialize test data */
        this->ds_test = new DataSet(&test_data, this->ds_full->get_normalization_strategy());
    }

    void ErrorFunction::return_full_data_set_for_training() {
        if(this->ds_test) {
            this->ds = this->ds_full;
        }
    }

    MSE::MSE(NeuralNetwork *net, DataSet *ds) {
        this->net = net;
        this->ds = ds;
        this->dimension = net->get_n_weights() + net->get_n_biases();
    }

    double MSE::eval_general(DataSet* data_set, std::vector<double> *weights) {
        size_t dim_out = data_set->get_output_dim();
        size_t n_elements = data_set->get_n_elements();
        double error = 0.0, val;

        std::vector<std::pair<std::vector<double>, std::vector<double>>>* data = data_set->get_data();

        //TODO instead use something smarter
        std::vector<double> output(dim_out);

        for (auto el: *data) {  // Iterate through every element in the test set

            this->net->eval_single(el.first,
                                   output,
                                   weights);  // Compute the net output and store it into 'output' variable

            for (size_t j = 0; j < dim_out; ++j) {  // Compute difference for every element of the output vector
                val = output[j] - el.second[j];
                error += val * val;
            }
        }
        return error / n_elements;
    }

    double MSE::eval(std::vector<double> *weights) {
        size_t dim_out = this->ds->get_output_dim();
//    unsigned int dim_in = this->ds->get_input_dim();
        size_t n_elements = this->ds->get_n_elements();
        double error = 0.0, val;

        std::vector<std::pair<std::vector<double>, std::vector<double>>> *data = this->ds->get_data();

//    //TODO instead use something smarter
//    this->net->copy_weights(weights);

        std::vector<double> output(dim_out);

        for (auto el: *data) {  // Iterate through every element in the test set

            this->net->eval_single(el.first, output,
                                   weights);  // Compute the net output and store it into 'output' variable

            for (size_t j = 0; j < dim_out; ++j) {  // Compute difference for every element of the output vector

                val = output[j] - el.second[j];
                error += val * val;
            }
        }
        return error / n_elements;
    }

    double MSE::eval_on_test_data(std::vector<double> *weights) {
        return this->eval_general(this->ds_test, weights);
    }

//    void MSE::calculate_error_gradient(std::vector<double> &params, std::vector<double> &grad, double alpha) {
//
//        size_t dim_out = this->ds->get_output_dim();
//        size_t n_elements = this->ds->get_n_elements();
//
//        std::vector<std::pair<std::vector<double>, std::vector<double>>> *data = this->ds->get_data();
//
//        std::vector<double> error_derivative(dim_out);
//
//
//        for (auto el: *data) {  // Iterate through every element in the test set
//
//            this->net->eval_single(el.first, error_derivative,
//                                   &params);  // Compute the net output and store it into 'output' variable
//
//            for (size_t j = 0; j < dim_out; ++j) {
//                error_derivative[j] = 2.0 * (error_derivative[j] - el.second[j]); //real - expected result
//            }
//
//            this->net->add_to_gradient_single(el.first, error_derivative, alpha / n_elements, grad);
//        }
//    }

    void MSE::calculate_error_gradient(std::vector<double> &params, std::vector<double> &grad, double alpha, size_t batch) {

        size_t dim_out = this->ds->get_output_dim();
        size_t n_elements = this->ds->get_n_elements();
        std::vector<std::pair<std::vector<double>, std::vector<double>>> *data = this->ds->get_data();

        if(batch) {
            *data = this->ds->get_random_data_batch(batch);
            n_elements = data->size();
        }
        std::vector<double> error_derivative(dim_out);


        for (auto el: *data) {  // Iterate through every element in the test set

            this->net->eval_single(el.first, error_derivative,
                                   &params);  // Compute the net output and store it into 'output' variable

            for (size_t j = 0; j < dim_out; ++j) {
                error_derivative[j] = 2.0 * (error_derivative[j] - el.second[j]); //real - expected result
            }

            this->net->add_to_gradient_single(el.first, error_derivative, alpha / n_elements, grad);
        }
    }

    std::vector<double> *MSE::get_parameters() {
        std::vector<double> *output = new std::vector<double>(this->net->get_n_weights() + this->net->get_n_biases());

        size_t i = 0;

        for (auto el: *this->net->get_parameter_ptr_weights()) {
            output->at(i) = el;
            ++i;
        }

        for (auto el: *this->net->get_parameter_ptr_biases()) {
            output->at(i) = el;
            ++i;
        }

        return output;
    }

    ErrorSum::ErrorSum() {
        this->summand = nullptr;
        this->summand_coefficient = nullptr;
        this->dimension = 0;
    }

    ErrorSum::~ErrorSum() {
        if (this->summand) {
            delete this->summand;
        }
        if (this->summand_coefficient) {
            delete this->summand_coefficient;
        }
    }

    double ErrorSum::eval_on_test_data(std::vector<double>* weights) {
        //TODO take care of the case, when there are no test data

        double output = 0.0;
        ErrorFunction *ef = nullptr;

        for(unsigned int i = 0; i < this->summand->size(); ++i) {
            ef = this->summand->at(i);

            if (ef) {
                output += ef->eval_on_test_data(weights) * this->summand_coefficient->at(i);
            }
        }

        return output;
    }

    double ErrorSum::eval(std::vector<double>* weights) {
        double output = 0.0;
        ErrorFunction *ef = nullptr;

        for (unsigned int i = 0; i < this->summand->size(); ++i) {
            ef = this->summand->at(i);

            if (ef) {
                output += ef->eval(weights) * this->summand_coefficient->at(i);
            }
        }

        return output;
    }

    void ErrorSum::calculate_error_gradient(std::vector<double> &params, std::vector<double> &grad, double alpha, size_t batch) {

        ErrorFunction *ef = nullptr;
        for (size_t i = 0; i < this->summand->size(); ++i) {
            ef = this->summand->at(i);

            if (ef) {
                ef->calculate_error_gradient(params, grad, this->summand_coefficient->at(i) * alpha, batch);
            }
        }
    }

    void ErrorSum::add_error_function(ErrorFunction *F, double alpha) {
        if (!this->summand) {
            this->summand = new std::vector<ErrorFunction *>(0);
        }
        this->summand->push_back(F);

        if (!this->summand_coefficient) {
            this->summand_coefficient = new std::vector<double>(0);
        }
        this->summand_coefficient->push_back(alpha);

        if (F) {
            if (F->get_dimension() > this->dimension) {
                this->dimension = F->get_dimension();
            }
        }
    }

    size_t ErrorSum::get_dimension() {
//    if(!this->dimension) {
//        size_t max = 0;
//        for(auto e : *this->summand) {
//            if(e->get_dimension() > max) {
//                max = e->get_dimension();
//            }
//        };
//
//        this->dimension = max;
//    }
        return this->dimension;
    }

    std::vector<double> *ErrorSum::get_parameters() {
        return this->summand->at(0)->get_parameters();
    }

}