DataSet.cpp

//
// Created by martin on 7/13/18.
//


#include "DataSetSerialization.h"

namespace lib4neuro {

    DataSet::DataSet(std::string file_path) {
        std::ifstream ifs(file_path);
        boost::archive::text_iarchive ia(ifs);
        ia >> *this;
        ifs.close();
    }

	DataSet::DataSet() {
		
	}

    DataSet::DataSet(std::vector<std::pair<std::vector<double>, std::vector<double>>> *data_ptr) {
        this->n_elements = data_ptr->size();
        this->data = *data_ptr;

        this->input_dim = this->data[0].first.size();
        this->output_dim = this->data[0].second.size();

        //TODO check the complete data set for input/output dimensions
    }

    DataSet::DataSet(double lower_bound, double upper_bound, unsigned int size, double output) {
        std::vector<std::pair<std::vector<double>, std::vector<double>>> new_data_vec;
        this->data = new_data_vec;
        this->n_elements = 0;
        this->input_dim = 1;
        this->output_dim = 1;

        this->add_isotropic_data(lower_bound, upper_bound, size, output);
    }

    DataSet::DataSet(std::vector<double> &bounds, unsigned int no_elems_in_one_dim,
                     std::vector<double> (*output_func)(std::vector<double> &), unsigned int output_dim) {
        std::vector<std::pair<std::vector<double>, std::vector<double>>> new_data_vec;
        this->data = new_data_vec;
        this->input_dim = bounds.size() / 2;
        this->output_dim = output_dim;
        this->n_elements = 0;

        this->add_isotropic_data(bounds, no_elems_in_one_dim, output_func);
    }


    void DataSet::add_data_pair(std::vector<double> &inputs, std::vector<double> &outputs) {
        if (inputs.size() != this->input_dim) {
            throw InvalidDimension("Bad input dimension.");
        } else if (outputs.size() != this->output_dim) {
            throw InvalidDimension("Bad output dimension.");
        }

        this->n_elements++;
        this->data.emplace_back(std::make_pair(inputs, outputs));
    }

    void DataSet::add_isotropic_data(double lower_bound, double upper_bound, unsigned int size, double output) {
        if (this->input_dim != 1 || this->output_dim != 1) {
            throw InvalidDimension("Cannot add data with dimensionality 1:1 when the data set "
                                   "is of different dimensionality!");
        }

        double frac = (upper_bound - lower_bound) / (size - 1);
        std::vector<double> inp, out;

        out = {output};

        for (unsigned int i = 0; i < size; ++i) {
            inp = {frac * i};
            this->data.emplace_back(std::make_pair(inp, out));
        }

        this->n_elements += size;
    }

    void DataSet::add_isotropic_data(std::vector<double> &bounds, unsigned int no_elems_in_one_dim,
                                     std::vector<double> (*output_func)(std::vector<double> &)) {
        // TODO add check of dataset dimensions

        std::vector<std::vector<double>> grid;
        std::vector<double> tmp;
        double frac;

        for (unsigned int i = 0; i < bounds.size(); i += 2) {
            frac = (bounds[i] + bounds[i + 1]) / (no_elems_in_one_dim - 1);
            tmp.clear();
            for (double j = bounds[i]; j <= bounds[i + 1]; j += frac) {
                tmp.emplace_back(j);
            }

            grid.emplace_back(tmp);
        }

        grid = this->cartesian_product(&grid);

        for (auto vec : grid) {
            this->n_elements++;
            this->data.emplace_back(std::make_pair(vec, output_func(vec)));
        }
    }

    std::vector<std::pair<std::vector<double>, std::vector<double>>> *DataSet::get_data() {
        return &(this->data);
    }

    size_t DataSet::get_n_elements() {
        return this->n_elements;
    }

    size_t DataSet::get_input_dim() {
        return this->input_dim;
    }

    size_t DataSet::get_output_dim() {
        return this->output_dim;
    }

    void DataSet::print_data() {
        if (n_elements) {
            for (auto p : this->data) {
                /* INPUT */
                for (auto v : std::get<0>(p)) {
                    std::cout << v << " ";
                }

                std::cout << "-> ";

                /* OUTPUT */
                for (auto v : std::get<1>(p)) {
                    std::cout << v << " ";
                }

                std::cout << std::endl;
            }
        }
    }

    void DataSet::store_text(std::string &file_path) {
        //TODO check if stream was successfully opened
        std::ofstream ofs(file_path);
        boost::archive::text_oarchive oa(ofs);
        oa << *this;
        ofs.close();
    }

    template<class T>
    std::vector<std::vector<T>> DataSet::cartesian_product(const std::vector<std::vector<T>> *v) {
        std::vector<std::vector<double>> v_combined_old, v_combined, v_tmp;
        std::vector<double> tmp;

        for (const auto &e : v->at(0)) {
            tmp = {e};
            v_combined.emplace_back(tmp);
        }

        for (unsigned int i = 1; i < v->size(); i++) {  // Iterate through remaining vectors of 'v'
            v_combined_old = v_combined;
            v_combined.clear();

            for (const auto &e : v->at(i)) {
                for (const auto &vec : v_combined_old) {
                    tmp = vec;
                    tmp.emplace_back(e);

                    /* Add only unique elements */
                    if (std::find(v_combined.begin(), v_combined.end(), tmp) == v_combined.end()) {
                        v_combined.emplace_back(tmp);
                    }
                }
            }
        }

        return v_combined;
    }

}