simulator.cpp

//
// Created by martin on 25.11.18.
//


#include <iostream>
#include <cstdio>
#include <fstream>
#include <vector>
#include <utility>
#include <algorithm>
#include <assert.h>

#include "4neuro.h"
#include "../CrossValidator/CrossValidator.h"


int main(int argc, char** argv) {

    try {
        /* PHASE 1 - TRAINING DATA LOADING, NETWORK ASSEMBLY AND PARTICLE SWARM OPTIMIZATION */
        l4n::CSVReader reader1("/tmp/lib4neuro_pokus/simulator_input.txt", "\t", true);  // File, separator, skip 1st line
        reader1.read();  // Read from the file

        /* PHASE 1 - NEURAL NETWORK SPECIFICATION */
        /* Create data set for both the first training of the neural network */
        /* Specify which columns are inputs or outputs */
        std::vector<unsigned int> inputs1 = { 0 };  // Possible multiple inputs, e.g. {0,3}, column indices starting from 0
        std::vector<unsigned int> outputs1 = { 1 };  // Possible multiple outputs, e.g. {1,2}
        l4n::DataSet ds1 = reader1.get_data_set(&inputs1, &outputs1);  // Creation of data-set for NN
        ds1.normalize();  // Normalization of data to prevent numerical problems

        /* Numbers of neurons in layers (including input and output layers) */
        std::vector<unsigned int> neuron_numbers_in_layers = { 1, 3, 1 };

        /* Fully connected feed-forward network with linear activation functions for input and output */
        /* layers and the specified activation fns for the hidden ones (each entry = layer)*/
        std::vector<l4n::NEURON_TYPE> hidden_type_v = { l4n::NEURON_TYPE::LOGISTIC}; // hidden_type_v = {l4n::NEURON_TYPE::LOGISTIC, l4n::NEURON_TYPE::LINEAR}
        l4n::FullyConnectedFFN nn1(&neuron_numbers_in_layers, &hidden_type_v);

        /* Error function */
        l4n::MSE mse1(&nn1, &ds1);  // First parameter - neural network, second parameter - data-set

        /* Particle Swarm method domain*/
        std::vector<double> domain_bounds(2 * (nn1.get_n_weights() + nn1.get_n_biases()));
        for (size_t i = 0; i < domain_bounds.size() / 2; ++i) {
            domain_bounds[2 * i] = -10;
            domain_bounds[2 * i + 1] = 10;
        }

        // Parameters of the Particle Swarm
        // 1) domain_bounds Bounds for every optimized parameter (p1_lower, p1_upper, p2_lower, p2_upper...)
        // 2) c1 Cognitive parameter
        // 3) c2 Social parameter
        // 4) w Inertia weight
        // 5) gamma Threshold value for particle velocity - all particles must posses the same or slower velocity for the algorithm to end
        // 6) epsilon Radius of the cluster area (Euclidean distance)
        // 7) delta Amount of particles, which has to be in the cluster for the algorithm to stop (0-1)
        // 8) n_particles Number of particles in the swarm
        // 9) iter_max Maximal number of iterations - optimization will stop after that, even if not converged
        l4n::ParticleSwarm ps(&domain_bounds,
                              1.711897,
                              1.711897,
                              0.711897,
                              0.5,
                              0.3,
                              0.7,
                              150,
                              1500);

        /* Weight and bias randomization in the network accordingly to the uniform distribution */
        nn1.randomize_parameters();

        /* Particle Swarm optimization */
        ps.optimize(mse1);
        /* Save Neural network parameters to file */
        nn1.save_text("test_net_Particle_Swarm.4n");

        /* PHASE 3 - LOADING NN FROM FILE AND TRAINING NO 2 - GRADIENT DESCENT */

        l4n::NeuralNetwork nn2("test_net_Particle_Swarm.4n");
        /* Training data loading for the second phase */
        l4n::CSVReader reader2("/tmp/lib4neuro_pokus/simulator_input.txt", "\t", true);  // File, separator, skip 1st line
        reader2.read();  // Read from the file

        /* Create data set for both the first training of the neural network */
        /* Specify which columns are inputs or outputs */
        std::vector<unsigned int> inputs2 = { 0 };  // Possible multiple inputs, e.g. {0,3}, column indices starting from 0
        std::vector<unsigned int> outputs2 = { 1 };  // Possible multiple outputs, e.g. {1,2}
        l4n::DataSet ds2 = reader2.get_data_set(&inputs2, &outputs2);  // Creation of data-set for NN
        ds2.normalize();  // Normalization of data to prevent numerical problems

        /* Error function */
        l4n::MSE mse2(&nn2, &ds2);  // First parameter - neural network, second parameter - data-set

        // Parameters of the gradient descent
        // 1) Threshold for the successful ending of the optimization - deviation from minima
        // 2) Number of iterations to reset step size to tolerance/10.0
        // 3) Maximal number of iterations - optimization will stop after that, even if not converged
        l4n::GradientDescent gs(1e-4, 150, 200000);

        /* Gradient Descent Optimization */
        gs.optimize(mse2);  // Network training

        /* Save Neural network parameters to file */
        nn2.save_text("test_net_Gradient_Descent.4n");

        /* PHASE 4 - TESTING DATA */

        /* Output file specification */
        std::string filename = "simulator_output.txt";
        std::ofstream output_file(filename);
        if (!output_file.is_open()) {
            throw std::runtime_error("File '" + filename + "' can't be opened!");
        }

        /* Neural network loading */
        l4n::NeuralNetwork nn3("test_net_Gradient_Descent.4n");

        /* Check of the saved network - write to the file */
        output_file << std::endl << "The loaded network info:" << std::endl;
        nn3.write_stats(&output_file);
        nn3.write_weights(&output_file);
        nn3.write_biases(&output_file);

        /* Evaluate network on an arbitrary data-set and save results into the file */
        l4n::CSVReader reader3("/tmp/lib4neuro_pokus/simulator_input.txt", "\t", true);  // File, separator, skip 1st line
        reader3.read();  // Read from the file

        /* Create data set for both the testing of the neural network */
        /* Specify which columns are inputs or outputs */
        std::vector<unsigned int> inputs3 = { 0 };  // Possible multiple inputs, e.g. {0,3}, column indices starting from 0
        std::vector<unsigned int> outputs3 = { 1 };  // Possible multiple outputs, e.g. {1,2}

        l4n::DataSet ds3 = reader3.get_data_set(&inputs3, &outputs3);  // Creation of data-set for NN
        ds3.normalize();  // Normalization of data to prevent numerical problems

        output_file << std::endl << "Evaluating network on the dataset: " << std::endl;
        ds3.store_data_text(&output_file);

        output_file << "Output and the error:" << std::endl;

        /* Error function */
        l4n::MSE mse3(&nn3, &ds3);  // First parameter - neural network, second parameter - data-set

        std::cout << "Eval on normalized data:" << std::endl;
        mse3.eval_on_data_set(&ds3, &output_file);

        std::cout << "Eval on de-normalized data:" << std::endl;
        ds3.de_normalize();
        mse3.eval_on_data_set(&ds3, &output_file);

        /* Close the output file for writing */
        output_file.close();

        return 0;

    }
    catch (const std::exception& e) {
        std::cerr << e.what() << std::endl;
        exit(EXIT_FAILURE);
    }

}