linreg.hpp

Go to the documentation of this file.

/*************************************************************************
 *
 *  Project
 *                         _____ _____  __  __ _____
 *                        / ____|  __ \|  \/  |  __ \
 *  ___  _ __   ___ _ __ | |  __| |__) | \  / | |__) |
 * / _ \| '_ \ / _ \ '_ \| | |_ |  ___/| |\/| |  ___/
 *| (_) | |_) |  __/ | | | |__| | |    | |  | | |
 * \___/| .__/ \___|_| |_|\_____|_|    |_|  |_|_|
 *      | |
 *      |_|
 *
 * Copyright (C) Akiel Aries, <akiel@akiel.org>, et al.
 *
 * This software is licensed as described in the file LICENSE, which
 * you should have received as part of this distribution. The terms
 * among other details are referenced in the official documentation
 * seen here : https://akielaries.github.io/openGPMP/ along with
 * important files seen in this project.
 *
 * You may opt to use, copy, modify, merge, publish, distribute
 * and/or sell copies of the Software, and permit persons to whom
 * the Software is furnished to do so, under the terms of the
 * LICENSE file. As this is an Open Source effort, all implementations
 * must be of the same methodology.
 *
 *
 *
 * This software is distributed on an AS IS basis, WITHOUT
 * WARRANTY OF ANY KIND, either express or implied.
 *
 ************************************************************************/
 
/*
 * Linear regression is a statistical method for modeling
 * relationships between a dependent variable with a given
 * independent variable. Multiple linear regression  follows
 * the same idea with multiple or a set of independent
 * variables.
 */
 
#ifndef LINREG_HPP
#define LINREG_HPP
#include "../core/datatable.hpp"
#include "../core/utils.hpp"
#include <cstdint>
#include <vector>
 
namespace gpmp {
 
namespace ml {
 
class LinearRegression {
  public:
    std::vector<long double> x;
    std::vector<long double> y;
    long double coeff;
    long double constant;
    long double sum_xy;
    long double sum_x;
    long double sum_y;
    long double sum_x_square;
    long double sum_y_square;
    std::vector<long double> x_train;
    std::vector<long double> y_train;
    std::vector<long double> x_test;
    std::vector<long double> y_test;
 
    LinearRegression();
 
    void calculate_coeffecient();
 
    void calculate_constant();
 
    int64_t data_size();
 
    long double return_coeffecient();
 
    long double return_constant();
 
    void best_fit();
 
    void get_input(const std::vector<long double> &x_data,
                   const std::vector<long double> &y_data);
 
    void get_input(const gpmp::core::DataTableStr &data,
                   const std::vector<std::string> &columns);
 
    void get_input(const char *file);
 
    void split_data(double test_size, unsigned int seed, bool shuffle);
 
    void show_data();
 
    long double predict(long double _x) const;
 
    long double predict(long double _x, const std::vector<long double> &x_data);
 
    long double error_in(long double num);
 
    long double error_in(long double num,
                         const std::vector<long double> &x_data,
                         const std::vector<long double> &y_data);
 
    long double error_square();
 
    long double mse(const std::vector<long double> &x_data,
                    const std::vector<long double> &y_data) const;
 
    long double r_sqrd(const std::vector<long double> &x_data,
                       const std::vector<long double> &y_data) const;
 
    int64_t num_rows(const char *input);
};
 
} // namespace ml
 
} // namespace gpmp
 
#endif