#include <iostream>
#include <fstream>
#include <sstream>
#include <vector>
#include <regex>
#include <cmath>
#include <limits>

using namespace std;

// 定义一个结构体来保存每一行的值
struct TargetData {
    int id;
    double x, y, width, height;
};

// 读取日志文件并提取目标数据
vector<TargetData> readLogFile(const string& filepath) {
    vector<TargetData> data;
    ifstream file(filepath);
    string line;

    // 正则表达式来匹配Target ID后的五个值
    regex targetRegex("Target ID: (-?\\d+),\\s*(-?\\d+),\\s*(-?\\d+),\\s*(-?\\d+),\\s*(-?\\d+)");

    while (getline(file, line)) {
        smatch matches;
        if (regex_search(line, matches, targetRegex)) {
            TargetData target;
            target.id = stoi(matches[1].str());
            target.x = stod(matches[2].str());
            target.y = stod(matches[3].str());
            target.width = stod(matches[4].str());
            target.height = stod(matches[5].str());

            data.push_back(target);
        }
    }
    return data;
}

// 清洗数据，去掉横坐标小于100或大于600的数据，以及极端值
void cleanData(vector<TargetData>& data, double n) {
    // 计算平均值
    double sum = 0;
    for (const auto& target : data) {
        sum += target.width;
    }
    double mean = sum / data.size();

    // 计算标准差
    double variance = 0;
    for (const auto& target : data) {
        variance += pow(target.width - mean, 2);
    }
    double stddev = sqrt(variance / data.size());

    // 根据误差系数范围n清洗数据
    vector<TargetData> cleanedData;
    for (const auto& target : data) {
        // 添加条件，去掉横坐标小于100或大于600的数据
        if (target.x >= 100 && target.x <= 600 &&
            abs(target.width - mean) <= n * stddev) {
            cleanedData.push_back(target);
        }
    }

    data = cleanedData;
}

// 用最小二乘法来计算线性回归的参数 (width = a * y + b)
void fitLinearModel(const vector<TargetData>& data, double& a, double& b) {
    int n = data.size();
    double sum_y = 0, sum_width = 0, sum_yy = 0, sum_yw = 0;

    // 计算所需的累加和
    for (const auto& target : data) {
        sum_y += target.y;
        sum_width += target.width;
        sum_yy += target.y * target.y;
        sum_yw += target.y * target.width;
    }

    // 计算线性回归的系数 a 和 b
    double denominator = n * sum_yy - sum_y * sum_y;
    if (denominator == 0) {
        a = 0;
        b = 0;
        return;
    }

    a = (n * sum_yw - sum_y * sum_width) / denominator;
    b = (sum_yy * sum_width - sum_y * sum_yw) / denominator;
}

// 输出拟合结果
void printFitEquation(double a, double b) {
    cout << "拟合结果: width = " << a << " * y + " << b << endl;
}

// 打印data中的所有数据
void printData(const vector<TargetData>& data) {
    for (const auto& target : data) {
        cout << "ID: " << target.id 
             << ", x: " << target.x 
             << ", y: " << target.y 
             << ", width: " << target.width 
             << ", height: " << target.height << endl;
    }
}


int main(int argc, char* argv[]) {
    if (argc < 3) {
        cout << "使用方法: " << argv[0] << " <日志文件路径> <误差系数范围>" << endl;
        return 1;
    }

    string logFilePath = argv[1];
    double n = stod(argv[2]);  // 误差系数范围

    // 读取日志文件中的目标数据
    vector<TargetData> data = readLogFile(logFilePath);

    // 数据清洗
    cleanData(data, n);

    // 打印清洗后的数据
    cout << "\n清洗后的数据:" << endl;
    printData(data);

    // 使用最小二乘法拟合数据
    double a, b;
    fitLinearModel(data, a, b);

    // 输出拟合的函数公式
    printFitEquation(a, b);

    return 0;
}