#include<iostream>
#include<fstream>
#include<opencv2/opencv.hpp>
#include<opencv2/highgui.hpp>
#include<opencv2/core.hpp>
#include<io.h>                          //api和結(jié)構(gòu)體
#include<string.h>
#include<string>
#include<sstream>                     //string 轉(zhuǎn) int 數(shù)據(jù)類型包含
using namespace std;
using namespace cv; 
void ergodicTest(string filename, string name);    //遍歷函數(shù)
string Image_Compression(string imgpath);          //壓縮圖片并返回字符串
void Bayes();                                     //貝葉斯分類器
int turn(char a);
void main()
{
	const char* filepath = "E:\\learn\\vsfile\\c++project\\pictureData\\train-images";
	ergodicTest(filepath, "train_num.txt");         //處理訓(xùn)練集
	const char* test_path = "E:\\learn\\vsfile\\c++project\\pictureData\\test-images";
	ergodicTest(test_path, "test_num.txt");
	Bayes();
 
} 
void ergodicTest(string filename, string name)       //遍歷并把路徑存到files
{
	string firstfilename = filename + "\\*.bmp";
	struct _finddata_t fileinfo;
	intptr_t handle;            //不能用long，因?yàn)榫葐栴}會導(dǎo)致訪問沖突,longlong也可
	string rout = "E:\\learn\\vsfile\\c++project\\pictureData\\" + name;
	ofstream file;
	file.open(rout, ios::out);
	handle = _findfirst(firstfilename.c_str(), &fileinfo);
	if (_findfirst(firstfilename.c_str(), &fileinfo) != -1)
	{
		do
		{
			file << fileinfo.name<<":"<< Image_Compression(filename + "\\" + fileinfo.name) << endl;
		} while (!_findnext(handle, &fileinfo));
		file.close();
		_findclose(handle);
	}
}
 
string Image_Compression(string imgpath)   //輸入圖片地址返回圖片二值像素字符
{
	Mat Image = imread(imgpath);               //輸入的圖片
	cvtColor(Image, Image, COLOR_BGR2GRAY);
	int Matrix[28][28];                        //將digitization轉(zhuǎn)化為字符串類型
	for (int row = 0; row < Image.rows; row++)  //把圖片的像素點(diǎn)傳給數(shù)組
		for (int col = 0; col < Image.cols; col++)
		{
			Matrix[row][col] = Image.at<uchar>(row, col);
		}
	string img_str = "";                   //用來存儲結(jié)果字符串
	int x = 0, y = 0;
	for (int k = 1; k < 50; k++)
	{
		int total = 0;
		for (int q = 0; q < 4; q++)
			for (int p = 0; p < 4; p++)
				if (Matrix[x + q][y + p] > 127) total += 1;
		y = (y + 4) % 28;
		if (total >= 6) img_str += '1';    //將28*28的圖片轉(zhuǎn)化為7*7即壓縮
		else img_str += '0';
		if (k % 7 == 0)
		{
			x += 4;
			y = 0;
		}
	}
	return img_str;
}
 
int turn(char a)  //這個函數(shù)是把string類型轉(zhuǎn)換成int類型
{
	stringstream str;
	int f = 1;
	str << a;
	str >> f;
	str.clear();
	return f;
}
 
void Bayes()
{
	ifstream data_test, data_train;     //從兩個數(shù)據(jù)字符串文件中取數(shù)據(jù)的文件流
	string temp;                        //中間暫存字符串的變量
	double count[10] = { 0 };                      //用來計(jì)數(shù)每個數(shù)字樣本1個數(shù)
	double probability[10][49] = { 0 };
	int t = 0;            //避免算數(shù)溢出
 
	for (int i = 0; i < 49; i++)    //按列處理訓(xùn)練樣本（每一個樣本數(shù)據(jù)長度位49位）
	{
		data_train.open("E:\\learn\\vsfile\\c++project\\pictureData\\train_num.txt");
		for (int j = 0; j < 1000; j++)   //按順序取一千次數(shù)據(jù)
		{
			getline(data_train, temp);    //順序取每一行數(shù)據(jù)			
			if (temp.length() == 57)   //本來長度是49，因?yàn)槲矣形募砸^文件名
			{
				t = i + 8;     //用t來代替i+8是因?yàn)閟tring的[]中沒有+-重載，好像是這樣
				if (turn(temp[t]) == 1) count[turn(temp[0])]++;         //相應(yīng)數(shù)字為1計(jì)數(shù)加1
				else continue;
			}
			else if(temp.length() == 58)
			{
				t = i + 9;   //有的文件名為8位有的為9位
				if (turn(temp[t]) == 1) count[turn(temp[0])]++;         //相應(yīng)數(shù)字
				else continue;
			}
		}
		data_train.close();  //一定要注意文件流打開和關(guān)閉的時(shí)機(jī)，打開和關(guān)閉一次之間是一次完整的遍歷（getline）
		for (int q = 0; q < 10; q++)
		{
			probability[q][i] =count[q] / 100.0;                //計(jì)算每個數(shù)字?jǐn)?shù)據(jù)樣本的每一位1的概率
			count[q] = 0;//循環(huán)還要使用count，所以要初始化
		}
	}
 
	double probab[10] = { 1,1,1,1,1,1,1,1,1,1 };     //該數(shù)組是這個數(shù)字的概率（10個數(shù)字）
	data_test.open("E:\\learn\\vsfile\\c++project\\pictureData\\test_num.txt");
	double temp_prob = 0;             //對比可能性的中間變量:概率
	int temp_num = -1;                //對比可能性的中間變量:數(shù)字
	bool flag = true;                 //標(biāo)志拒絕識別，假就拒絕
	int num_r = 0, num_f = 0, num_t = 0;   //分別表示拒絕，錯誤，正確
	for (int d = 0; d < 200; d++)    //200個測試樣本
	{
		for (int o = 0; o < 10; o++) probab[o] = 1;//初始化概率數(shù)組，雖然前面有初始化，但是我們循環(huán)會多次使用，所以我們要每循環(huán)一次初始化一次
		getline(data_test, temp);
		for (int y = 0; y < 10; y++)   //分別和每個數(shù)字得出一個概率，既該測試用例是這個數(shù)字的概率
		{
			for (int s = 0; s < 49; s++)  //49位對應(yīng)去累乘得到概率
			{
				if (temp.length() == 57)
				{
					t = s + 8;
					if (turn(temp[t]) == 1) probab[y] *=1+probability[y][s];        //加1是因?yàn)榱泓c(diǎn)幾越乘越小，不好比較，而且有的概率可能為0，
					else probab[y] *= 2 - probability[y][s]; //同樣的，為0的概率也要加上1
				}
				else
				{
					t = s + 9;
					if (turn(temp[t]) == 1) probab[y] *=1+probability[y][s];         //相應(yīng)數(shù)字
					else probab[y] *= (2 - probability[y][s]);
				}
			}
		}
 
		flag = true;         //標(biāo)志置位真
		temp_prob = 0;       //重置中間變量
		temp_num = -1;       //開始前不標(biāo)識為任何數(shù)值
		for (int l = 0; l < 10; l++)  //比較測試用例是某個數(shù)字的概率，確定最大的那個
		{
			if (probab[l] > temp_prob)
			{
				temp_prob = probab[l];
				temp_num = l;
				flag = true;          //不被拒絕
			}
			else if (probab[l] == temp_prob )
			{
				flag = false;          //拒絕識別
			}
		}
		if (!flag)
		{
			num_r++;
		}
		else
		{
			cout << temp[0] << " " << temp_num << endl;
			if (temp_num == turn(temp[0]))
			{
				cout << "識別為：" << temp_num << endl;
				num_t++;
			}
			else
			{
				cout << "識別錯誤！" << endl;
				num_f++;
			}
		}
	}
	data_test.close();
	cout << "拒絕識別率為：" << num_r / 200.0 << endl;
	cout << "正確識別率為：" << num_t / 200.0 << endl;
	cout << "錯誤識別率為：" << num_f / 200.0 << endl;
}