Perceptron算法—C语言

最新推荐文章于 2024-02-19 14:15:00 发布

YWonchall

最新推荐文章于 2024-02-19 14:15:00 发布

阅读量329

点赞数

分类专栏：机器学习-C语言文章标签：算法机器学习 python

本文链接：https://blog.csdn.net/weixin_45821421/article/details/110101203

版权

机器学习-C语言专栏收录该内容

4 篇文章 3 订阅

订阅专栏

本篇介绍第三个算法，感知机算法，同样仅介绍两个主要函数：预测函数和训练函数。

需要说明，本算法仍使用随机梯度下降算法，与上篇多元线性回归有很多相似之处。

算法介绍

激活函数可以如下表示：
$\sum_{i=1}^{n}weight_i×x_i$

阶跃函数
$p r e d i c t i o n = 1.0 I F a c t i v a t i o n \geq 0.0 E L S E 0.0$

函数

读取csv

以下三个函数分别为获取行数、获取列数、获取文本内容。

double **dataset;
int row,col;

int get_row(char *filename)//获取行数
{
	char line[1024];
	int i = 0;
	FILE* stream = fopen(filename, "r");
	while(fgets(line, 1024, stream)){
		i++;
	}
	fclose(stream);
	return i;
}

int get_col(char *filename)//获取列数
{
	char line[1024];
	int i = 0;
	FILE* stream = fopen(filename, "r");
	fgets(line, 1024, stream);
	char* token = strtok(line, ",");
	while(token){
		token = strtok(NULL, ",");
		i++;
	}
	fclose(stream);
	return i;
}

void get_two_dimension(char* line, double** data, char *filename)
{
	FILE* stream = fopen(filename, "r");
	int i = 0;
	while (fgets(line, 1024, stream))//逐行读取
    {
    	int j = 0;
    	char *tok;
        char* tmp = strdup(line);
        for (tok = strtok(line, ","); tok && *tok; j++, tok = strtok(NULL, ",\n")){
        	data[i][j] = atof(tok);//转换成浮点数
		}//字符串拆分操作
        i++;
        free(tmp);
    }
    fclose(stream);//文件打开后要进行关闭操作
}

EXAMPLE

int main()
{
	char filename[] = "data.csv";
    char line[1024];
    double **data;
    int row, col;
    row = get_row(filename);
    col = get_col(filename);
    data = (double **)malloc(row * sizeof(int *));
	for (int i = 0; i < row; ++i){
		data[i] = (double *)malloc(col * sizeof(double));
	}//动态申请二维数组
	get_two_dimension(line, data, filename);
	printf("row = %d\n", row);
	printf("col = %d\n", col);

	int i, j;
	for(i=0; i<row; i++){
		for(j=0; j<col; j++){

	float mean = (float)(sum / length);
	return mean;
}

随机梯度下降估计回归系数

更新方程：
$KaTeX parse error: Undefined control sequence: \ at position 29: …iction-expected\̲ ̲$

$b_1(t+1) = b_1(t) - learning\space rate × error(t) × x_1(t)$

$b_0(t+1) = b_0(t) - learning\space rate × error(t)$

// 参数为：数据集、每个数据集属性个数(带label)、权重、学习率、epoch、train_size
void train_weights(double **data, int col,double *weights, double l_rate, int n_epoch, int train_size) {
	int i;
	for (i = 0; i < n_epoch; i++) {
		int j = 0;//遍历每一行
		for (j = 0; j < train_size; j++) {
			double yhat = predict(col,data[j], weights);
			double err = data[j][col - 1] - yhat;
			weights[0] += l_rate * err;
			int k;
			for (k = 0; k < col - 1; k++) {
				weights[k + 1] += l_rate * err * data[j][k];
			}
		}
	}
	for (i = 0; i < col; i++) {
		printf("weights[%d]=%f\n",i, weights[i]);
	}
}

预测函数

// 参数：样本属性个数、样本、权重
double predict(int col,double *array, double *weights) {//预测某一行的值
	double activation = weights[0];
	int i;
	for (i = 0; i < col - 1; i++)
		activation += weights[i + 1] * array[i];
	double output = 0.0;
	if (activation >= 0.0)
		output = 1.0;
	else
		output = 0.0;
	return output;
}