import numpy as np  
import os  
from scipy.spatial.distance import mahalanobis  
from collections import Counter   

# 学号和姓名  
id = "202210423111"  
name = ""  

def classify(input_vector, dataSet, labels, k=1):  
    """  
    KNN 分类算法，使用马氏距离。  
    """  
    # 计算协方差矩阵及其逆  
    cov_matrix = np.cov(dataSet.T)  
    if np.linalg.det(cov_matrix) == 0:  # 检查奇异矩阵  
        cov_matrix += np.eye(cov_matrix.shape[0]) * 1e-8  # 添加正则化  
    inv_cov_matrix = np.linalg.inv(cov_matrix)  
    
    # 计算马氏距离  
    distances = [mahalanobis(input_vector, point, inv_cov_matrix) for point in dataSet]  
    
    # 获取距离最近的 k 个样本的索引  
    k_indices = np.argsort(distances)[:k]  
      
    # 获取最近邻样本的标签  
    k_nearest_labels = [labels[i] for i in k_indices]  
      
    # 找出出现次数最多的标签  
    most_common = Counter(k_nearest_labels).most_common(1)[0][0]  
    
    return most_common  
  
def load_dataset(directory):  
    """  
    从文件夹中加载数据。  
    """  
    features = []  
    labels = []  
      
    # 遍历文件夹中的所有文件  
    for filename in os.listdir(directory):  
        if filename.endswith(".txt"):  # 假设文件是 .txt 格式  
            filepath = os.path.join(directory, filename)  
              
            try:  
                label = int(filename.split('_')[0])  
                image_vector = img_to_vector(filepath)  
                features.append(image_vector)  
                labels.append(label)  
            except Exception as e:  
                print(f"Error processing file {filepath}: {e}")  
      
    return np.array(features), np.array(labels)  
  
def img_to_vector(filename):  
    """  
    将二值图像转换为向量。  
    """  
    try:  
        with open(filename) as file:  
            lines = file.readlines()  
            image_vector = np.array([int(char) for line in lines for char in line.strip()])  
            return image_vector  
    except Exception as e:  
        print(f"Error reading file {filename}: {e}")  
        return np.zeros(1024)  # 假设有一个预期的向量长度，此处设为1024  

if __name__ == "__main__":  
    # 测试  
    train_data, train_labels = load_dataset("trainingDigits")  

    test_data = (  
        "00000000000000110000000000000000"  
        # ... (省略的测试数据)  
    )  
    predicted_label = classify(  
        np.array([int(char) for char in test_data]).reshape(1, 1024),  
        train_data,  
        train_labels,  
    )  

    print(f"预测的标签: {predicted_label}")