# function.py
import numpy as np  
import os  
from scipy.spatial.distance import mahalanobis  
  
"""
实验说明:
- 自行编写实现数据加载与 kNN 的手写数字分类算法。
- 函数输入: 待分类的样本 input_vector, 训练数据集 dataSet, 训练集对应的标签 labels。
- 函数返回: 预测的分类标签。

注意事项:
- 在 function.py 中实现 kNN 分类算法。
- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
- 自动评测脚本仅会加载 classify 和 load_data 函数，请勿修改函数名。
- 训练集和测试集需手动下载解压，并放入当前目录下。

测评环境:
- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
- OS: Ubuntu 22.04.4 LTS
- Python: 3.10.12
- numpy: 2.1.1
"""


"""
请在这里填写学号和姓名，不填写即成绩无效。
"""
id = "202210423111"
name = "李劲"


"""
参数说明:
- input_vector (numpy array): 输入待分类的样本。
- dataSet (numpy array): 训练数据集。
- labels (list or numpy array): 训练集对应的标签。
- k (int): kNN 算法参数，请**自行设置默认值**，评测时仅会使用其默认值，不修改默认值将**无法通过**评测，**成绩为零**。
返回值:
- int: 预测的分类标签。
"""

  
python
复制代码
	def classify(input_vector, dataSet, labels, k=3):  

	    cov_matrix = np.cov(dataSet, rowvar=False)  

	    inv_cov_matrix = np.linalg.inv(cov_matrix)  

	    diffMat = dataSet - input_vector  

	    left_term = np.dot(diffMat, inv_cov_matrix)  

	    mahalanobis_distances = np.sqrt(np.sum(left_term * diffMat, axis=1))  

	    k_indices = np.argsort(mahalanobis_distances)[:k]  

	    k_nearest_labels = [labels[i] for i in k_indices]  

	    most_common = max(set(k_nearest_labels), key=k_nearest_labels.count)  

	    return most_common
  
python
复制代码
	def load_dataset(directory):  

	    features = []  

	    labels = []  

	    for filename in os.listdir(directory):  

	        if filename.endswith(".txt"):  

	            filepath = os.path.join(directory, filename)  

	            label = int(filename.split('_')[0])  

	            image_vector = img_to_vector(filepath)  

	            features.append(image_vector)  

	            labels.append(label)  

	    return np.array(features), np.array(labels) 
  
python
复制代码
	def img_to_vector(filename):  

	    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

if __name__ == "__main__":
    # 以下代码可用于测试，可自行随意修改
    train_data, train_labels = load_dataset("trainingDigits")

    test_data = (
        "00000000000000110000000000000000"
        "00000000000011111000000000000000"
        "00000000000011111100000000000000"
        "00000000001111111110000000000000"
        "00000000001111111110000000000000"
        "00000000001111111100000000000000"
        "00000000011111111000000000000000"
        "00000000111111111000000000000000"
        "00000000111111110000000000000000"
        "00000000111111110000000000000000"
        "00000000111111110000000000000000"
        "00000000111111110000000000000000"
        "00000000111111100000000000000000"
        "00000001111111100000000000000000"
        "00000001111111100000000000000000"
        "00000001111111100000000000000000"
        "00000001111111111111000000000000"
        "00000001111111111111111000000000"
        "00000001111111111111111100000000"
        "00000011111111111111111110000000"
        "00000011111111111111111110000000"
        "00000001111111111111111110000000"
        "00000001111111111111111110000000"
        "00000000111111111100111111100000"
        "00000000111111111000111111100000"
        "00000000011111111001111111100000"
        "00000000011111111111111111000000"
        "00000000001111111111111111000000"
        "00000000000111111111111111000000"
        "00000000000011111111111100000000"
        "00000000000001111111110000000000"
        "00000000000000000111100000000000"
    )
    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}")