From ea9e28dac6748ce0e1e8b69ca58393a22d0de3bd Mon Sep 17 00:00:00 2001
From: zhe <2904040094@qq.com>
Date: Wed, 23 Oct 2024 11:46:52 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 115 +++++++++++-----------------------------------------
 1 file changed, 23 insertions(+), 92 deletions(-)

diff --git a/function.py b/function.py
index 7faac63..103fa23 100644
--- a/function.py
+++ b/function.py
@@ -1,53 +1,20 @@
-# function.py
-import numpy as np
-import os
+import numpy as np  
+import os  
 from scipy.spatial.distance import mahalanobis  
-from collections import Counter 
-"""
-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。
+from collections import Counter   
 
-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。
+# 学号和姓名  
+id = "202210423111"  
+name = ""  
 
-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。
-"""
-
-
-# 这里写自己的代码实现
 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  
@@ -77,12 +44,8 @@ def load_dataset(directory):
             filepath = os.path.join(directory, filename)  
               
             try:  
-                # 假设文件名格式为 "数字_编号.txt"  
                 label = int(filename.split('_')[0])  
-                  
-                # 加载文件中的二进制数据并转换为 1D 向量  
                 image_vector = img_to_vector(filepath)  
-                  
                 features.append(image_vector)  
                 labels.append(label)  
             except Exception as e:  
@@ -98,55 +61,23 @@ 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  
     except Exception as e:  
         print(f"Error reading file {filename}: {e}")  
-        image_vector = np.zeros(expected_vector_length)  # 假设有一个预期的向量长度  
-        # 或者可以抛出一个异常，根据需求决定  
-      
-    return image_vector
+        return np.zeros(1024)  # 假设有一个预期的向量长度，此处设为1024  
 
-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")
+if __name__ == "__main__":  
+    # 测试  
+    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,
-    )
+    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}")
+    print(f"预测的标签: {predicted_label}")
\ No newline at end of file