更新 function.py

function.py

@@ -25,8 +25,8 @@ import os
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 """
-id = "202210423xxx"
-name = "test_name"
+id = "202210423105"
+name = "魏明帅"
 
 
 """
@@ -54,8 +54,23 @@ def classify(input_vector, dataSet, labels, k=0):
     Returns:
     - int: 预测的分类标签。
     """
-
-
+    """
+    欧式距离的 kNN 分类算法。
+    """
+     # 计算欧式距离
+    distances = np.linalg.norm(dataSet - input_vector, axis=1)
+    
+    # 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 = max(set(k_nearest_labels), key=k_nearest_labels.count)
+    
+    return most_common
+    
 # 这里也写自己的代码实现
 def load_dataset(directory):
     """
@@ -68,7 +83,24 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-
+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)
+            
+            # 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)
+    
+    return np.array(features), np.array(labels)
 
 # 这里还写自己的代码实现
 def img_to_vector(filename):
@@ -82,7 +114,11 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
-
+ 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
@@ -94,32 +130,32 @@ if __name__ == "__main__":
         "00000000000011111100000000000000"
         "00000000001111111110000000000000"
         "00000000001111111110000000000000"
-        "00000000001111111100000000000000"
+        "00000000001111000000000"
         "00000000011111111000000000000000"
-        "00000000111111111000000000000000"
+        "000000001111111110000000000000"
         "00000000111111110000000000000000"
         "00000000111111110000000000000000"
+        "0000000011111111000000000000"
         "00000000111111110000000000000000"
-        "00000000111111110000000000000000"
-        "00000000111111100000000000000000"
+        "0000000011111110000000000"
         "00000001111111100000000000000000"
         "00000001111111100000000000000000"
         "00000001111111100000000000000000"
         "00000001111111111111000000000000"
-        "00000001111111111111111000000000"
+        "0000000111111111000000000"
         "00000001111111111111111100000000"
         "00000011111111111111111110000000"
         "00000011111111111111111110000000"
-        "00000001111111111111111110000000"
+        "0000000111111110000000"
         "00000001111111111111111110000000"
         "00000000111111111100111111100000"
         "00000000111111111000111111100000"
-        "00000000011111111001111111100000"
-        "00000000011111111111111111000000"
+        "000000000111111110011100000"
+        "000000000111111111111000000"
         "00000000001111111111111111000000"
-        "00000000000111111111111111000000"
+        "00000000000111111111000000"
         "00000000000011111111111100000000"
-        "00000000000001111111110000000000"
+        "000000001110000000000"
         "00000000000000000111100000000000"
     )
     predicted_label = classify(