更新 function.py

function.py

@@ -54,19 +54,19 @@ def classify(input_vector, dataSet, labels, k=3):
     Returns:
     - int: 预测的分类标签。
     """
-      # 计算输入向量与训练集中每个样本之间的欧氏距离  
-    distances = [np.sqrt(np.sum((x - input_vector) ** 2)) for x in dataSet]  
+   # 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]
     
-    # 获取这 k 个样本的标签  
+    # 获取最近邻样本的标签
     k_nearest_labels = [labels[i] for i in k_indices]
     
-    # 返回出现次数最多的标签  
-    from collections import Counter  
-    most_common = Counter(k_nearest_labels).most_common(1)  
-    return most_common[0][0]
+    # 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):
@@ -80,28 +80,24 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-    data = []  
+    features = []
     labels = []
-    directory="D:\\two"
-    try:  
-        files = os.listdir(directory)  
-        print("Files in the directory:", files)  
-    except FileNotFoundError:  
-        print(f"The directory '{directory}' does not exist.")  
-    except PermissionError:  
-        print(f"You do not have permission to access the directory '{directory}'.")  
-    except Exception as e:  
-        print(f"An unexpected error occurred: {e}")
+    
+    # 遍历文件夹中的所有文件
     for filename in os.listdir(directory):
-        if filename.endswith(".txt"):  
-            label = int(filename.split('_')[0])  # 假设文件名格式为 "label_xxx.txt"  
-            with open(os.path.join(directory, filename), 'r') as f:  
-                img_str = f.read().strip()  
-                img_vector = np.array([int(pixel) for pixel in img_str]).reshape(1, -1)  
-                data.append(img_vector.flatten())  # 将图像向量展平  
+        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(data), np.array(labels)
+    return np.array(features), np.array(labels)
 
 # 这里还写自己的代码实现
 def img_to_vector(filename):
@@ -116,10 +112,11 @@ def img_to_vector(filename):
     - np.array: 二值图像向量。
     """
   
-    with open(filename, 'r') as f:  
-        img_str = f.read().strip()  
-        img_vector = np.array([int(pixel) for pixel in img_str]).reshape(1, -1)  
-    return img_vector.flatten()
+        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