更新 function.py

function.py

@@ -56,12 +56,8 @@ def classify(input_vector, dataSet, labels, k=3):
     """
     if k > len(labels):
         raise ValueError("k 不能大于训练集样本数")
-    min_vals = dataSet.min(axis=0)  
-    max_vals = dataSet.max(axis=0)  
-    norm_dataSet = (dataSet - min_vals) / (max_vals - min_vals)  
-    norm_input_vector = (input_vector - min_vals) / (max_vals - min_vals)  
 
-    distances = np.linalg.norm(norm_dataSet - norm_input_vector, axis=1)  
+    distances = np.linalg.norm(dataSet - input_vector, axis=1)
     sorted_indices = distances.argsort()
     nearest_labels = np.array(labels)[sorted_indices[:k]]
     predicted_label = np.bincount(nearest_labels).argmax()
@@ -83,8 +79,10 @@ def load_dataset(directory):
     labels = []
     for filename in os.listdir(directory):
         if filename.endswith(".txt"):
+            # 提取文件名中的标签信息
             label = int(filename.split('_')[0])
             labels.append(label)
+            # 将图像文件转换为向量
             vector = img_to_vector(os.path.join(directory, filename))
             data.append(vector)
     return np.array(data), np.array(labels)
@@ -103,6 +101,7 @@ def img_to_vector(filename):
     """
     with open(filename, 'r') as f:
         lines = f.readlines()
+    # 将32x32的字符矩阵转换为长度为1024的一维数组
     vector = np.array([int(char) for line in lines for char in line.strip()])
     return vector