更新 function.py

function.py

@@ -54,7 +54,7 @@ def classify(input_vector, dataSet, labels, k=3):
     Returns:
     - int: 预测的分类标签。
     """
-    # 计算欧氏距离
+     # 计算欧氏距离
     distances = np.linalg.norm(dataSet - input_vector, axis=1)
     # 获取距离最近的 k 个样本的索引
     nearest_neighbors_indices = distances.argsort()[:k]
@@ -79,12 +79,14 @@ def load_dataset(directory):
     labels = []
     data_list = []
     for filename in os.listdir(directory):
-        label = int(filename.split('_')[0])
-        labels.append(label)
-        vector = img_to_vector(os.path.join(directory, filename))
-        data_list.append(vector)
+        if filename.endswith(".txt"):  # 确保读取的是 txt 文件
+            label = int(filename.split('_')[0])
+            labels.append(label)
+            vector = img_to_vector(os.path.join(directory, filename))
+            data_list.append(vector)
     return np.array(data_list), np.array(labels)
 
+
 # 这里还写自己的代码实现
 def img_to_vector(filename):
     """
@@ -97,16 +99,15 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
-    with open(filename) as f:
+   with open(filename, 'r') as f:  # 确保使用文本模式读取
         lines = f.readlines()
-    vector = np.zeros((1, 1024))
+    vector = np.zeros((1024,), dtype=int)  # 将其改为 (1024,) 的一维数组
     for i in range(32):
         for j in range(32):
-            vector[0, 32 * i + j] = int(lines[i][j])
+            vector[32 * i + j] = int(lines[i][j])
     return 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 = (
@@ -143,10 +144,8 @@ if __name__ == "__main__":
         "00000000000001111111110000000000"
         "00000000000000000111100000000000"
     )
-    predicted_label = classify(
-        np.array([int(char) for char in test_data]).reshape(1, 1024),
-        train_data,
-        train_labels,
-    )
-
+    
+    test_vector = np.array([int(char) for char in test_data]).reshape(1, 1024)
+    
+    predicted_label = classify(test_vector, train_data, train_labels)
     print(f"预测的标签: {predicted_label}")