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 = "202210423209"
+name = "万子玉"
 
 
 """
@@ -41,7 +41,7 @@ name = "test_name"
 
 
 # 这里写自己的代码实现
-def classify(input_vector, dataSet, labels, k=0):
+def classify(input_vector, dataSet, labels, k=3):
     """
     KNN 分类算法。
 
@@ -54,6 +54,22 @@ def classify(input_vector, dataSet, labels, k=0):
     Returns:
     - int: 预测的分类标签。
     """
+    dists = [distance.euclidean(input_vector, data) for data in dataSet]
+    k_indices = np.argsort(dists)[:k]
+    k_nearest_labels = [labels[i] for i in k_indices]
+    
+    # 确保至少有一个近邻
+    if not k_nearest_labels:
+        raise ValueError("No neighbors found; possible causes: k is too small or all distances are the same.")
+    
+    most_common = Counter(k_nearest_labels).most_common(1)
+    
+    # 检查most_common是否为空
+    if most_common:
+        return most_common[0][0]
+    else:
+        # 如果为空，返回一个默认值或者抛出异常
+        return None  # 或者 raise ValueError("No common labels found")
 
 
 # 这里也写自己的代码实现
@@ -68,6 +84,15 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
+    data_list = []
+    label_list = []
+    for root, dirs, files in os.walk(directory):
+        for file in files:
+            file_path = os.path.join(root, file)
+            vector = img_to_vector(file_path)
+            data_list.append(vector)
+            label_list.append(int(file.split('_')[0]))
+    return np.array(data_list), np.array(label_list)
 
 
 # 这里还写自己的代码实现
@@ -82,6 +107,8 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
+     with open(filename, 'r') as f:
+        return np.array([int(char) for char in f.read().strip()]).reshape(1, -1)
 
 
 if __name__ == "__main__":