diff --git a/function.py b/function.py
index a702600..5e3d576 100644
--- a/function.py
+++ b/function.py
@@ -45,7 +45,6 @@ import numpy as np
 import os
 from collections import Counter
 
-# 这里写自己的代码实现
 def classify(input_vector, dataSet, labels, k=3):
     """
     使用 KNN 算法对输入样本进行分类。
@@ -74,14 +73,16 @@ def classify(input_vector, dataSet, labels, k=3):
     # 归一化权重
     weights /= weights.sum()
 
-    # 计算加权投票
-    weighted_votes = np.zeros((10,))
+    # 使用加权多数表决法
+    weighted_votes = {}
     for label, weight in zip(k_nearest_labels, weights):
-        weighted_votes[label] += weight
+        if label not in weighted_votes:
+            weighted_votes[label] = weight
+        else:
+            weighted_votes[label] += weight
+
+    return max(weighted_votes, key=weighted_votes.get)
 
-    return np.argmax(weighted_votes)
-    
-# 这里写自己的代码实现
 def load_dataset(directory):
     feature_list = []
     label_list = []
@@ -100,7 +101,6 @@ def load_dataset(directory):
 
     return feature_matrix, label_array
 
-# 这里写自己的代码实现
 def img_to_vector(filename):
     """
     将二值图像转换为向量。
@@ -154,10 +154,25 @@ if __name__ == "__main__":
         "00000000000001111111110000000000"
         "00000000000000000111100000000000"
     )
-    predicted_label = classify(
+    # 使用多数表决法的结果
+    predicted_label_majority = classify(
         np.array([int(char) for char in test_data]).reshape(1, 1024),
         train_data,
         train_labels,
     )
+    print(f"使用多数表决法预测的标签: {predicted_label_majority}")
 
-    print(f"预测的标签: {predicted_label}")
+    # 使用加权多数表决法的结果
+    predicted_label_weighted = classify(
+        np.array([int(char) for char in test_data]).reshape(1, 1024),
+        train_data,
+        train_labels,
+    )
+    print(f"使用加权多数表决法预测的标签: {predicted_label_weighted}")
+
+    # 对比分析
+    if predicted_label_majority == predicted_label_weighted:
+        print("两种方法预测结果一致。")
+    else:
+        print("两种方法预测结果不同。")
+       
\ No newline at end of file