更新 function.py

function.py

@@ -43,14 +43,30 @@ name = "陈垣豪"
 
 # 这里写自己的代码实现
 def classify(input_vector, dataSet, labels, k=3):
-    distances = np.sum((dataSet - input_vector) ** 2, axis=1)
+    # 计算协方差矩阵的逆
+    cov_matrix = np.cov(dataSet.T)
+    cov_inv = np.linalg.inv(cov_matrix)
+
+    #计算马氏距离
+    distances_squared = np.array([
+        (input_vector - point).dot(cov_inv).dot((input_vector - point).T)
+        for point in dataSet
+    ])
+    
+    # 获取最近k个样本的索引
     nearest_indices = np.argsort(distances)[:k]
     nearest_labels = [labels[i] for i in nearest_indices]
-    most_common_label = Counter(nearest_labels).most_common(1)[0][0]
-    return most_common_label
+    
+    # 根据距离加权投票
+    weights = 1 / (distances[nearest_indices] + 1e-10)  # 避免除零
+    weight_counts = Counter()
+    
+    for label, weight in zip(nearest_labels, weights):
+        weight_counts[label] += weight
 
+    # 返回加权投票结果
+    return weight_counts.most_common(1)[0][0]
 
-# 这里也写自己的代码实现
 def load_dataset(directory):
     file_list = os.listdir(directory)
     num_files = len(file_list)
@@ -64,8 +80,6 @@ def load_dataset(directory):
 
     return dataSet, np.array(labels)
 
-
-# 这里还写自己的代码实现
 def img_to_vector(filename):
     return_vector = np.zeros((1, 1024))
     with open(filename) as f:
@@ -76,7 +90,6 @@ def img_to_vector(filename):
     return 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 = (
@@ -113,10 +126,11 @@ if __name__ == "__main__":
         "00000000000001111111110000000000"
         "00000000000000000111100000000000"
     )
+    
     predicted_label = classify(
         np.array([int(char) for char in test_data]).reshape(1, 1024),
         train_data,
         train_labels,
     )
 
-    print(f"预测的标签: {predicted_label}")
+    print(f"预测的标签: {predicted_label}")