更新 function.py

function.py

@@ -41,7 +41,7 @@ name = "熊浩燃"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, k=0):
+def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
 
@@ -54,19 +54,21 @@ def classify0(inX, dataSet, labels, k=0):
     Returns:
     - int: 预测的分类标签。
     """
-# 计算距离
-    distances = np.linalg.norm(dataSet - inX, axis=1)
+# 计算协方差矩阵的逆
+    cov_matrix = np.cov(dataSet, rowvar=False)
+    inv_cov_matrix = np.linalg.inv(cov_matrix)
     
-    # 获取距离最小的 k 个样本的索引
-    k_indices = np.argsort(distances)[:k]
+    # 计算马氏距离
+    diff = dataSet - inX
+    distances = np.sqrt(np.sum(diff @ inv_cov_matrix * diff, axis=1))
     
-    # 获取这 k 个样本的标签
-    k_nearest_labels = [labels[i] for i in k_indices]
+    # 按距离排序并返回 k 个最近的标签
+    sorted_indices = distances.argsort()
+    nearest_labels = [labels[i] for i in sorted_indices[:k]]
     
-    # 进行投票
-    most_common = np.bincount(k_nearest_labels).argmax()
-    
-    return most_common
+    # 找出出现次数最多的标签
+    label_counts = np.bincount(nearest_labels)
+    return label_counts.argmax()
 
 def load_data(file_path):
     """
@@ -80,11 +82,6 @@ def load_data(file_path):
 
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改
-
     train_file = "datingTrainSet2.tsv"
     train_data, train_labels = load_data(train_file)
-    
-    # 测试分类
-    sample = np.array([65915, 3.868359, 0.128078])
-    predicted_label = classify0(sample, train_data, train_labels)
-    print(f"Predicted label: {predicted_label}")
+    print(classify0(np.array([65915, 3.868359, 0.128078]), train_data, train_labels))