From 620afde54283ed70de400cf30f427ba1d28ef881 Mon Sep 17 00:00:00 2001
From: wzy <675163717@qq.com>
Date: Tue, 22 Oct 2024 19:50:10 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/function.py b/function.py
index 6a453bb..8cdca64 100644
--- a/function.py
+++ b/function.py
@@ -41,8 +41,10 @@ name = "万子玉"
 """
 
 # 这里写自己的代码实现
-def euclidean_distance(a, b):
-    return np.sqrt(np.sum((a - b) ** 2))
+def mahalanobis_distance(x, mean, inv_covmat):
+    delta = x - mean
+    m_dist = np.sqrt(np.dot(np.dot(delta, inv_covmat), delta.T))
+    return m_dist
 
 def classify(input_vector, dataSet, labels, k=2):
     """
@@ -57,7 +59,15 @@ def classify(input_vector, dataSet, labels, k=2):
     Returns:
     - int: 预测的分类标签。
     """
-    dists = [euclidean_distance(input_vector, data) for data in dataSet]
+    mean = np.mean(dataSet, axis=0)
+    covmat = np.cov(dataSet, rowvar=0)
+    inv_covmat = np.linalg.inv(covmat)
+    
+    dists = [mahalanobis_distance(input_vector, mean, inv_covmat)]
+    
+    for data in dataSet:
+        dists.append(mahalanobis_distance(data, mean, inv_covmat))
+    
     k_indices = np.argsort(dists)[:k]
     k_nearest_labels = [labels[i] for i in k_indices]
     
@@ -69,7 +79,7 @@ def classify(input_vector, dataSet, labels, k=2):
     if most_common:
         return most_common[0][0]
     else:
-        return None  # 或者 raise ValueError("No common labels found")
+        return None 
 
 
 # 这里也写自己的代码实现
@@ -156,4 +166,4 @@ if __name__ == "__main__":
         train_labels,
     )
 
-    print(f"预测的标签: {predicted_label}")
+    print(f"预测的标签: {predicted_label}")
\ No newline at end of file