From 7593fcb68896955ef3604c69350af8d50eab32e0 Mon Sep 17 00:00:00 2001
From: cy <939601402@qq.com>
Date: Tue, 1 Oct 2024 20:25:37 +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 | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/function.py b/function.py
index 6871bda..c9162ac 100644
--- a/function.py
+++ b/function.py
@@ -41,7 +41,7 @@ name = "程悦"
 
 
 # 这里写自己的代码实现
-def classify0(inX, dataSet, labels, k=3):
+def classify0(inX, dataSet, labels, k=9):
     """
     KNN 分类算法。
 
@@ -54,20 +54,22 @@ def classify0(inX, dataSet, labels, k=3):
     Returns:
     - int: 预测的分类标签。
     """
-    
+    # 计算协方差矩阵并求逆矩阵
+    cov_matrix = np.cov(dataSet, rowvar=False)
+    inv_cov_matrix = np.linalg.inv(cov_matrix)
 
-    # 计算输入样本与训练集中每个样本的欧几里得距离
-    distances = distance.cdist(dataSet, [inX], metric='euclidean').flatten()
+    # 计算输入样本与训练集样本的马氏距离
+    distances = [distance.mahalanobis(inX, data_point, inv_cov_matrix) for data_point in dataSet]
 
-    # 按距离排序并选择前k个最小的距离
+    # 按距离排序并选择前 k 个最近的邻居
     k_indices = np.argsort(distances)[:k]
     k_nearest_labels = [labels[i] for i in k_indices]
 
-    # 计算多数标签
+    # 统计最近邻居中最多的标签
     label_counts = Counter(k_nearest_labels)
     most_common_label = label_counts.most_common(1)[0][0]
 
-    return most_common_label 
+    return most_common_label
 
 
 def load_data(file_path):