From e651b192f7a7fac28a607a70376ad945ba3acb08 Mon Sep 17 00:00:00 2001
From: yuhaopan <1159526601@qq.com>
Date: Tue, 15 Oct 2024 20:43:50 +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 | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/function.py b/function.py
index 470a4df..9dcfdf1 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,6 @@
 # function.py
 import numpy as np
-from numpy.linalg import inv
+from numpy.linalg import inv,dot
 
 """
 挑战说明:
@@ -40,7 +40,7 @@ name = "潘宇豪"
 
 def classify0(inX, dataSet, labels, k=3):
     """
-    KNN 分类算法，使用马氏距离，并对特定的第64次错误实例进行修正。
+    KNN 分类算法。 
 
     参数:
     - inX (numpy array): 输入待分类的样本。
@@ -51,25 +51,24 @@ def classify0(inX, dataSet, labels, k=3):
     返回值:
     - int: 预测的分类标签。
     """
-    # 特定实例的手动修正
-    # 修正第64次测试错误,数据[5.56500e+03 9.73334e+00 9.77746e-01]被分类到3实际是2
-    if np.allclose(inX, [5.56500e+03, 9.73334e+00, 9.77746e-01], atol=1e-2):
-        return 2  # 返回正确分类
-
-    # 计算马氏距离
+    # 计算均值和协方差的逆
     mean = np.mean(dataSet, axis=0)
     cov_inv = inv(np.cov(dataSet, rowvar=False))
 
-    # 计算每个样本与输入样本的马氏距离
+    # 计算输入样本与每个训练样本之间的马氏距离
     diff = dataSet - inX
     distances = np.sqrt(np.einsum('ij,jk->i', diff, np.dot(cov_inv, diff.T)))
 
     # 找到最近的k个邻居
     sortedDistIndices = np.argsort(distances)[:k]
-    classCount = np.bincount(labels[sortedDistIndices].astype(int))
+    nearest_labels = labels[sortedDistIndices]
+
+    # 使用np.bincount统计类别出现次数
+    classCount = np.bincount(nearest_labels.astype(int))
 
     # 返回出现次数最多的类别
     return np.argmax(classCount)
+
  
 def load_data(file_path):
     """