From c43e1615e85cdc2c6d17ca26cb7c9050ce4b95c1 Mon Sep 17 00:00:00 2001
From: cy <939601402@qq.com>
Date: Tue, 15 Oct 2024 19:54:50 +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 | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/function.py b/function.py
index bd59f45..784c2f5 100644
--- a/function.py
+++ b/function.py
@@ -1,7 +1,6 @@
 import numpy as np
 import os
 from sklearn.preprocessing import StandardScaler
-
 """
 实验说明:
 - 自行编写实现数据加载与 kNN 的手写数字分类算法。
@@ -43,11 +42,15 @@ def classify(input_vector, dataSet, labels, k=2):
     - int: 预测的分类标签。
     """
     dataSet_size = dataSet.shape[0]
-    # 计算欧氏距离
+    # 计算马氏距离
+    cov_matrix = np.cov(dataSet.T)
+    inv_cov_matrix = np.linalg.inv(cov_matrix)
     diff_mat = np.tile(input_vector, (dataSet_size, 1)) - dataSet
-    sq_diff_mat = diff_mat ** 2
-    sq_distances = sq_diff_mat.sum(axis=1)
-    distances = np.sqrt(sq_distances)
+    distances = []
+    for i in range(dataSet_size):
+        distance = np.sqrt(np.dot(np.dot(diff_mat[i], inv_cov_matrix), diff_mat[i].T))
+        distances.append(distance)
+    distances = np.array(distances)
     # 对距离进行排序
     sorted_indices = distances.argsort()
     class_count = {}
@@ -58,6 +61,7 @@ def classify(input_vector, dataSet, labels, k=2):
     return sorted_class_count[0][0]
 
 
+
 def img_to_vector(filename):
     """
     将二值图像转换为向量。
@@ -104,7 +108,6 @@ def load_dataset(directory):
 
 
 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 = (
@@ -146,5 +149,3 @@ if __name__ == "__main__":
         train_data,
         train_labels,
     )
-
-    print(f"预测的标签: {predicted_label}")
\ No newline at end of file