From 42a492551b554819127dcbad67c2e42df55500b9 Mon Sep 17 00:00:00 2001
From: zhangchenghong <1598349064@qq.com>
Date: Sun, 20 Oct 2024 13:37:56 +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 | 36 +++++++++++++++++++++---------------
 1 file changed, 21 insertions(+), 15 deletions(-)

diff --git a/function.py b/function.py
index d2ed52e..aeea5fa 100644
--- a/function.py
+++ b/function.py
@@ -61,15 +61,22 @@ def classify(input_vector, dataSet, labels, k=2):
     - int: 预测的分类标签。  
     """  
     # 计算输入向量与训练集之间的欧氏距离
-    distances = np.sum((input_vector - dataSet) ** 2, axis=1) ** 0.5
-    # 根据距离排序并获取索引
+    distances = np.sum((input_vector - dataSet) ** 2, axis=1)
     sorted_indices = distances.argsort()
-    # 选择距离最近的k个点
-    k_nearest_labels = labels[sorted_indices[:k]].tolist()  # 将 NumPy 数组转换为列表
-    # 统计k个点中各类别的数量
-    count = Counter(k_nearest_labels)
-    # 返回数量最多的类别标签
-    return count.most_common(1)[0][0]
+    k_nearest_distances = distances[sorted_indices[:k]]
+    k_nearest_labels = labels[sorted_indices[:k]]
+
+    # 计算权重（距离的倒数）
+    weights = 1 / k_nearest_distances
+    # 归一化权重
+    weights /= weights.sum()
+
+    # 计算加权投票
+    weighted_votes = np.zeros((10,))
+    for label, weight in zip(k_nearest_labels, weights):
+        weighted_votes[label] += weight
+
+    return np.argmax(weighted_votes)
 
 # 这里也写自己的代码实现  
 def load_dataset(directory):  
@@ -83,22 +90,21 @@ def load_dataset(directory):
 	    - np.array: 特征数据（Mx1024）。  
 	    - np.array: 标签数据（Mx1）。  
     """  
-    # 初始化特征数据列表和标签列表
     feature_list = []
     label_list = []
-    # 遍历目录中的所有文件
     for file in os.listdir(directory):
-        # 获取文件的完整路径
         file_path = os.path.join(directory, file)
-        # 将图像文件转换为向量
         feature_vector = img_to_vector(file_path)
-        # 将特征向量添加到列表中
         feature_list.append(feature_vector)
-        # 获取文件名中的标签并添加到标签列表中
         label_list.append(int(file.split('_')[0]))
-    # 将特征列表和标签列表转换为numpy数组
     feature_matrix = np.array(feature_list)
     label_array = np.array(label_list)
+
+    # 特征缩放（归一化）
+    min_value = np.min(feature_matrix)
+    max_value = np.max(feature_matrix)
+    feature_matrix = (feature_matrix - min_value) / (max_value - min_value)
+
     return feature_matrix, label_array
 # 这里还写自己的代码实现  
 def img_to_vector(filename):