From 7c8839246ce1a8e0d639c5f55bf0dc667f64a212 Mon Sep 17 00:00:00 2001
From: 202210423116 <2477589483@qq.com>
Date: Wed, 16 Oct 2024 21:04:40 +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 | 46 ++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 40 insertions(+), 6 deletions(-)

diff --git a/function.py b/function.py
index b1f8c16..2959a20 100644
--- a/function.py
+++ b/function.py
@@ -41,7 +41,7 @@ name = "test_name"
 
 
 # 这里写自己的代码实现
-def classify(input_vector, dataSet, labels, k=0):
+def classify(input_vector, dataSet, labels, k=3):
     """
     KNN 分类算法。
 
@@ -54,7 +54,22 @@ def classify(input_vector, dataSet, labels, k=0):
     Returns:
     - int: 预测的分类标签。
     """
-
+    """
+    使用欧式距离的 kNN 分类算法。
+    """
+     # 计算欧式距离
+    distances = np.linalg.norm(dataSet - input_vector, axis=1)
+    
+    # 获取距离最近的 k 个样本的索引
+    k_indices = np.argsort(distances)[:k]
+    
+    # 获取最近邻样本的标签
+    k_nearest_labels = [labels[i] for i in k_indices]
+    
+    # 找出出现次数最多的标签
+    most_common = max(set(k_nearest_labels), key=k_nearest_labels.count)
+    
+    return most_common
 
 # 这里也写自己的代码实现
 def load_dataset(directory):
@@ -68,7 +83,24 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-
+    features = []
+    labels = []
+    
+    # 遍历文件夹中的所有文件
+    for filename in os.listdir(directory):
+        if filename.endswith(".txt"):  # 假设文件是 .txt 格式
+            filepath = os.path.join(directory, filename)
+            
+            # 假设文件名格式为 "数字_编号.txt"
+            label = int(filename.split('_')[0])
+            
+            # 加载文件中的二进制数据并转换为 1D 向量
+            image_vector = img_to_vector(filepath)
+            
+            features.append(image_vector)
+            labels.append(label)
+    
+    return np.array(features), np.array(labels
 
 # 这里还写自己的代码实现
 def img_to_vector(filename):
@@ -82,9 +114,11 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
-
-
-if __name__ == "__main__":
+    with open(filename) as file:
+        lines = file.readlines()
+        image_vector = np.array([int(char) for line in lines for char in line.strip()])
+    
+    return image_vector
     # 以下代码可用于测试，可自行随意修改
     train_data, train_labels = load_dataset("trainingDigits")