更新 function.py

function.py

@@ -1,6 +1,6 @@
-# function.py
 import numpy as np
 import os
+from concurrent.futures import ThreadPoolExecutor
 
 """
 实验说明:
@@ -43,7 +43,7 @@ name = "熊浩燃"
 # 这里写自己的代码实现
 def classify(input_vector, dataSet, labels, k=1):
     """
-    KNN 分类算法。
+    KNN 分类算法，使用多线程加速距离计算。
 
     Args:
     - input_vector (numpy array): 输入待分类的样本。
@@ -54,10 +54,15 @@ def classify(input_vector, dataSet, labels, k=1):
     Returns:
     - int: 预测的分类标签。
     """
-    # 计算欧氏距离
-    distances = np.linalg.norm(dataSet - input_vector, axis=1)
+    def calculate_distance(row):
+        return np.sum((row - input_vector) ** 2)
+    
+    # 使用多线程加速距离计算
+    with ThreadPoolExecutor() as executor:
+        distances = list(executor.map(calculate_distance, dataSet))
+    
     # 获取距离最近的 k 个样本的索引
-    nearest_neighbors_indices = distances.argsort()[:k]
+    nearest_neighbors_indices = np.argsort(distances)[:k]
     # 获取这些样本的标签
     nearest_labels = np.array(labels)[nearest_neighbors_indices]
     # 统计出现次数最多的标签并返回
@@ -78,12 +83,14 @@ def load_dataset(directory):
     """
     labels = []
     data_list = []
-    for filename in os.listdir(directory):
-        if filename.endswith(".txt"):  # 确保读取的是 txt 文件
-            label = int(filename.split('_')[0])
-            labels.append(label)
-            vector = img_to_vector(os.path.join(directory, filename))
-            data_list.append(vector)
+    filenames = [os.path.join(directory, f) for f in os.listdir(directory) if f.endswith(".txt")]
+    
+    for filename in filenames:
+        label = int(os.path.basename(filename).split('_')[0])
+        labels.append(label)
+        vector = img_to_vector(filename)
+        data_list.append(vector)
+    
     return np.array(data_list), np.array(labels)
 
 # 这里还写自己的代码实现
@@ -98,9 +105,9 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
-    with open(filename, 'r') as f:  # 确保使用文本模式读取
+    with open(filename, 'r') as f:
         lines = f.readlines()
-    vector = np.zeros((1024,), dtype=int)  # 将其改为 (1024,) 的一维数组
+    vector = np.zeros((1024,), dtype=np.uint8)  # 使用更小的类型节省内存
     for i in range(32):
         for j in range(32):
             vector[32 * i + j] = int(lines[i][j])
@@ -149,4 +156,4 @@ if __name__ == "__main__":
     test_vector = np.array([int(char) for char in test_data]).reshape(1, 1024)
     
     predicted_label = classify(test_vector, train_data, train_labels)
-    print(f"预测的标签: {predicted_label}")
+    print(f"预测的标签: {predicted_label}")