更新 function.py

function.py

@@ -45,23 +45,12 @@ import numpy as np
 import os
 from collections import Counter
 
-def classify(input_vector, dataSet, labels, k=1):  
+def classify(input_vector, dataSet, labels, k=3):  # 设置默认值 k=3
-    """  
+    """使用 KNN 算法对输入样本进行分类。"""
-    使用 KNN 算法对输入样本进行分类。  
-      
-    参数:  
-    input_vector (ndarray): 输入的特征向量，形状为 (1, n_features)。  
-    dataSet (ndarray): 训练集特征矩阵，形状为 (m_samples, n_features)。  
-    labels (ndarray): 训练集标签数组，形状为 (m_samples,)。  
-    k (int): 选择最近邻的个数，默认为 1。  
-      
-    返回:  
-    int: 预测的类别标签。  
-    """  
     # 计算输入向量与训练集之间的欧氏距离
     distances = np.linalg.norm(dataSet - input_vector, axis=1)
     # 根据距离排序并获取索引
-    sorted_indices = np.argsort(distances)  
+    sorted_indices = distances.argsort()
     # 选择距离最近的k个点
     k_nearest_labels = labels[sorted_indices[:k]]
     # 统计k个点中各类别的数量
@@ -70,62 +59,30 @@ def classify(input_vector, dataSet, labels, k=1):
     return count.most_common(1)[0][0]
 
 def load_dataset(directory):
-    """  
+    """加载数据集中的图像，并将其转换为特征向量和标签。"""
-    加载数据集中的图像，并将其转换为特征向量和标签。  
-      
-    参数:  
-    directory (str): 包含图像文件的目录路径。  
-      
-    返回:  
-    tuple: 包含特征矩阵 (ndarray) 和标签数组 (ndarray) 的元组。  
-    """  
     feature_list = []
     label_list = []
-    try:  
+    for file in os.listdir(directory):
-        for file in os.listdir(directory):  
+        file_path = os.path.join(directory, file)
-            file_path = os.path.join(directory, file)  
+        feature_vector = img_to_vector(file_path)
-            feature_vector = img_to_vector(file_path)  
+        feature_list.append(feature_vector)
-            label = int(file.split('_')[0])  
+        label_list.append(int(file.split('_')[0]))
-            feature_list.append(feature_vector)  
+    feature_matrix = np.array(feature_list)
-            label_list.append(label)  
+    label_array = np.array(label_list)
-        feature_matrix = np.array(feature_list)  
-        label_array = np.array(label_list)  
-    except Exception as e:  
-        print(f"Error loading dataset: {e}")  
-        return None, None  
     return feature_matrix, label_array
 
 def img_to_vector(filename):
-    """  
+    """将二值图像转换为向量。"""
-    将二值图像转换为向量。  
+    with open(filename, 'r') as file:
-      
+        lines = file.read().strip()
-    参数:  
+    vector = np.array(list(map(int, lines))).reshape(1024,)
-    filename (str): 图像文件的路径。  
-      
-    返回:  
-    ndarray: 转换后的特征向量，形状为 (1024,)。  
-    """  
-    try:  
-        with open(filename, 'r') as file:  
-            lines = file.readlines()  
-        vector = np.array([int(char) for line in lines for char in line.strip()]).reshape(1024,)  
-    except Exception as e:  
-        print(f"Error converting image to vector: {e}")  
-        return None  
     return vector
 
 if __name__ == "__main__":
-    # 加载训练数据集  
+    # 测试代码
-    train_data, train_labels = load_dataset("trainingDigits")  
-    if train_data is None or train_labels is None:  
-        print("Failed to load training data.")  
-        exit(1)  
-
-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 = (
+    test_data_str = (
         "00000000000000110000000000000000"
         "00000000000011111000000000000000"
         "00000000000011111100000000000000"
@@ -159,12 +116,6 @@ if __name__ == "__main__"：
         "00000000000001111111110000000000"
         "00000000000000000111100000000000"
     )
-
+    test_data = np.array(list(map(int, test_data_str))).reshape(1, 1024)
-    predicted_label = classify(
+    predicted_label = classify(test_data, train_data, train_labels)
-        np.array([int(char) for char in test_data]).reshape(1, 1024),
-        train_data,
-        train_labels,
-    )
-
     print(f"预测的标签: {predicted_label}")
-