更新 function.py

function.py

@@ -41,61 +41,125 @@ name = "邓龙树"
 
 
 # 这里写自己的代码实现
-import numpy as np
-import os
-from collections import Counter
+import numpy as np  
+import os  
+from collections import Counter  
+  
+def classify(input_vector, dataSet, labels, k=1):  
+    """  
+    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)  
+    # 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  
+    count = Counter(k_nearest_labels)  
+    # 返回数量最多的类别标签  
+    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。  
+      
+    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):  
+            file_path = os.path.join(directory, file)  
+            feature_vector = img_to_vector(file_path)  
+            label = int(file.split('_')[0])  
+            feature_list.append(feature_vector)  
+            label_list.append(label)  
+        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。  
+      
+    参数:  
+    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  
+    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)  
 
-def classify(input_vector, dataSet, labels, k=1):  # 设置默认值 k=1
-    """使用 KNN 算法对输入样本进行分类。"""
-    # 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 = 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
-    count = Counter(k_nearest_labels)
-    # 返回数量最多的类别标签
-    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。"""
-    # 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)
-    return feature_matrix, label_array
-
-def img_to_vector(filename):
-    """将二值图像转换为向量。"""
-    # 读取文件内容并转换为整数数组
-    with open(filename, 'r') as file:
-        lines = file.readlines()
-    # 将每行的数字字符转换为整数，并使用 NumPy 的 reshape 方法转换为一维数组
-    vector = np.array([int(char) for line in lines for char in line.strip()]).reshape(1024,)
-    return vector
-
-if __name__ == "__main__":
+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 = (
         "00000000000000110000000000000000"
-        # ... (省略中间的行以节省空间)
+        "00000000000011111000000000000000"
+        "00000000000011111100000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111110000000000000"
+        "00000000001111111100000000000000"
+        "00000000011111111000000000000000"
+        "00000000111111111000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111110000000000000000"
+        "00000000111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111100000000000000000"
+        "00000001111111111111000000000000"
+        "00000001111111111111111000000000"
+        "00000001111111111111111100000000"
+        "00000011111111111111111110000000"
+        "00000011111111111111111110000000"
+        "00000001111111111111111110000000"
+        "00000001111111111111111110000000"
+        "00000000111111111100111111100000"
+        "00000000111111111000111111100000"
+        "00000000011111111001111111100000"
+        "00000000011111111111111111000000"
+        "00000000001111111111111111000000"
+        "00000000000111111111111111000000"
+        "00000000000011111111111100000000"
+        "00000000000001111111110000000000"
         "00000000000000000111100000000000"
     )
+
     predicted_label = classify(
         np.array([int(char) for char in test_data]).reshape(1, 1024),
         train_data,