diff --git a/function.py b/function.py
index 0b1bff6..1a57eaf 100644
--- a/function.py
+++ b/function.py
@@ -53,23 +53,23 @@ def classify(input_vector, dataSet, labels, k=3):
     Returns:
     - int: 预测的分类标签。
     """
-    # 计算输入向量与数据集中每个向量之间的距离
-    distances = [np.linalg.norm(row-input_vector) for row in dataSet]
-    # 获取距离最小的k个样本的索引
-    sortedDistIndices = np.argsort(distances)
-    # 获取这些样本对应的标签
-    classCount = {}
-    for i in range(k):
-        voteLabel = labels[sortedDistIndices[i]]
-        # 统计每个类别的出现次数
-        classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
-    # 返回出现次数最多的类别
-    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
-    return sortedClassCount[0][0]
+    # 检查k的值是否大于训练集样本数，如果是，则抛出异常
+    if k > len(labels):
+        raise ValueError("k 不能大于训练集样本数")
+
+    # 计算输入向量与数据集中每个样本的欧几里得距离
+    distances = np.linalg.norm(dataSet - input_vector, axis=1)
+    # 获取距离最近的k个样本的索引
+    sorted_indices = distances.argsort()
+    # 获取这k个最近邻样本的标签
+    nearest_labels = np.array(labels)[sorted_indices[:k]]
+    # 统计这k个样本中出现次数最多的标签，并返回该标签作为预测结果
+    predicted_label = np.bincount(nearest_labels).argmax()
+    return predicted_label
 
 def load_dataset(directory):
     """
-    从文件夹中加载数据，若不自行正确实现，则无法通过评测，**不记录成绩**。
+    从文件夹中加载数据，若不自行正确实现，则无法通过评测，不记录成绩。
 
     Args:
     - directory (str): 数据文件夹路径。
@@ -78,25 +78,23 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-    fileList = os.listdir(directory)
-    numberOfFiles = len(fileList)
-    m = numberOfFiles
-    n = 1024  # 假设每个图像是32x32的
-    dataSet = np.zeros((m, n))  # 存储特征数据
-    labels = []  # 存储标签
-    for i in range(m):
-        filename = fileList[i]
-        filePath = os.path.join(directory, filename)
-        vector = img_to_vector(filePath)
-        dataSet[i, :] = vector
-        # 假设文件名的格式是"label01.txt"，其中label是标签
-        label = int(filename.split('.')[0][1])
-        labels.append(label)
-    return dataSet, np.array(labels)
+    data = []
+    labels = []
+    # 遍历文件夹中的所有文件
+    for filename in os.listdir(directory):
+        if filename.endswith(".txt"):
+            # 提取文件名中的标签信息
+            label = int(filename.split('_')[0])
+            labels.append(label)
+            # 将图像文件转换为向量
+            vector = img_to_vector(os.path.join(directory, filename))
+            data.append(vector)
+    return np.array(data), np.array(labels)
 
 def img_to_vector(filename):
     """
     将二值图像转换为向量。
+    该部分应为 load_dataset 函数的辅助子函数，可单独在这里实现，也可直接集成至 load_dataset 函数中。
 
     Args:
     - filename (str): 图像文件路径。
@@ -104,57 +102,29 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
-    returnVect = np.zeros((1, 1024))  # 假设图像是32x32的
-    with open(filename, 'r') as file:
-        lines = file.readlines()
-        index = 0
-        for line in lines:
-            for i in range(len(line)-1):
-                if line[i] == '1':
-                    returnVect[0, index] = 1
-                index += 1
-    return returnVect
+    with open(filename, 'r') as f:
+        lines = f.readlines()
+    # 将32x32的字符矩阵转换为长度为1024的一维数组
+    vector = np.array([int(char) for line in lines for char in line.strip()])
+    return vector
 
 if __name__ == "__main__":
-    train_data, train_labels = load_dataset("trainingDigits")
-    test_data = (
-        "00000000000000110000000000000000"
-        "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,
-        train_labels,
-    )
+    # 加载训练集和测试集
+    train_data, train_labels = load_dataset("D:\projects\机器学习_projects\实验\trainingDigits")
+    test_data, test_labels = load_dataset("D:\projects\机器学习_projects\实验\testDigits")
 
-    print(f"预测的标签: {predicted_label}")
\ No newline at end of file
+    # 记录预测的正确数量
+    correct_count = 0
+
+    # 遍历测试集，逐个样本进行分类
+    for i in range(len(test_data)):
+        predicted_label = classify(test_data[i], train_data, train_labels)
+        print(f"测试样本 {i+1} 的真实标签: {test_labels[i]}，预测标签: {predicted_label}")
+
+        # 如果预测正确，则正确数量加一
+        if predicted_label == test_labels[i]:
+            correct_count += 1
+
+    # 打印准确率
+    accuracy = correct_count / len(test_data) * 100
+    print(f"测试集的准确率: {accuracy:.2f}%")
\ No newline at end of file