sy1

function.py

@@ -25,8 +25,8 @@ import os
 """
 请在这里填写学号和姓名，不填写即成绩无效。
 """
-id = "202210423xxx"
-name = "test_name"
+id = "202210423109"
+name = "孔祥芷"
 
 
 """
@@ -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。
     
@@ -49,17 +49,31 @@ def classify(input_vector, dataSet, labels, k=0):
     - input_vector (numpy array): 输入待分类的样本。
     - dataSet (numpy array): 训练数据集。
     - labels (list or numpy array): 训练集对应的标签。
-    - k (int): kNN 算法参数，请**自行设置默认值**，评测时仅会使用其默认值，不修改默认值将**无法通过**评测，**成绩为零**。
+    - k (int): kNN 算法参数，默认值为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欧式距离
+    diffMat = np.tile(input_vector, (dataSet.shape[0], 1)) - dataSet
+    sqDiffMat = diffMat**2
+    sqDistances = sqDiffMat.sum(axis=1)
+    distances = sqDistances**0.5
+    # 获取k个最近邻的索引
+    sortedDistIndices = distances.argsort()
+    classCount = {}
+    for i in range(k):
+        voteIlabel = labels[sortedDistIndices[i]]
+        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
+    # 以出现次数最多的类别作为预测类别
+    sortedClassCount = sorted(classCount.items(), key=lambda x: x[1], reverse=True)
+    return sortedClassCount[0][0]
+
 
 
-# 这里也写自己的代码实现
 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。
 
     Args:
     - directory (str): 数据文件夹路径。
@@ -68,13 +82,22 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
+    fileList = os.listdir(directory)  # 使用 os.listdir
+    numFiles = len(fileList)
+    trainingMat = np.zeros((numFiles, 1024))
+    hwLabels = []
+    for i in range(numFiles):
+        fileNameStr = fileList[i]
+        fileStr = fileNameStr.split(',')[0]
+        classNumStr = int(fileStr.split('_')[0])
+        hwLabels.append(classNumStr)
+        returnVect = img_to_vector(os.path.join(directory, fileNameStr))  # 使用 os.path.join
+        trainingMat[i, :] = returnVect
+    return trainingMat, np.array(hwLabels)
 
-
-# 这里还写自己的代码实现
 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。
@@ -82,50 +105,31 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
+    returnVect = np.zeros((1, 1024))
+    with open(filename, 'r') as fr:
+        for i in range(32):
+            lineStr = fr.readline()
+            for j in range(32):
+                returnVect[0, 32 * i + j] = int(lineStr[j])
+    return returnVect.flatten()
 
 
 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")
+    # 加载训练集和测试集数据
+    train_data, train_labels = load_dataset("C:\\Users\\kxz\\Desktop\\kxz\\ds\\ML\\sy1\\trainingDigits")
+    test_data, test_labels = load_dataset("C:\\Users\\kxz\\Desktop\\kxz\\ds\\ML\\sy1\\testDigits")
+
+    # Test the classifier
+    errorCount = 0.0
+    mTest = len(test_data)
+    for i in range(mTest):
+        vectorUnderTest = test_data[i, :]
+        classifierResult = classify(vectorUnderTest, train_data, train_labels, 3)
+        print(f"KNN classified as: {classifierResult}, Actual: {test_labels[i]}")
+        if (classifierResult != test_labels[i]):
+            errorCount += 1.0
+
+    print(f"\nError Count: {errorCount}")
+    print(f"\nAccuracy: {(1 - errorCount / float(mTest)) * 100}%")
 
-    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,
-    )
 
-    print(f"预测的标签: {predicted_label}")