更新 function.py

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 = "202210423217"
+name = "吴俊煯"
 
 
 """
@@ -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。
 
@@ -54,7 +54,14 @@ def classify(input_vector, dataSet, labels, k=0):
     Returns:
     - int: 预测的分类标签。
     """
+    if k > len(labels):
+        raise ValueError("k 不能大于训练集样本数")
 
+    distances = np.linalg.norm(dataSet - input_vector, axis=1)
+    sorted_indices = distances.argsort()
+    nearest_labels = np.array(labels)[sorted_indices[:k]]
+    predicted_label = np.bincount(nearest_labels).argmax()
+    return predicted_label
 
 # 这里也写自己的代码实现
 def load_dataset(directory):
@@ -68,7 +75,17 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-
+    data = []
+    labels = []
+    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)
 
 # 这里还写自己的代码实现
 def img_to_vector(filename):
@@ -82,50 +99,28 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
-
+    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__":
-    # 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
+    train_data, train_labels = load_dataset("E:\二值手写数字数据集 (1)\trainingDigits")
+    test_data, test_labels = load_dataset("E:\二值手写数字数据集 (1)\testDigits")
 
-    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,
-    )
+    # 记录预测的正确数量
+    correct_count = 0
 
-    print(f"预测的标签: {predicted_label}")
+    # 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}")
+
+        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}%")