更新 function.py

function.py

@@ -1,7 +1,7 @@
 # function.py
 import numpy as np
 import os
-
+from scipy.spatial import distance
 """
 实验说明:
 - 自行编写实现数据加载与 kNN 的手写数字分类算法。
@@ -25,10 +25,10 @@ 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 = "202210423224"
+name = "吴杨洋"
 
+ 
 """
 参数说明:
 - input_vector (numpy array): 输入待分类的样本。
@@ -40,8 +40,9 @@ 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 +50,33 @@ 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的欧氏距离
+    distances = [distance.euclidean(input_vector, row) for row in dataSet]
+    
+    # 获取距离最近的k个样本的索引
+    k_indices = np.argsort(distances)[:k]
+    
+    # 获取这些样本对应的标签
+    k_nearest_labels = [labels[index] for index in k_indices]
+    
+    # 统计每个类别的出现次数
+    class_count = {}
+    for vote in k_nearest_labels:
+        class_count[vote] = class_count.get(vote, 0) + 1
+    
+    # 预测的类别是出现次数最多的类别
+    predicted_class = max(class_count, key=class_count.get)
+    
+    return predicted_class
 
-
-# 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 +85,21 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
+    training_file_list = os.listdir(directory)
+    training_matrix = []
+    training_labels = []
+    
+    for file in training_file_list:
+        class_num = int(file.split('_')[0])
+        vector = img_to_vector(os.path.join(directory, file))
+        training_matrix.append(vector)
+        training_labels.append(class_num)
+    
+    return np.array(training_matrix), np.array(training_labels)
 
-
-# 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 +107,20 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
-
+    return_vec = np.zeros((1024,))
+    with open(filename) as fr:
+        lines = fr.readlines()
+        for i in range(32):
+            line_str = str(lines[i])
+            for j in range(32):
+                if line_str[j] == '1':
+                    return_vec[32*i + j] = 1
+                else:
+                    return_vec[32*i + j] = 0
+    return return_vec
 
 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"
-        "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}")
+    this_digit = img_to_vector('testDigits/0_13.txt')
+    test_result = classify(this_digit, train_data, train_labels)
+    print(test_result)

requirements.txt

@@ -1,2 +1,3 @@
 numpy==2.1.1
 requests==2.32.3
+scipy==1.13.1