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 = "202210423216"
+name = "李潼"
 
 
 """
@@ -39,9 +39,7 @@ name = "test_name"
 - int: 预测的分类标签。
 """
 
-
-# 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。
 
@@ -49,14 +47,24 @@ 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。
     """
+    dataSet_size = dataSet.shape[0]
+    diff_mat = np.tile(input_vector, (dataSet_size, 1)) - dataSet
+    sq_diff_mat = diff_mat ** 2
+    sq_distances = sq_diff_mat.sum(axis=1)
+    distances = sq_distances ** 0.5
+    sorted_dist_indices = np.argsort(distances)
+    class_count = {}
+    for i in range(k):
+        vote_label = labels[sorted_dist_indices[i]]
+        class_count[vote_label] = class_count.get(vote_label, 0) + 1
+    sorted_class_count = sorted(class_count.items(), key=lambda x: x[1], reverse=True)
+    return sorted_class_count[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**。
@@ -68,26 +76,20 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-
-
-# 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。
-
-    Returns:
-    - np.array: 二值图像向量。
-    """
-
+    training_files = os.listdir(directory)
+    features = []
+    labels = []
+    for file in training_files:
+        label = int(file.split('_')[0])
+        with open(os.path.join(directory, file), 'r') as f:
+            content = f.read().strip()
+            feature = [int(char) for char in content]
+            features.append(feature)
+            labels.append(label)
+    return np.array(features), np.array(labels)
 
 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"
@@ -101,31 +103,27 @@ if __name__ == "__main__":
         "00000000111111110000000000000000"
         "00000000111111110000000000000000"
         "00000000111111110000000000000000"
-        "00000000111111100000000000000000"
-        "00000001111111100000000000000000"
-        "00000001111111100000000000000000"
-        "00000001111111100000000000000000"
-        "00000001111111111111000000000000"
-        "00000001111111111111111000000000"
-        "00000001111111111111111100000000"
-        "00000011111111111111111110000000"
-        "00000011111111111111111110000000"
-        "00000001111111111111111110000000"
-        "00000001111111111111111110000000"
-        "00000000111111111100111111100000"
-        "00000000111111111000111111100000"
-        "00000000011111111001111111100000"
-        "00000000011111111111111111000000"
-        "00000000001111111111111111000000"
-        "00000000000111111111111111000000"
-        "00000000000011111111111100000000"
-        "00000000000001111111110000000000"
-        "00000000000000000111100000000000"
+        "00000000111111110000000000000000"
+        "00000001111111110000000000000000"
+        "00000001111111110000000000000000"
+        "00000001111111110000000000000000"
+        "00000001111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "11111111111111111111111111111111"
+        "1111111111111111111"
     )
     predicted_label = classify(
-        np.array([int(char) for char in test_data]).reshape(1, 1024),
+        np.array([int(char) for char in test_data]).reshape(-1, 64),
         train_data,
         train_labels,
     )
+    print(f"预测的标签： {predicted_label}")
+
+    )
 
     print(f"预测的标签: {predicted_label}")