更新 function.py

function.py

@@ -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 +54,15 @@ def classify(input_vector, dataSet, labels, k=0):
     Returns:
     - int: 预测的分类标签。
     """
-
+    # 计算欧氏距离
+    distances = np.linalg.norm(dataSet - input_vector, axis=1)
+    # 获取距离最近的 k 个样本的索引
+    nearest_neighbors_indices = distances.argsort()[:k]
+    # 获取这些样本的标签
+    nearest_labels = np.array(labels)[nearest_neighbors_indices]
+    # 统计出现次数最多的标签并返回
+    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 +76,14 @@ def load_dataset(directory):
     - np.array: 特征数据。
     - np.array: 标签数据。
     """
-
+    labels = []
+    data_list = []
+    for filename in os.listdir(directory):
+        label = int(filename.split('_')[0])
+        labels.append(label)
+        vector = img_to_vector(os.path.join(directory, filename))
+        data_list.append(vector)
+    return np.array(data_list), np.array(labels)
 
 # 这里还写自己的代码实现
 def img_to_vector(filename):
@@ -82,7 +97,13 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
-
+    with open(filename) as f:
+        lines = f.readlines()
+    vector = np.zeros((1, 1024))
+    for i in range(32):
+        for j in range(32):
+            vector[0, 32 * i + j] = int(lines[i][j])
+    return vector
 
 if __name__ == "__main__":
     # 以下代码可用于测试，可自行随意修改
@@ -128,4 +149,4 @@ if __name__ == "__main__":
         train_labels,
     )
 
-    print(f"预测的标签: {predicted_label}")
+    print(f"预测的标签: {predicted_label}")