上传文件至 /

function.py

@@ -57,19 +57,19 @@ def classify(input_vector, dataSet, labels, k=3):
     """
     使用欧式距离的 kNN 分类算法。
     """
-    # 计算输入样本与训练集中每个样本的欧氏距离
+    # 计算欧式距离
     distances = np.linalg.norm(dataSet - input_vector, axis=1)
 
-    # 按距离升序排列，选出距离最小的k个点的索引
-    nearest_neighbors = distances.argsort()[:k]
+    # 获取距离最近的 k 个样本的索引
+    k_indices = np.argsort(distances)[:k]
 
-    # 获取这k个邻居的标签，并转为列表
-    neighbor_labels = list(labels[nearest_neighbors])
+    # 获取最近邻样本的标签
+    k_nearest_labels = [labels[i] for i in k_indices]
 
-    # 返回出现次数最多的标签
-    predicted_label = max(set(neighbor_labels), key=neighbor_labels.count)
+    # 找出出现次数最多的标签
+    most_common = max(set(k_nearest_labels), key=k_nearest_labels.count)
 
-    return predicted_label
+    return most_common
 
 
 # 这里也写自己的代码实现
@@ -87,19 +87,22 @@ def load_dataset(directory):
     """
     features = []
     labels = []
-    
+
     # 遍历文件夹中的所有文件
-    data = []
-    labels = []
-
-    # 遍历目录中的所有文件
     for filename in os.listdir(directory):
-        if filename.endswith(".txt"):
-            file_path = os.path.join(directory, filename)
-            data.append(img_to_vector(file_path))
-            labels.append(int(filename.split('_')[0]))  # 假设文件名格式为 'label_index.txt'
+        if filename.endswith(".txt"):  # 假设文件是 .txt 格式
+            filepath = os.path.join(directory, filename)
 
-    return np.array(data), np.array(labels)
+            # 假设文件名格式为 "数字_编号.txt"
+            label = int(filename.split('_')[0])
+
+            # 加载文件中的二进制数据并转换为 1D 向量
+            image_vector = img_to_vector(filepath)
+
+            features.append(image_vector)
+            labels.append(label)
+
+    return np.array(features), np.array(labels)
 
 
 # 这里还写自己的代码实现
@@ -114,13 +117,11 @@ 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):  # 图像是32x32的
-        for j in range(32):
-            vector[0, 32 * i + j] = int(lines[i][j])
-    return vector
+    with open(filename) as file:
+        lines = file.readlines()
+        image_vector = np.array([int(char) for line in lines for char in line.strip()])
+
+    return image_vector
 
 
 if __name__ == "__main__":