更新 function.py

function.py

@@ -54,17 +54,13 @@ def classify(input_vector, dataSet, labels, k=3):
     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")   
-    min_vals = dataSet.min(axis=0)  
-    max_vals = dataSet.max(axis=0)  
-    norm_dataSet = (dataSet - min_vals) / (max_vals - min_vals)  
-    norm_input_vector = (input_vector - min_vals) / (max_vals - min_vals)  
-  
-    distances = np.linalg.norm(norm_dataSet - norm_input_vector, axis=1)  
-    sorted_indices = distances.argsort()  
-    nearest_labels = np.array(labels)[sorted_indices[:k]]  
-    predicted_label = np.bincount(nearest_labels).argmax()  
+    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
@@ -79,14 +75,16 @@ 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"):  
-            label = int(filename.split('_')[0])  
-            labels.append(label)  
-            vector = img_to_vector(os.path.join(directory, filename))  
-            data.append(vector)  
+    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
@@ -101,9 +99,10 @@ def img_to_vector(filename):
     Returns:
     - np.array: 二值图像向量。
     """
-    with open(filename, 'r') as f:  
-        lines = f.readlines()  
-    vector = np.array([int(char) for line in lines for char in line.strip()])  
+    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__":