更新 function.py

function.py

@@ -40,6 +40,7 @@ name = "孔祥芷"
 
 
 # 这里写自己的代码实现
+
 def classify0(inX, dataSet, labels, k=3):
     """
     KNN 分类算法。
@@ -48,50 +49,73 @@ def classify0(inX, dataSet, labels, k=3):
     - inX (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。
+    - k (int): KNN 算法参数。
 
     Returns:
     - int: 预测的分类标签。
     """
+    # 计算待分类样本与训练集中每个样本之间的距离
     dists = np.sqrt(((dataSet - inX) ** 2).sum(axis=1))
+    # 根据距离对训练样本进行排序
     sorted_index = np.argsort(dists)
+    # 选择距离最近的k个样本
     class_count = {}
     for i in range(k):
         vote_label = labels[sorted_index[i]]
-        if vote_label not in class_count.keys():
-            class_count[vote_label] = 1
-        else:
-            class_count[vote_label] += 1
+        class_count[vote_label] = class_count.get(vote_label, 0) + 1
+    # 投票得到最多的标签作为预测结果
     sorted_class_count = sorted(class_count.items(), key=lambda item: item[1], reverse=True)
-    return sorted_class_count[0][0]
-
-
+    if sorted_class_count:
+        return sorted_class_count[0][0]
+    else:
+        return -1
 
 def load_data(file_path):
-    
-    #加载 TSV 格式数据文件。
-    
+    """
+    加载 TSV 格式数据文件。
+
+    Args:
+    - file_path (str): 文件路径。
+
+    Returns:
+    - features (numpy array): 特征数据。
+    - labels (numpy array): 标签数据。
+    """
     data = np.loadtxt(file_path, delimiter="\t")
     features = data[:, :-1]
     labels = data[:, -1].astype(int)
     return features, labels
 
-
-
+def standardize(features):
+    mean = np.mean(features, axis=0)
+    std = np.std(features, axis=0)
+    standardized = (features - mean) / std
+    return standardized
 
 if __name__ == "__main__":
-    # 以下代码可用于测试，可自行随意修改
     train_file_path = "datingTrainSet2.tsv"
     train_features, train_labels = load_data(train_file_path)
     
     test_file_path = "datingTestSet2.tsv"
     test_features, test_labels = load_data(test_file_path)
     
+    # 特征标准化
+    train_features = standardize(train_features)
+    test_features = standardize(test_features)
+    
     correct_count = 0
     for i in range(len(test_features)):
         test_feature = test_features[i].reshape(1, -1)
         predict_label = classify0(test_feature, train_features, train_labels, k=3)
+        if predict_label == -1:
+            continue
         correct_count += (predict_label == test_labels[i])
     
+    accuracy = correct_count / len(test_features)
+    print(f"Accuracy: {accuracy:.2f}")
+
+
+
+    
     accuracy = correct_count / len(test_features)
     print(f"Accuracy: {accuracy:.2f}")