更新 function.py

function.py

@@ -41,76 +41,90 @@ name = "邓龙树"
 import numpy as np  
   
 def euclidean_distance(point1, point2):  
-    """  
-    计算两个点之间的欧氏距离。  
-    """  
-    return np.sqrt(np.sum((point1 - point2) ** 2))  
+    """计算两个点之间的欧氏距离。"""  
+    return np.sqrt(np.sum((np.array(point1) - np.array(point2)) ** 2))  
+  
+def compute_distances(dataSet, inX):  
+    """计算数据集中每个点与输入点inX的欧氏距离。"""  
+    inX_array = np.array(inX)  
+    diff = dataSet - inX_array  
+    squared_diff = diff ** 2  
+    distances = np.sqrt(np.sum(squared_diff, axis=1))  
+    return distances  
   
 def classify0(inX, dataSet, labels, k=3):  
-    """  
-    KNN 分类算法。  
+    """KNN 分类算法。  
       
     Args:  
-    - inX (numpy array): 输入待分类的样本。  
+    - inX (list or numpy array): 输入待分类的样本。  
     - dataSet (numpy array): 训练数据集。  
     - labels (numpy array): 训练集对应的标签。  
-    - k (int): KNN 算法参数，默认值为3。  
+    - k (int): KNN 算法参数，表示选择最近的k个邻居，默认值为3。  
       
     Returns:  
     - int: 预测的分类标签。  
     """  
-    # 确保 labels 是 numpy 数组  
-    labels = np.array(labels)  
-      
-    # 计算待分类样本与训练集中每个样本之间的距离  
-    distances = [euclidean_distance(inX, x) for x in dataSet]  
-      
-    # 对距离进行排序，并获取距离最小的k个样本的索引  
+    distances = compute_distances(dataSet, inX)  
     sorted_indices = np.argsort(distances)  
     k_nearest_indices = sorted_indices[:k]  
-      
-    # 获取k个最近样本的标签  
     k_nearest_labels = labels[k_nearest_indices]  
-      
-    # 使用 np.unique 和 np.bincount 的一个更健壮的方法来找到出现次数最多的标签  
     unique_labels, counts = np.unique(k_nearest_labels, return_counts=True)  
     most_common_label = unique_labels[np.argmax(counts)]  
-      
-    return int(most_common_label)  # 确保返回的是整数  
+    return int(most_common_label)  
   
 def load_data(file_path):  
+    """加载TSV格式数据文件。  
+      
+    Args:  
+    - file_path (str): 数据文件的路径。  
+      
+    Returns:  
+    - tuple: 特征集和标签集。  
     """  
-    加载 TSV 格式数据文件。  
+    try:  
+        data = np.loadtxt(file_path, delimiter="\t")  
+        features = data[:, :-1]  
+        labels = data[:, -1].astype(int)  
+        return features, labels  
+    except FileNotFoundError:  
+        print(f"Error: The file {file_path} was not found.")  
+        return None, None  
+    except ValueError as e:  
+        print(f"Error: The file {file_path} has an incorrect format. {e}")  
+        return None, None  
+  
+def test_knn(train_file, test_file, k=3):  
+    """测试KNN算法。  
+      
+    Args:  
+    - train_file (str): 训练数据文件的路径。  
+    - test_file (str): 测试数据文件的路径。  
+    - k (int): KNN算法参数，默认值为3。  
+      
+    Returns:  
+    - float: 测试集上的准确率。  
     """  
-    data = np.loadtxt(file_path, delimiter="\t")  
-    features = data[:, :-1]  
-    labels = data[:, -1].astype(int)  
-    return features, labels  
+    train_data, train_labels = load_data(train_file)  
+    if train_data is None or train_labels is None:  
+        print("Failed to load training data.")  
+        return None  
+      
+    test_data, test_labels = load_data(test_file)  
+    if test_data is None or test_labels is None:  
+        print("Failed to load test data.")  
+        return None  
+      
+    accuracy = np.mean([classify0(test_data[i], train_data, train_labels, k) == test_labels[i] for i in range(len(test_data))])  
+    print(f"Accuracy on test set with k={k}: {accuracy}")  
+    return accuracy  
   
 if __name__ == "__main__":  
-    # 测试代码  
-    train_file = "datingTrainSet2.tsv"  
-    test_file = "datingTestSet2.tsv"  # 假设有一个测试文件用于验证  
+    train_file_path = "path/to/datingTrainSet2.tsv"  # 替换为您的训练文件路径  
+    test_file_path = "path/to/datingTestSet2.tsv"    # 替换为您的测试文件路径  
       
-    # 加载训练数据和测试数据  
-    train_data, train_labels = load_data(train_file)  
-    test_data, test_labels = load_data(test_file)  # 取消注释以测试整个测试集  
+    # 测试KNN算法，默认k=3  
+    test_knn(train_file_path, test_file_path)  
       
-    # 测试 classify0 函数  
-    sample = [65915, 3.868359, 0.128078]  # 示例样本  
-    predicted_label = classify0(sample, train_data, train_labels)  
-    print(f"Predicted label for sample {sample}: {predicted_label}")  
-  
-    # 测试整个测试集（可选）  
-    accuracy = np.mean([classify0(test_data[i], train_data, train_labels) == test_labels[i] for i in range(len(test_data))])  
-    print(f"Accuracy on test set: {accuracy}") 
-    # test_data, test_labels = load_data(test_file)  # 如果需要测试，可以取消注释并添加相应的测试代码  
-  
-    # 测试 classify0 函数  
-    sample = [65915, 3.868359, 0.128078]  # 示例样本  
-    predicted_label = classify0(sample, train_data, train_labels)  
-    print(f"Predicted label for sample {sample}: {predicted_label}")  
-  
-    # 如果需要测试整个测试集，可以添加以下代码（注意：这部分代码是为了完整性而添加的，题目没明确要求）  
-    # accuracy = np.mean([classify0(test_data[i], train_data, train_labels) == test_labels[i] for i in range(len(test_data))])  
-    # print(f"Accuracy on test set: {accuracy}")
+    # 您可以尝试不同的k值来查看对准确率的影响  
+    # test_knn(train_file_path, test_file_path, k=5)  
+    # test_knn(train_file_path, test_file_path, k=1)