更新 function.py

function.py

@@ -40,63 +40,91 @@ name = "邓龙树"
 
 import numpy as np  
   
-class KNNClassifier:  
-    def __init__(self, k=3):  
-        self.k = k  
-        self.train_data = None  
-        self.train_labels = None  
+def euclidean_distance(point1, point2):  
+    """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 fit(self, data, labels):  
-        self.train_data = np.array(data)  
-        self.train_labels = np.array(labels)  
+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 _compute_distances(self, inX):  
-        inX_array = np.array(inX).reshape(1, -1)  
-        diff = self.train_data - 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。  
+      
+    Args:  
+    - 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，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。  
+    """  
+    distances = compute_distances(dataSet, inX)  
+    sorted_indices = np.argsort(distances)  
+    k_nearest_indices = sorted_indices[:k]  
+    k_nearest_labels = labels[k_nearest_indices]  
+    unique_labels, counts = np.unique(k_nearest_labels, return_counts=True)  
+    most_common_label = unique_labels[np.argmax(counts)]  
+    return int(most_common_label)  
   
-    def predict(self, inX):  
-        distances = self._compute_distances(inX)  
-        sorted_indices = np.argsort(distances)  
-        k_nearest_indices = sorted_indices[:self.k]  
-        k_nearest_labels = self.train_labels[k_nearest_indices]  
-        unique_labels, counts = np.unique(k_nearest_labels, return_counts=True)  
-        most_common_label = unique_labels[np.argmax(counts)]  
-        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。  
+    """  
+    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 load_data(self, file_path):  
-        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 evaluate(self, test_data, test_labels):  
-        accuracy = np.mean([self.predict(test_data[i]) == test_labels[i] for i in range(len(test_data))])  
-        print(f"Accuracy: {accuracy}")  
-        return accuracy  
+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。  
+    """  
+    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__":  
-    train_file_path = "path/to/datingTrainSet2.tsv"  
-    test_file_path = "path/to/datingTestSet2.tsv"  
-  
-    knn = KNNClassifier(k=3)  
-    train_data, train_labels = knn.load_data(train_file_path)  
-    if train_data is not None and train_labels is not None:  
-        knn.fit(train_data, train_labels)  
-  
-        test_data, test_labels = knn.load_data(test_file_path)  
-        if test_data is not None and test_labels is not None:  
-            knn.evaluate(test_data, test_labels)  
-        else:  
-            print("Failed to load test data.")  
-    else:  
-        print("Failed to load training data.")
+    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  
+      
+    # 测试KNN算法，默认k=3  
+    test_knn(train_file_path, test_file_path)  
+      
+    # 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)