更新 function.py

2024-10-08 23:05:15 +08:00
parent 47cc47bc65
commit f0cd071eba
1 changed files with 57 additions and 65 deletions
@@ -40,68 +40,60 @@ name = "章程鸿"


 # 这里写自己的代码实现
-import numpy as np  
-from sklearn.model_selection import GridSearchCV  
-from sklearn.neighbors import KNeighborsClassifier  
-  
-def load_data(file_path):  
-    """  
-    加载 TSV 格式数据文件。  
-    """  
-    data = np.loadtxt(file_path, delimiter="\t")  
-    features = data[:, :-1]  
-    labels = data[:, -1].astype(int)  
-    return features, labels  
-  
-def normalize_min_max(data):  
-    """  
-    对数据进行最小-最大缩放归一化。  
-  
-    Args:  
-    - data (numpy array): 待归一化的数据。  
-  
-    Returns:  
-    - numpy array: 归一化后的数据。  
-    - numpy array: 最小值。  
-    - numpy array: 最大值。  
-    """  
-    min_vals = data.min(0)  
-    max_vals = data.max(0)  
-    ranges = max_vals - min_vals  
-    ranges[ranges == 0.0] = 1.0  # 避免除以零  
-    norm_data = (data - min_vals) / ranges  
-    return norm_data, min_vals, max_vals  
-  
-if __name__ == "__main__":  
-    train_file = "datingTrainSet2.tsv"  
-    test_file = "datingTestSet2.tsv"  # 假设您有一个测试集文件  
-      
-    # 加载训练和测试数据  
-    train_data, train_labels = load_data(train_file)  
-    test_data, test_labels = load_data(test_file)  
-  
-    # 归一化训练和测试数据  
-    train_data_normalized, min_vals, max_vals = normalize_min_max(train_data)  
-    test_data_normalized = (test_data - min_vals) / (max_vals - min_vals)  
-  
-    # 定义KNN分类器  
-    knn = KNeighborsClassifier()  
-  
-    # 定义要搜索的k值范围  
-    param_grid = {'n_neighbors': list(range(1, 31))}  
-  
-    # 使用GridSearchCV进行网格搜索  
-    grid_search = GridSearchCV(knn, param_grid, cv=10, scoring='accuracy')  
-    grid_search.fit(train_data_normalized, train_labels)  
-  
-    # 获取最佳的k值  
-    optimal_k = grid_search.best_params_['n_neighbors']  
-    print("Optimal k:", optimal_k)  
-  
-    # 使用最佳k值进行预测  
-    best_knn = KNeighborsClassifier(n_neighbors=optimal_k)  
-    best_knn.fit(train_data_normalized, train_labels)  
-  
-    # 对测试数据进行预测  
-    predicted_labels = best_knn.predict(test_data_normalized)  
-    print("预测的分类标签是:", predicted_label[0])
+import numpy as np
+from sklearn.model_selection import GridSearchCV
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.preprocessing import MinMaxScaler
+from sklearn.metrics import accuracy_score
+
+def load_data(file_path):
+    """
+    加载 TSV 格式数据文件。
+    """
+    data = np.loadtxt(file_path, delimiter="\t")
+    features = data[:, :-1]
+    labels = data[:, -1].astype(int)
+    return features, labels
+
+if __name__ == "__main__":
+    train_file = "datingTrainSet2.tsv"
+    test_file = "datingTestSet2.tsv"  # 假设您有一个测试集文件
+    
+    # 加载训练和测试数据
+    train_data, train_labels = load_data(train_file)
+    test_data, test_labels = load_data(test_file)
+
+    # 使用MinMaxScaler进行归一化
+    scaler = MinMaxScaler()
+    train_data_normalized = scaler.fit_transform(train_data)
+    test_data_normalized = scaler.transform(test_data)
+
+    # 定义KNN分类器
+    knn = KNeighborsClassifier()
+
+    # 定义要搜索的k值范围
+    param_grid = {'n_neighbors': list(range(1, 31))}
+
+    # 使用GridSearchCV进行网格搜索
+    grid_search = GridSearchCV(knn, param_grid, cv=10, scoring='accuracy')
+    grid_search.fit(train_data_normalized, train_labels)
+
+    # 获取最佳的k值
+    optimal_k = grid_search.best_params_['n_neighbors']
+    print("Optimal k:", optimal_k)
+
+    # 使用最佳k值进行预测
+    best_knn = KNeighborsClassifier(n_neighbors=optimal_k)
+    best_knn.fit(train_data_normalized, train_labels)
+
+    # 对测试数据进行预测
+    predicted_labels = best_knn.predict(test_data_normalized)
+
+    # 输出预测结果
+    print("预测的分类标签是:")
+    for i, (predicted, actual) in enumerate(zip(predicted_labels, test_labels)):
+        print(f"样本 {i+1}: 预测标签: {predicted}, 实际标签: {actual}")
+
+    # 计算并输出准确率
+    accuracy = accuracy_score(test_labels, predicted_labels)
+    print(f"模型在测试集上的准确率为: {accuracy * 100:.2f}%")