更新 function.py

function.py

@@ -26,77 +26,64 @@ name = "吴俊煯"
 
 
 # 这里写自己的代码实现
-def train_logreg(X, y, learning_rate=0.01, iterations=1000, regularization=0.0):
+def train_logreg(X, y, learning_rate=0.01, iterations=1000):
     m, n = X.shape  
     weights = np.zeros(n)  
     bias = 0  
-    m = len(X)  # 重新赋值m，以确保它表示样本数量（在添加正则化时可能需要）  
-  
+      
     for _ in range(iterations):  
-        linear_output = np.dot(X, weights) + bias  # 向量化操作  
-        y_predicted = 1 / (1 + np.exp(-linear_output))  
-        error = y - y_predicted  
-  
+        for idx, x_i in enumerate(X):  
+            linear_output = np.dot(x_i, weights) + bias  
+            y_predicted = 1 / (1 + np.exp(-linear_output))  
+              
+            # 计算误差  
+            error = y[idx] - y_predicted  
+              
+            # 更新权重和偏置  
+            weights += learning_rate * error * x_i  
+            bias += learning_rate * error  
+      
+    return weights    
 
-        # 计算梯度（不包括正则化项）  
-        gradient = np.dot(X.T, error) / m  
-  
-        # 加上正则化项的梯度（注意这里是对weights的每个元素都加上-regularization*weight[i]）  
-        gradient += -regularization * weights  
-  
-        # 更新权重  
-        weights += learning_rate * gradient 
-        bias += learning_rate * np.sum(error) / m  
-  
-    return weights, bias   
-
-def predict_logreg(inX, weights, bias):
-    linear_output = np.dot(inX, weights) + bias  
-    # 如果需要sigmoid输出，可以添加下面这行  
-    # sigmoid_output = 1 / (1 + np.exp(-linear_output))  
-    # return sigmoid_output  
-    return linear_output
+def predict_logreg(inX, weights):
+    linear_output = np.dot(inX, weights)  
+    y_predicted = 1 / (1 + np.exp(-linear_output))  
+      
+    # 将输出转换为分类标签  
+    return 1 if y_predicted >= 0.5 else 0 
 
 # 这里也写自己的代码实现
 def load_data(filepath):
     data = []  
     with open(filepath, 'r') as file:  
         for line in file:  
+            # 分割行，并去除任何可能的空白字符  
             parts = [part.strip() for part in line.split()]  
+            # 将缺失值'?'替换为0（或者你可以选择其他适当的处理方式）  
             features = [float(part) if part != '?' else 0 for part in parts[:-1]]  
-            label = int(parts[-1]) - 1  # 假设标签是{1, 2}，转换为{0, 1}  
+            # 将标签从2转换为1（如果原始标签是1和2的话）  
+            label = int(parts[-1]) - 1  # 假设原始标签是1和2，转换为0和1  
             data.append(features + [label])  
+      
+    # 将数据转换为numpy数组  
     data_array = np.array(data)  
-    X = data_array[:, :-1]  
-    y = data_array[:, -1]  
-    return X, y 
-
-def evaluate_model(test_data, weights, bias, user_test_func=predict_logreg):  
-    results = []  
-    for i in range(len(test_data)):  
-        # 确保传递了正确的参数：test_data[i], weights, bias  
-        result = user_test_func(test_data[i], weights, bias)  
-        results.append(result)  
-    # 根据需要对结果进行进一步处理，例如计算准确率等  
-    return results
+      
+    # 分离特征和标签  
+    X = data_array[:, :-1]  # 所有行，除了最后一列  
+    y = data_array[:, -1]   # 所有行的最后一列  
+      
+    return X, y
 
 if __name__ == "__main__":
+    # 加载训练集  
     X_train, y_train = load_data("./data/horse-colic.data")  
+  
+    # 加载测试集  
     X_test, y_test = load_data("./data/horse-colic.test")  
   
-    # 数据标准化（可选，但通常有助于模型性能）  
-    X_train_mean = np.mean(X_train, axis=0)  
-    X_train_std = np.std(X_train, axis=0)  
-    X_train = (X_train - X_train_mean) / X_train_std  
-    X_test = (X_test - X_train_mean) / X_train_std  # 使用训练集的标准差来标准化测试集  
+    # 训练对率回归模型  
+    weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000)  
   
-    # 训练逻辑回归模型  
-    weights, bias = train_logreg(X_train, y_train, learning_rate=0.01, iterations=1000, regularization=0.1)  
-  
-    # 评估模型性能  
-    accuracy = evaluate_model(X_test, y_test, weights, bias)  
-    print(f"测试集准确率: {accuracy:.2f}")  
-  
-    # 测试单个数据（可选）  
-    y_pred = predict_logreg(X_test[11], weights, bias)  
-    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")
+    # 测试单个数据  
+    y_pred = predict_logreg(X_test[11], weights)  
+    print(f"预测结果: {y_pred}, 实际结果: {y_test[11]}")