更新 function.py

function.py

@@ -40,12 +40,12 @@ def load_data(filepath):
     file = open(filepath)
     fr = file.readlines()
     data_list = []
-    y = []
+    y_list = []
     for data in fr:
         data = data.strip()
         data = data.split(' ')
         data_25 = data[24]
-        y.append(data[22])
+        y_list.append(data[22])
         del data[-1]
         del data[26]
         del data[25]
@@ -56,13 +56,19 @@ def load_data(filepath):
             data.append(i)
         data = [0 if data_elem == '?' else float(data_elem) for data_elem in data]
         data_list.append(data)
-    data_number = len(y)
+    
+    data_number = len(y_list)
     y_train = np.array([1 if y[j] == '2' or y[j] == '3' else 0 for j in range(data_number)])
     X = np.array(data_list)
-    X_train = np.insert(X, 0, 1, axis=1) 
-    return X_train, y_train
+    
+    # 特征缩放
+    scaler = StandardScaler()
+    X = scaler.fit_transform(X)
+    X = np.insert(X, 0, 1, axis=1)  # 添加偏置项
+    
+    return X, y_train
 
-def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_reg=0.01):
+def train_logreg(X, y, numIter=1000, learning_rate=0.01, batch_size=128, lambda_reg=0.01):
     """
     对率回归训练函数，加入L2正则化。
 
@@ -70,7 +76,7 @@ def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_
     - X (numpy array): 特征数据。
     - y (numpy array): 标签数据。
     - numIter (int): 迭代次数。默认为1000。
-    - learning_rate (float): 学习率。默认为0.06。
+    - learning_rate (float): 学习率。默认为0.01。
     - batch_size (int): 批量大小。默认为128。
     - lambda_reg (float): L2正则化参数。默认为0.01。
 
@@ -84,19 +90,16 @@ def train_logreg(X, y, numIter=1000, learning_rate=0.06, batch_size=128, lambda_
         dataIndex = np.random.permutation(m)
         for i in range(0, m, batch_size):
             end = min(i + batch_size, m)
-            # 批量梯度上升
             batch_X = X[dataIndex[i:end]]
             batch_y = y[dataIndex[i:end]]
             
-            # 计算梯度
             z = np.dot(batch_X, weights)
             h = 1 / (1 + np.exp(-z))  # 计算h
             error = batch_y - h  # 计算误差
             gradient = np.dot(batch_X.T, error) / len(batch_y)  # 计算梯度
-            # 添加L2正则化
             reg_term = 2 * lambda_reg * weights
-            gradient -= reg_term / len(batch_y)
-            weights += learning_rate * gradient  # 更新权重
+            gradient += reg_term / len(batch_y)
+            weights -= learning_rate * gradient  # 更新权重
 
     return weights
 
@@ -127,11 +130,9 @@ if __name__ == "__main__":
 
     # 测试模型
     error = 0
-    accuracy_list = []
     for i in range(len(y_test)):
         y_pred = predict_logreg(X_test[i], weights)
         if y_pred != y_test[i]:
             error += 1
-        print(f"预测结果: {y_pred}, 实际结果: {y_test[i]}")
     accuracy = (len(y_test) - error) / len(y_test)
-    print(f"Accuracy: {accuracy}")
+    print(f"Accuracy: {accuracy:.3f}")