更新 function.py

function.py

@@ -1,4 +1,5 @@
 import numpy as np
+from sklearn.preprocessing import StandardScaler
 
 """
 请在这里填写学号和姓名，不填写即成绩无效。
@@ -6,14 +7,12 @@ import numpy as np
 id = "202210423224"
 name = "吴杨洋"
 
-
 def sigmoid(z):
     """
     Sigmoid 激活函数。
     """
     return 1 / (1 + np.exp(-z))
 
-
 def train_logreg(X, y, numIter=1000, learning_rate=0.01, lambda_reg=0.01):
     m, n = X.shape
     weights = np.zeros(n)
@@ -28,7 +27,6 @@ def train_logreg(X, y, numIter=1000, learning_rate=0.01, lambda_reg=0.01):
             weights += learning_rate * gradient
     return weights
 
-
 def predict_logreg(inX, weights):
     """
     对率回归预测函数。
@@ -44,7 +42,6 @@ def predict_logreg(inX, weights):
     prob = sigmoid(z)
     return 1 if prob >= 0.5 else 0
 
-
 def load_data(filepath):
     """
     从文件中加载数据，若不自行正确实现，则无法通过评测，不记录成绩。
@@ -78,15 +75,7 @@ def load_data(filepath):
     data_number = len(y)
     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)  # 添加偏置项
-    return X_train, y_train
-
-
-def standardize(X):
-    mean = X.mean(axis=0)
-    std = X.std(axis=0)
-    return (X - mean) / std, mean, std
-
+    return X, y_train  # 不在这里添加偏置项
 
 def main():
     # 加载训练集
@@ -94,9 +83,16 @@ def main():
     # 加载测试集
     X_test, y_test = load_data("./data/horse-colic.test")
 
+    # 创建标准化器实例
+    scaler = StandardScaler()
+    
     # 标准化特征数据
-    X_train, mean, std = standardize(X_train)
-    X_test = (X_test - mean) / std
+    X_train = scaler.fit_transform(X_train)
+    X_test = scaler.transform(X_test)
+    
+    # 添加偏置项
+    X_train = np.insert(X_train, 0, 1, axis=1)  # 训练集
+    X_test = np.insert(X_test, 0, 1, axis=1)  # 测试集
 
     # 训练对率回归模型
     weights = train_logreg(X_train, y_train, numIter=1000, learning_rate=0.01, lambda_reg=0.1)
@@ -106,6 +102,5 @@ def main():
     accuracy_test = np.mean(y_pred_test == y_test)
     print(f"Test Accuracy: {accuracy_test:.2f}")
 
-
 if __name__ == "__main__":
     main()