更新 function.py

function.py

@@ -1,13 +1,13 @@
 import numpy as np
 import pandas as pd
-from sklearn.preprocessing import StandardScaler, PolynomialFeatures
-from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.preprocessing import StandardScaler
+from sklearn.model_selection import train_test_split
 from sklearn.linear_model import LogisticRegression
 
 id = "202210423130"
 name = "董秋"
 
-def train_logreg(X, y, learning_rate=0.05, iterations=1000, lambda_reg=0.01):
+def train_logreg(X, y, learning_rate=0.01, iterations=1500, lambda_reg=0.01):
     """
     逻辑回归训练函数。
 
@@ -86,19 +86,7 @@ def preprocess_data(X):
     # 标准化
     scaler = StandardScaler()
     X_scaled = scaler.fit_transform(X)
-    
-    # 创建多项式特征
-    poly = PolynomialFeatures(degree=2, interaction_only=False, include_bias=False)
-    X_poly = poly.fit_transform(X_scaled)
-
-    # 例如，可以对某个特征进行分箱处理
-    age_bins = pd.cut(X_scaled[:, 0], bins=[0, 30, 60, 100], labels=["年轻", "中年", "老年"])
-    age_dummies = pd.get_dummies(age_bins, drop_first=True)
-
-    # 将独热编码的结果与原特征组合
-    X_combined = np.hstack((X_poly, age_dummies.values))
-    
-    return X_combined
+    return X_scaled
 
 if __name__ == "__main__":
     # 加载数据集
@@ -106,26 +94,12 @@ if __name__ == "__main__":
     X = preprocess_data(X)
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
-    # 定义参数网格
-    param_grid = {
-        'C': [0.01, 0.1, 1.0, 10.0],  # L2正则化强度的倒数
-        'max_iter': [500, 1000, 2000]
-    }
+    # 使用sklearn的LogisticRegression进行训练
+    model = LogisticRegression(penalty='l2', solver='lbfgs', max_iter=2000)
+    model.fit(X_train, y_train)
 
-    # 使用sklearn的LogisticRegression进行网格搜索
-    model = LogisticRegression(penalty='l2', solver='lbfgs')
-    grid_search = GridSearchCV(model, param_grid, cv=5)
-    grid_search.fit(X_train, y_train)
-
-    # 获取最佳参数
-    best_params = grid_search.best_params_
-    print(f"最佳参数: {best_params}")
-
-    # 使用最佳参数重新训练模型
-    weights = train_logreg(X_train, y_train, 
-                           learning_rate=0.1, 
-                           iterations=best_params['max_iter'], 
-                           lambda_reg=1 / best_params['C'])  # 将C转换为lambda_reg
+    # 获取权重
+    weights = model.coef_[0]  # 只获取第一类的权重
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)