更新 function.py

function.py

@@ -1,36 +1,41 @@
 import numpy as np
 from sklearn.preprocessing import StandardScaler
 from sklearn.model_selection import KFold
+
 """
 实验说明:
-  - 自行编写实现数据加载与预测病马死亡的对率回归算法。 
-  
- 注意事项:
- - 在 function.py 中实现对率回归算法。
- - 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
- - 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。 
- 测评环境:
- - CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
- - OS: Ubuntu 22.04.4 LTS
- - Python: 3.10.12
- - numpy: 2.1.1
+- 自行编写实现数据加载与预测病马死亡的对率回归算法。
+
+注意事项:
+- 在 function.py 中实现对率回归算法。
+- 可以自行导入其他库，需要在 requirements.txt 添加依赖，若未在 requirements.txt 中添加使用到的依赖，则无法自动评测，成绩为零。
+- 自动评测脚本仅会加载 train_logreg、predict_logreg 和 load_data 函数，请勿修改函数名。
+
+测评环境:
+- CPU: Intel Xeon(R) CPU E3-1231 v3 @ 3.40GHz
+- OS: Ubuntu 22.04.4 LTS
+- Python: 3.10.12
+- numpy: 2.1.1
 """
+
 """
- 请在这里填写学号和姓名，不填写即成绩无效。
+请在这里填写学号和姓名，不填写即成绩无效。
 """
 id = "202210423117"
 name = "程悦"
-  
+
+
 def sigmoid(z):
     return 1.0 / (1 + np.exp(-z))
 
 
 def train_logreg(X, y, learning_rate=0.05,
-                  iterations=1500,
-                  batch_size=64, regularization='L2', lambda_reg=0.05, cv=5):
+                 iterations=1500,
+                 batch_size=64, regularization='L2', lambda_reg=0.05, cv=5):
     m, n = X.shape
     kf = KFold(n_splits=cv, shuffle=True)
     weights_list = []
+    fold_scores = []
     for train_index, val_index in kf.split(X):
         X_train, X_val = X[train_index], X[val_index]
         y_train, y_val = y[train_index], y[val_index]
@@ -52,8 +57,20 @@ def train_logreg(X, y, learning_rate=0.05,
                 weights -= learning_rate * gradient
             if i % 100 == 0:
                 learning_rate *= 0.95
+        # 在验证集上计算准确率
+        predictions = [predict_logreg(x, weights) for x in X_val]
+        score = np.mean(predictions == y_val)
+        fold_scores.append(score)
         weights_list.append(weights)
-    return weights_list[-1]
+    # 对权重进行加权平均融合，权重为各折的准确率
+    total_score = sum(fold_scores)
+    if total_score == 0:
+        return weights_list[-1]
+    averaged_weights = np.zeros(n)
+    for weight, score in zip(weights_list, fold_scores):
+        averaged_weights += weight * score
+    averaged_weights /= total_score
+    return averaged_weights
 
 
 def predict_logreg(inX, weights):
@@ -92,8 +109,8 @@ def accuracy(X, y, weights):
 
 
 if __name__ == "__main__":
-    X_train, y_train = load_data("./horse - colic.data")
-    X_test, y_test = load_data("./horse - colic.test")
+    X_train, y_train = load_data("./horse-colic.data")
+    X_test, y_test = load_data("./horse-colic.test")
 
     final_weights = train_logreg(X_train, y_train, learning_rate=0.01, iterations=5000, batch_size=32, regularization='None',
                                  lambda_reg=0.01)