更新 function.py

function.py

@@ -1,7 +1,7 @@
 import numpy as np
 import pandas as pd
 from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import train_test_split
+from sklearn.model_selection import train_test_split, KFold
 
 id = "202210423130"
 name = "董秋"
@@ -91,9 +91,27 @@ if __name__ == "__main__":
     # 使用 train_test_split 打乱并随机抽取数据
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
+    # K折交叉验证
+    k = 5
+    kf = KFold(n_splits=k, shuffle=True, random_state=42)
+    accuracies = []
+
+    for train_index, val_index in kf.split(X_train):
+        X_train_kf, X_val_kf = X_train[train_index], X_train[val_index]
+        y_train_kf, y_val_kf = y_train[train_index], y_train[val_index]
+
         # 训练逻辑回归模型，设置 batch size
-    batch_size = 64
-    weights = train_logreg(X_train, y_train, learning_rate=0.1, iterations=1000, lambda_reg=0.01, batch_size=batch_size)
+        batch_size = 32
+        weights = train_logreg(X_train_kf, y_train_kf, learning_rate=0.1, iterations=1000, lambda_reg=0.01, batch_size=batch_size)
+
+        # 验证模型
+        val_predictions = [predict_logreg(X_val_kf[i], weights) for i in range(len(X_val_kf))]
+        accuracy = np.mean(val_predictions == y_val_kf)
+        accuracies.append(accuracy)
+
+    # 输出交叉验证的准确率和平均准确率
+    print(f"K折交叉验证得分: {accuracies}")
+    print(f"平均准确率: {np.mean(accuracies)}")
 
     # 测试单个数据
     y_pred = predict_logreg(X_test[11], weights)