From e18a66026cfa5d1a4466f8cfb14859ce008023a5 Mon Sep 17 00:00:00 2001
From: lzh <2233673261@qq.com>
Date: Sat, 2 Nov 2024 20:51:02 +0800
Subject: [PATCH] 55555

---
 function.py | 41 ++++++++++++++++++++++++++++++++---------
 1 file changed, 32 insertions(+), 9 deletions(-)

diff --git a/function.py b/function.py
index d074dd0..fbc31eb 100644
--- a/function.py
+++ b/function.py
@@ -1,8 +1,11 @@
 # function.py
 import numpy as np
-from sklearn.model_selection import train_test_split
+from sklearn.model_selection import train_test_split, GridSearchCV
 from sklearn.preprocessing import StandardScaler
-from sklearn.metrics import accuracy_score
+from sklearn.metrics import accuracy_score, roc_auc_score
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.linear_model import LogisticRegression
+from sklearn.ensemble import VotingClassifier
 """
 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。
@@ -28,7 +31,6 @@ name = "廖子豪"
 
 
 # 这里写自己的代码实现
-
 def load_data(filepath):
     """
     从文件中加载数据。
@@ -136,18 +138,39 @@ if __name__ == "__main__":
 
     # 训练对率回归模型，使用早停法
     best_weights = None
-    best_accuracy = 0
+    best_auc = 0
     for iter in range(1, 1001):
         weights = train_logreg(X_train, y_train, numIter=iter, learning_rate=0.01, lambda_reg=0.1)
         y_pred = [predict_logreg(x, weights) for x in X_val]
-        accuracy = accuracy_score(y_val, y_pred)
-        if accuracy > best_accuracy:
-            best_accuracy = accuracy
+        auc = roc_auc_score(y_val, y_pred)
+        if auc > best_auc:
+            best_auc = auc
             best_weights = weights
-        if iter > 10 and accuracy == best_accuracy:
+        if iter > 10 and auc == best_auc:
             break  # 早停
 
     # 使用最佳权重在测试集上评估模型
     y_pred_test = [predict_logreg(x, best_weights) for x in X_test]
     accuracy_test = accuracy_score(y_test, y_pred_test)
-    print(f"Test Accuracy: {accuracy_test}")
\ No newline at end of file
+    print(f"Test Accuracy: {accuracy_test}")
+
+    # 随机森林模型
+    param_grid = {
+        'n_estimators': [100, 200, 300],
+        'max_depth': [5, 10, 15],
+        'learning_rate': [0.01, 0.05, 0.1]
+    }
+    rf = RandomForestClassifier()
+    grid_search = GridSearchCV(estimator=rf, param_grid=param_grid, cv=5, scoring='accuracy')
+    grid_search.fit(X_train, y_train)
+    best_rf = grid_search.best_estimator_
+    print("Best parameters:", grid_search.best_params_)
+    print("Best accuracy:", grid_search.best_score_)
+
+    # 集成学习 - 投票分类器
+    log_clf = LogisticRegression()
+    rnd_clf = RandomForestClassifier(n_estimators=100, random_state=42)
+    voting_clf = VotingClassifier(estimators=[('lr', log_clf), ('rf', rnd_clf)], voting='soft')
+    voting_clf.fit(X_train, y_train)
+    y_pred = voting_clf.predict(X_test)
+    print("Voting classifier accuracy:", accuracy_score(y_test, y_pred))
\ No newline at end of file