From 8f9194ec43509ce0da7fe244aa6df81f7b5191af Mon Sep 17 00:00:00 2001
From: 43606070 <43606070@qq.com>
Date: Thu, 31 Oct 2024 10:45:17 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=20function.py?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 42 +++++++++++++++++++++++++++++++++---------
 1 file changed, 33 insertions(+), 9 deletions(-)

diff --git a/function.py b/function.py
index e401431..881308e 100644
--- a/function.py
+++ b/function.py
@@ -1,12 +1,18 @@
+import os
 import csv
 import numpy as np
-from sklearn.model_selection import train_test_split
+from sklearn.model_selection import train_test_split, GridSearchCV
 from sklearn.linear_model import LogisticRegression
-from sklearn.metrics import classification_report, confusion_matrix
+from sklearn.metrics import classification_report, confusion_matrix, accuracy_score, roc_auc_score
+from sklearn.preprocessing import StandardScaler
+from sklearn.pipeline import Pipeline
 from imblearn.over_sampling import SMOTE
 
 # 读取 CSV 数据的函数
 def load_data(file_path):
+    if not os.path.exists(file_path):
+        raise FileNotFoundError(f"文件未找到: {file_path}")
+    
     features = []
     labels = []
     with open(file_path, 'r') as csvfile:
@@ -18,11 +24,16 @@ def load_data(file_path):
     return np.array(features), np.array(labels)
 
 # 评估模型的函数
-def evaluate_model(y_true, y_pred):
+def evaluate_model(y_true, y_pred, y_prob=None):
     print("Confusion Matrix:")
     print(confusion_matrix(y_true, y_pred))
     print("\nClassification Report:")
     print(classification_report(y_true, y_pred))
+    print(f"Accuracy: {accuracy_score(y_true, y_pred):.4f}")
+    
+    if y_prob is not None:
+        auc = roc_auc_score(y_true, y_prob)
+        print(f"AUC Score: {auc:.4f}")
 
 # 主函数
 def main():
@@ -37,15 +48,28 @@ def main():
     smote = SMOTE(random_state=42)
     X_train_res, y_train_res = smote.fit_resample(X_train, y_train)
 
-    # 训练逻辑回归模型
-    model = LogisticRegression(max_iter=1000)
-    model.fit(X_train_res, y_train_res)
+    # 创建管道，包含标准化和逻辑回归
+    pipeline = Pipeline([
+        ('scaler', StandardScaler()),  # 数据标准化
+        ('classifier', LogisticRegression(max_iter=1000))  # 逻辑回归
+    ])
 
-    # 进行预测
-    y_pred = model.predict(X_test)
+    # 网格搜索以优化正则化参数 C
+    param_grid = {'classifier__C': [0.01, 0.1, 1, 10, 100]}
+    grid_search = GridSearchCV(pipeline, param_grid, cv=5, scoring='accuracy')
+    grid_search.fit(X_train_res, y_train_res)
+    
+    # 输出最佳参数
+    print(f"Best Parameters: {grid_search.best_params_}")
+
+    # 使用最佳模型进行预测
+    best_model = grid_search.best_estimator_
+    y_pred = best_model.predict(X_test)
+    y_prob = best_model.predict_proba(X_test)[:, 1]  # 用于 AUC 计算
 
     # 评估模型
-    evaluate_model(y_test, y_pred)
+    evaluate_model(y_test, y_pred, y_prob)
 
 if __name__ == "__main__":
     main()
+