From 84423f7537664e087c63d9a2a93dfb23e6626331 Mon Sep 17 00:00:00 2001
From: 202210423104 <1961532386@qq.com>
Date: Sun, 3 Nov 2024 17:24:08 +0800
Subject: [PATCH] =?UTF-8?q?=E4=B8=8A=E4=BC=A0=E6=96=87=E4=BB=B6=E8=87=B3?=
 =?UTF-8?q?=20/?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 function.py | 33 ++++++++++++---------------------
 1 file changed, 12 insertions(+), 21 deletions(-)

diff --git a/function.py b/function.py
index d2bd3bb..aaae632 100644
--- a/function.py
+++ b/function.py
@@ -3,12 +3,11 @@ from sklearn.ensemble import RandomForestClassifier
 from sklearn.preprocessing import PolynomialFeatures, StandardScaler
 from sklearn.impute import SimpleImputer
 from sklearn.metrics import accuracy_score
-from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.model_selection import train_test_split
 
 id = "202210423104"
 name = "张钦诚"
 
-
 def load_data(filepath):
     data = []
     with open(filepath, 'r') as file:
@@ -27,7 +26,6 @@ def load_data(filepath):
     y = data[:, -1]  # 标签
     return X, y
 
-
 def preprocess_data(X):
     scaler = StandardScaler()
     X_standardized = scaler.fit_transform(X)
@@ -35,24 +33,17 @@ def preprocess_data(X):
     X_poly = poly.fit_transform(X_standardized)
     return X_poly
 
-
 def train_logreg(X, y):
     X_processed = preprocess_data(X)  # 预处理训练数据
-
-    # 超参数调优
-    param_grid = {
-        'n_estimators': [100, 200, 300],
-        'max_depth': [None, 15, 25],
-        'min_samples_split': [2, 5, 10],
-        'class_weight': ['balanced', None]
-    }
-
-    model = RandomForestClassifier(random_state=42)
-    grid_search = GridSearchCV(model, param_grid, cv=5, scoring='accuracy', n_jobs=-1)
-    grid_search.fit(X_processed, y)
-
-    return grid_search.best_estimator_  # 返回最佳模型
-
+    model = RandomForestClassifier(
+        n_estimators=300,  # 增加树的数量
+        max_depth=25,      # 调整最大深度
+        min_samples_split=5,
+        class_weight='balanced',  # 处理类别不平衡
+        random_state=42  # 固定随机种子
+    )
+    model.fit(X_processed, y)
+    return model  # 返回训练好的模型
 
 def predict_logreg(X, model):
     if len(X.shape) == 1:
@@ -60,11 +51,11 @@ def predict_logreg(X, model):
     X_processed = preprocess_data(X)  # 预处理测试数据
     return model.predict(X_processed)[0]  # 确保 model 是训练好的模型
 
-
 if __name__ == "__main__":
+    # 数据加载和预处理保持不变
     X, y = load_data("./data/horse-colic.data")
 
-    # 划分训练集和测试集
+    # 划分训练集和测试集时固定随机种子
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
     # 训练模型