From f749c67eef7ed3e9170bb44d24ab28b8b2688436 Mon Sep 17 00:00:00 2001
From: 202210423104 <1961532386@qq.com>
Date: Sun, 3 Nov 2024 16:35:10 +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 | 19 +++++--------------
 1 file changed, 5 insertions(+), 14 deletions(-)

diff --git a/function.py b/function.py
index 0e417d3..461de10 100644
--- a/function.py
+++ b/function.py
@@ -1,6 +1,5 @@
 import numpy as np
 from sklearn.ensemble import RandomForestClassifier
-from sklearn.model_selection import train_test_split, cross_val_score
 from sklearn.preprocessing import PolynomialFeatures, StandardScaler
 
 id = "202210423104"
@@ -27,22 +26,14 @@ def preprocess_data(X):
     return X_poly
 
 def train_logreg(X, y):
-    X_processed = preprocess_data(X)
-    model = RandomForestClassifier(n_estimators=200, max_depth=15, random_state=42)  # 改变参数
+    X_processed = preprocess_data(X)  # 预处理训练数据
+    model = RandomForestClassifier(n_estimators=113, max_depth=10, random_state=42)
     model.fit(X_processed, y)
-    return model
+    return model  # 返回训练好的模型
 
 def predict_logreg(model, X):
-    if len(X.shape) == 1:
-        X = X.reshape(1, -1)
-    X_processed = preprocess_data(X)
-    return model.predict(X_processed)[0]
+    X_processed = preprocess_data(X)  # 预处理测试数据
+    return model.predict(X_processed)[0]  # 返回预测结果
 
 if __name__ == "__main__":
     X, y = load_data("./data/horse-colic.data")
-    model = train_logreg(X, y)
-    
-    # 交叉验证
-    X_processed = preprocess_data(X)
-    cv_scores = cross_val_score(model, X_processed, y, cv=5)
-    print(f"交叉验证准确率: {np.mean(cv_scores) * 100:.2f}%")