From 92bc054265dde216b61395be1208c2461c6c8bef Mon Sep 17 00:00:00 2001
From: haotian <2421912570@qq.com>
Date: Tue, 8 Apr 2025 10:53:13 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E6=94=B9--=E6=95=B0=E6=8D=AE=E9=9B=86?=
 =?UTF-8?q?=E5=88=92=E5=88=86=E6=97=B6=E5=8F=AF=E4=BB=A5=E8=AE=BE=E5=AE=9A?=
 =?UTF-8?q?=E9=9A=8F=E6=9C=BA=E7=A7=8D=E5=AD=90?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 config/config.yaml             |  2 +-
 doc/各领域应用(附带数据集).txt | 10 ++++++++++
 function/data_manager.py       |  5 +++--
 3 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/config/config.yaml b/config/config.yaml
index 9d11c9b..e2bb86e 100644
--- a/config/config.yaml
+++ b/config/config.yaml
@@ -16,7 +16,7 @@ dataset:
 model:
   save_dir: "models"
   batch_size: 32
-  num_workers: 4
+  num_workers: 1
   
 # 系统监控配置
 monitor:
diff --git a/doc/各领域应用(附带数据集).txt b/doc/各领域应用(附带数据集).txt
index c37cd89..5523c48 100644
--- a/doc/各领域应用(附带数据集).txt
+++ b/doc/各领域应用(附带数据集).txt
@@ -30,6 +30,16 @@
             测试集真值:
                 暂无
             注: 不同训练集文件对应不同的现场情况, 不要混用.
+        测试结果:
+            train_FD001.txt
+                训练集:
+                    mae: 16.xx
+                验证集:
+                    mae: 30.xx
+                结果分析:
+                    对于存在时序信息的数据,只用随机森林来拟合,效果不好.
+                    虽然数据有26列特征,但有的数据完全一致根本没有参考价值.
+
 2.能源行业-风电功率预测
     (1)基于天气与历史数据预测风力发电量
     (2)XGBoost,LSTM,Prophet时间序列模型
diff --git a/function/data_manager.py b/function/data_manager.py
index cb987de..6be6719 100644
--- a/function/data_manager.py
+++ b/function/data_manager.py
@@ -424,7 +424,8 @@ class DataManager:
         self,
         df: pd.DataFrame,
         test_size: float = 0,
-        val_size: float = 0
+        val_size: float = 0,
+        random_state: int = 42
     ) -> Tuple[pd.DataFrame, pd.DataFrame, pd.DataFrame]:
         """划分数据集"""
         try:
@@ -433,7 +434,7 @@ class DataManager:
                 train_val_data, test_data = train_test_split(
                     df,
                     test_size=test_size,
-                    random_state=42
+                    random_state=random_state
                 )
             else:
                 train_val_data = df