From da929edbac00846677a2ae6b097a65e588e92978 Mon Sep 17 00:00:00 2001
From: workpc <liurui_test@163.com>
Date: Mon, 18 Nov 2024 10:34:40 +0800
Subject: [PATCH] =?UTF-8?q?=E6=A0=B9=E6=8D=AE=E9=A2=84=E6=B5=8B=E5=88=97?=
 =?UTF-8?q?=E5=88=A4=E6=96=AD=E9=A2=84=E8=AD=A6=E7=89=B9=E5=BE=81=E5=B9=B6?=
 =?UTF-8?q?=E5=88=A0=E9=99=A4=E9=A2=84=E8=AD=A6=E7=9A=84=E7=89=B9=E5=BE=81?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 config_jingbo.py        |   2 +-
 dataset/jbsh_yuanyou.db | Bin 77824 -> 77824 bytes
 lib/dataread.py         |  22 ++++++++++++++++++++--
 main_yuanyou.py         |   7 ++-----
 4 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/config_jingbo.py b/config_jingbo.py
index 1c9f779..4c4b0fb 100644
--- a/config_jingbo.py
+++ b/config_jingbo.py
@@ -168,7 +168,7 @@ upload_data = {
 ### 开关
 is_train = True # 是否训练
 is_debug = False # 是否调试
-is_eta = True # 是否使用eta接口
+is_eta = False # 是否使用eta接口
 is_timefurture = True # 是否使用时间特征
 is_fivemodels = False # 是否使用之前保存的最佳的5个模型
 is_edbcode = False # 特征使用edbcoding列表中的
diff --git a/dataset/jbsh_yuanyou.db b/dataset/jbsh_yuanyou.db
index 89a4b1ae045a4d1d268bc6d27b509f0e87ad33fa..0daf5e6633740c36f315a7a47f47096f0c7e57b5 100644
GIT binary patch
delta 77
zcmV-T0J8sp-~@o+1dtm6)sY-S0oAc!q#pw!3*?grAVUHR<g-yAm<u2tA_FrWGB7eU
jEio}IF*qPGFgi0aIy5pwWo2+qP*hWc1T41%ECKujx!M+K

delta 44
zcmV+{0Mq|~-~@o+1dtm6)R7!R0o1Wzq#pwz3<Q%0AVafJAd?G`kSBu#EVl$K0sI4H
CqYk$K

diff --git a/lib/dataread.py b/lib/dataread.py
index 863be41..ec93b3c 100644
--- a/lib/dataread.py
+++ b/lib/dataread.py
@@ -463,6 +463,8 @@ def datachuli(df_zhibiaoshuju,df_zhibiaoliebiao,datecol='date',end_time='',y='y'
     # 保存每列的最后更新时间到文件
     last_update_times_df = pd.DataFrame(columns  =  ['feature', 'last_update_time','is_value','update_period','warning_date'])
     
+    
+    
     # 打印每列的最后更新时间
     for column, last_update_time in last_update_times.items():
         values = []
@@ -476,7 +478,7 @@ def datachuli(df_zhibiaoshuju,df_zhibiaoliebiao,datecol='date',end_time='',y='y'
             # 计算预警日期
             time_diff = (df1[column].dropna().index.to_series().diff().mode()[0]).total_seconds() / 3600 / 24
             from datetime import timedelta
-            early_warning_date = datetime.datetime.strptime(last_update_time, '%Y-%m-%d') + timedelta(days=time_diff)*2
+            early_warning_date = datetime.datetime.strptime(last_update_time, '%Y-%m-%d') + timedelta(days=time_diff)*2 + timedelta(days=1)
             early_warning_date = early_warning_date.strftime('%Y-%m-%d')
         except KeyError:
             time_diff = 0
@@ -489,15 +491,25 @@ def datachuli(df_zhibiaoshuju,df_zhibiaoliebiao,datecol='date',end_time='',y='y'
     last_update_times_df.to_csv(os.path.join(dataset,'last_update_times.csv'), index=False)
     logger.info('特征停更信息保存到文件：last_update_times.csv')
 
+    logger.info(f'删除预警的特征前数据量：{df.shape}')
+    y_last_update_time = last_update_times['y']
+    columns_to_drop = last_update_times_df[last_update_times_df['warning_date'] < y_last_update_time ]['feature'].values.tolist()
+    df = df.drop(columns = columns_to_drop)
+    
+    logger.info(f'删除预警的特征后数据量：{df.shape}')
 
     logger.info(f'删除两月不更新特征前数据量：{df.shape}')
     # 去掉近最后数据对应的日期在六月以前的列，删除近2月的数据是常熟的列
     current_date = datetime.datetime.now()
     two_months_ago = current_date - timedelta(days=180)
+    
 
     def check_column(col_name):
         '''
-        判断两月不更新指标
+        去掉空值列
+        去掉180天没有更新的列
+        去掉常数值列
+        
         输入：列名
         输出：True or False
         '''
@@ -505,6 +517,7 @@ def datachuli(df_zhibiaoshuju,df_zhibiaoliebiao,datecol='date',end_time='',y='y'
             return False
         df_check_column = df[['ds',col_name]]
         df_check_column = df_check_column.dropna()
+
         if len(df_check_column) == 0:
             print(f'空值列：{col_name}')
             return True
@@ -516,8 +529,13 @@ def datachuli(df_zhibiaoshuju,df_zhibiaoliebiao,datecol='date',end_time='',y='y'
         return corresponding_date < two_months_ago
     columns_to_drop = df.columns[df.columns.map(check_column)].tolist()
     df = df.drop(columns = columns_to_drop)
+    
+
+    
     logger.info(f'删除两月不更新特征后数据量：{df.shape}')
     
+
+    
     # 删除预测列空值的行
     df = df.dropna(subset=['y'])
     logger.info(f'删除预测列为空值的行后数据量：{df.shape}')
diff --git a/main_yuanyou.py b/main_yuanyou.py
index 86bfb98..51afe07 100644
--- a/main_yuanyou.py
+++ b/main_yuanyou.py
@@ -141,11 +141,8 @@ def predict_main():
     
     logger.info('制作报告ing')
     title = f'{settings}--{now}-预测报告' # 报告标题
-    if 'Brent' in y:
-        brent_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time,
-                reportname=reportname,sqlitedb=sqlitedb),
-    else:
-        pp_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time,
+
+    brent_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time,
                 reportname=reportname,sqlitedb=sqlitedb),
 
     logger.info('制作报告end')