From 8106ea1e6959278d7e365f34f6458ce301cb21f6 Mon Sep 17 00:00:00 2001 From: workpc Date: Thu, 10 Apr 2025 13:47:36 +0800 Subject: [PATCH] =?UTF-8?q?=E8=B0=83=E8=AF=95=E5=8E=BB=E9=99=A4=E5=88=97?= =?UTF-8?q?=E9=80=BB=E8=BE=91?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- lib/dataread.py | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/lib/dataread.py b/lib/dataread.py index 2405340..3c74674 100644 --- a/lib/dataread.py +++ b/lib/dataread.py @@ -792,11 +792,13 @@ def datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, datecol='date', end_time='', y df['ds'] = pd.to_datetime(df['ds']) # 获取 start_year 对应年份的第一天日期 - start_date = datetime.datetime(config.start_year, 1, 1).strftime('%Y-%m-%d') + start_date = datetime.datetime(config.start_year, 1, 1) # 删除全为空值的列 df = df.dropna(axis=1, how='all') + # 删除开始时间没有数据的列 + config.logger.info(f'删除开始时间没有数据的列前数据量：{df.shape}') for col in df.columns: if col == 'ds': # 跳过 'ds' 列 continue @@ -806,7 +808,9 @@ def datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, datecol='date', end_time='', y # 判断对应的 'ds' 是否大于 start_date if df.loc[first_valid_index, 'ds'] > start_date: df.drop(columns=[col], inplace=True) + config.logger.info(f'删除开始时间没有数据的列：{col},第一条数据日期为：{df.loc[first_valid_index, "ds"]}') + config.logger.info(f'删除开始时间没有数据的列后数据量：{df.shape}') # 获取start_year年到end_time的数据 df = df[df['ds'].dt.year >= config.start_year]