mdbq 3.1.7__tar.gz → 3.1.9__tar.gz

{mdbq-3.1.7 → mdbq-3.1.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 3.1.7
+Version: 3.1.9
 Home-page: https://pypi.org/project/mdbq
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-3.1.7 → mdbq-3.1.9}/mdbq/aggregation/aggregation.py

@@ -1213,38 +1213,80 @@ def one_file_to_mysql(file, db_name, table_name):
     )
 
 
-def test():
-    path = r'/Users/xigua/Downloads/京准通'
-
+def cut_as_year_month(as_month=False):
+    """
+    将表格数据按年划分
+    as_month： true 按月重新保存
+    """
+    file_name = '达摩盘_人群报表'
+    path = r'/Users/xigua/Downloads/数据库导出'
 
     for root, dirs, files in os.walk(path, topdown=False):
         for name in files:
             if name.endswith('.csv') and 'baidu' not in name and '~' not in name:
-                # df = pd.read_excel(os.path.join(root, name), header=0)
-                df = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
-
-                # print(name)
-                if len(df) == 0:
+                pattern = re.findall(r'\d{4}.csv|\d{4}-\d{2}.csv', name)
+                if pattern:
                     continue
-                df['类目ID'] = df['类目ID'].apply(lambda x: 0 if str(x) == 'null' else x)
-                df['类目名称'] = df['类目ID'].apply(lambda x: 0 if str(x) == 'null' else x)
-                df.to_csv(os.path.join(root, name), encoding='utf-8_sig', index=False, header=True)
+                if file_name not in name:
+                    continue
+                # df = pd.read_excel(os.path.join(root, name), header=0)
+                df_before = pd.read_csv(os.path.join(root, name), encoding='utf-8_sig', header=0, na_filter=False)
+                df_before['日期'] = pd.to_datetime(df_before['日期'], format='%Y-%m-%d', errors='ignore')
+                max_date = df_before['日期'].max(skipna=True).year
+                min_date = df_before['日期'].min(skipna=True).year
+                for year in range(min_date, max_date+1):
+                    df = df_before[(df_before['日期'] >= f'{year}-01-01') & (df_before['日期'] <= f'{year}-12-31')]
+                    if as_month:
+                        for month in range(1, 13):
+                            if month < 10:
+                                month = f'0{month}'
+                            for n in range(31, 27, -1):
+                                try:
+                                    end_day = pd.to_datetime(f'{year}-{month}-{n}')
+                                    break
+                                except:
+                                    continue
+                            st_day = pd.to_datetime(f'{year}-{month}-01')
+                            df_month = df[(df['日期'] >= st_day) & (df['日期'] <= end_day)]
+                            if len(df_month) == 0:
+                                continue
+                            df_month.sort_values('日期', ascending=True, ignore_index=True, inplace=True)
+                            df_month = df_month.reset_index(drop=True)
+                            df_month = df_month.reset_index(drop=False)
+                            df_month.pop('id')
+                            df_month.rename(columns={'index': 'id'}, inplace=True)
+                            df_month['id'] = df_month['id'].apply(lambda x: x + 1)
+                            new_name = f'{os.path.splitext(name)[0]}_{year}_{month}.csv'
+                            print(new_name)
+                            df_month.to_csv(os.path.join(root, new_name), encoding='utf-8_sig', index=False, header=True)
+                    else:
+                        df.sort_values('日期', ascending=True, ignore_index=True, inplace=True)
+                        df = df.reset_index(drop=True)
+                        df = df.reset_index(drop=False)
+                        df.pop('id')
+                        df.rename(columns={'index': 'id'}, inplace=True)
+                        df['id'] = df['id'].apply(lambda x: x + 1)
+                        new_name = f'{os.path.splitext(name)[0]}_{year}.csv'
+                        print(new_name)
+                        df.to_csv(os.path.join(root, new_name), encoding='utf-8_sig', index=False, header=True)
 
 
 if __name__ == '__main__':
+    cut_as_year_month(as_month=False)
+
     # username = 'root'
     # password = ''
     # host = ''
     # port = ''
     #
-    # 上传 1 个文件到数据库
-    one_file_to_mysql(
-        file=r'/Users/xigua/Downloads/批量SKU导出-批量任务.xlsx',
-        db_name='属性设置3',
-        table_name='京东商品属性',
-    )
+    # # 上传 1 个文件到数据库
+    # one_file_to_mysql(
+    #     file=r'/Users/xigua/Downloads/批量SKU导出-批量任务.xlsx',
+    #     db_name='属性设置3',
+    #     table_name='京东商品属性',
+    # )
+
 
-    # test()
     # col = 1
     # if col:
     #     # 上传一个目录到指定数据库