mdbq 1.4.7__py3-none-any.whl → 1.4.9__py3-none-any.whl

mdbq/aggregation/aggregation.py

@@ -1032,12 +1032,12 @@ if __name__ == '__main__':
 
     # test2()
 
-    # file = ''
-    # df = pd.read_csv(file, encoding='utf-8_sig', header=0, na_filter=False)
-    # username, password, host, port = get_myconf.select_config_values(target_service='company', database='mysql')
-    # m = mysql.MysqlUpload(username=username, password=password, host=host, port=port)
-    # m.df_to_mysql(df=df, db_name='test', table_name='增量更新测试',
-    #               drop_duplicates=True,
-    #               # icm_update=['日期', '推广费余额'],
-    #               system_name='company',
-    #               )
+    file = ''
+    df = pd.read_csv(file, encoding='utf-8_sig', header=0, na_filter=False)
+    username, password, host, port = get_myconf.select_config_values(target_service='company', database='mysql')
+    m = mysql.MysqlUpload(username=username, password=password, host=host, port=port)
+    m.df_to_mysql(df=df, db_name='市场数据2', table_name='搜索排行',
+                  drop_duplicates=True,
+                  # icm_update=['日期', '推广费余额'],
+                  system_name='company',
+                  )

mdbq/aggregation/query_data.py

@@ -349,9 +349,60 @@ class GroupBy:
                 }
             )
             return df
-        elif '店铺来源_日数据' in table_name:
+        elif '店铺来源_日数据' in table_name and '旧版' not in table_name:
+            # 包含三级来源名称和预设索引值列
+            # 截取 从上月1日 至 今天的花费数据, 推广款式按此数据从高到低排序（商品图+排序）
+            df_visitor3 = df.groupby(['日期', '三级来源'], as_index=False).agg({'访客数': 'sum'})
+            df_visitor3 = df_visitor3[~df_visitor3['三级来源'].isin([''])]  # 指定列中删除包含空值的行
+            # df_visitor = df_visitor[(df_visitor['日期'] >= f'{year_my}-{last_month.month}-01')]
+            df_visitor3 = df_visitor3.groupby(['三级来源'], as_index=False).agg({'访客数': 'sum'})
+            df_visitor3.sort_values('访客数', ascending=False, ignore_index=True, inplace=True)
+            df_visitor3.reset_index(inplace=True)
+            df_visitor3['index'] = df_visitor3['index'] + 100
+            df_visitor3.rename(columns={'index': '三级访客索引'}, inplace=True)
+            df_visitor3 = df_visitor3[['三级来源', '三级访客索引']]
+
+            # 包含二级来源名称和预设索引值列
+            df_visitor2 = df.groupby(['日期', '二级来源'], as_index=False).agg({'访客数': 'sum'})
+            df_visitor2 = df_visitor2[~df_visitor2['二级来源'].isin([''])]  # 指定列中删除包含空值的行
+            # df_visitor2 = df_visitor2[(df_visitor2['日期'] >= f'{year_my}-{last_month.month}-01')]
+            df_visitor2 = df_visitor2.groupby(['二级来源'], as_index=False).agg({'访客数': 'sum'})
+            df_visitor2.sort_values('访客数', ascending=False, ignore_index=True, inplace=True)
+            df_visitor2.reset_index(inplace=True)
+            df_visitor2['index'] = df_visitor2['index'] + 100
+            df_visitor2.rename(columns={'index': '二级访客索引'}, inplace=True)
+            df_visitor2 = df_visitor2[['二级来源', '二级访客索引']]
+
+            df = pd.merge(df, df_visitor2, how='left', left_on='二级来源', right_on='二级来源')
+            df = pd.merge(df, df_visitor3, how='left', left_on='三级来源', right_on='三级来源')
             return df
-        elif '店铺来源_日数据_旧版' in table_name:
+        elif '天猫_店铺来源_日数据_旧版' in table_name:
+
+            # 包含三级来源名称和预设索引值列
+            # 截取 从上月1日 至 今天的花费数据, 推广款式按此数据从高到低排序（商品图+排序）
+            df_visitor3 = df.groupby(['日期', '三级来源'], as_index=False).agg({'访客数': 'sum'})
+            df_visitor3 = df_visitor3[~df_visitor3['三级来源'].isin([''])]  # 指定列中删除包含空值的行
+            # df_visitor = df_visitor[(df_visitor['日期'] >= f'{year_my}-{last_month.month}-01')]
+            df_visitor3 = df_visitor3.groupby(['三级来源'], as_index=False).agg({'访客数': 'sum'})
+            df_visitor3.sort_values('访客数', ascending=False, ignore_index=True, inplace=True)
+            df_visitor3.reset_index(inplace=True)
+            df_visitor3['index'] = df_visitor3['index'] + 100
+            df_visitor3.rename(columns={'index': '三级访客索引'}, inplace=True)
+            df_visitor3 = df_visitor3[['三级来源', '三级访客索引']]
+
+            # 包含二级来源名称和预设索引值列
+            df_visitor2 = df.groupby(['日期', '二级来源'], as_index=False).agg({'访客数': 'sum'})
+            df_visitor2 = df_visitor2[~df_visitor2['二级来源'].isin([''])]  # 指定列中删除包含空值的行
+            # df_visitor2 = df_visitor2[(df_visitor2['日期'] >= f'{year_my}-{last_month.month}-01')]
+            df_visitor2 = df_visitor2.groupby(['二级来源'], as_index=False).agg({'访客数': 'sum'})
+            df_visitor2.sort_values('访客数', ascending=False, ignore_index=True, inplace=True)
+            df_visitor2.reset_index(inplace=True)
+            df_visitor2['index'] = df_visitor2['index'] + 100
+            df_visitor2.rename(columns={'index': '二级访客索引'}, inplace=True)
+            df_visitor2 = df_visitor2[['二级来源', '二级访客索引']]
+
+            df = pd.merge(df, df_visitor2, how='left', left_on='二级来源', right_on='二级来源')
+            df = pd.merge(df, df_visitor3, how='left', left_on='三级来源', right_on='三级来源')
             return df
         elif '商品id编码表' in table_name:
             df['宝贝id'] = df['宝贝id'].astype(str)
@@ -542,6 +593,12 @@ def data_aggregation_one(service_databases=[{}], months=1, system_name=None,):
             # 从数据库中获取数据, 返回包含 df 数据的字典
             # 单独处理某一个聚合数据库，在这里修改添加 data_dict 的值
             data_dict = [
+                {
+                    '数据库名': '聚合数据',
+                    '集合名': '天猫_店铺来源_日数据_旧版',
+                    '唯一主键': ['日期', '一级来源', '二级来源', '三级来源'],
+                    '数据主体': sdq.dplyd_old(),
+                },
                 {
                     '数据库名': '聚合数据',
                     '集合名': '天猫_店铺来源_日数据',
@@ -665,5 +722,5 @@ def data_aggregation(service_databases=[{}], months=1, system_name=None,):
 
 if __name__ == '__main__':
     # data_aggregation(service_databases=[{'home_lx': 'mysql'}], months=1, system_name='home_lx')
-    data_aggregation_one(service_databases=[{'company': 'mysql'}], months=10, system_name='company')
+    data_aggregation_one(service_databases=[{'company': 'mysql'}], months=12, system_name='company')
     # optimize_data.op_data(service_databases=[{'company': 'mysql'}], days=3650)  # 立即启动对聚合数据的清理工作

mdbq/config/products.py

@@ -17,6 +17,9 @@ class Products:
 
     def update_my_datas(self):
         my_datas = [
+            {
+                '平台': '天猫', '商品id': '830789689032', '上市年份': '2024年9月'
+            },
             {
                 '平台': '天猫', '商品id': '822020840000', '上市年份': '2024年8月'
             },

{mdbq-1.4.7.dist-info → mdbq-1.4.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 1.4.7
+Version: 1.4.9
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-1.4.7.dist-info → mdbq-1.4.9.dist-info}/RECORD

@@ -1,11 +1,11 @@
 mdbq/__init__.py,sha256=Il5Q9ATdX8yXqVxtP_nYqUhExzxPC_qk_WXQ_4h0exg,16
 mdbq/__version__.py,sha256=y9Mp_8x0BCZSHsdLT_q5tX9wZwd5QgqrSIENLrb6vXA,62
 mdbq/aggregation/__init__.py,sha256=EeDqX2Aml6SPx8363J-v1lz0EcZtgwIBYyCJV6CcEDU,40
-mdbq/aggregation/aggregation.py,sha256=uGLS4Zn8oX0TmFxo2G_bDuA7hok4afiZajJZDLxmSNg,59528
+mdbq/aggregation/aggregation.py,sha256=UThzLh2KTL91BpiXxiuy6Z-Nck6v_uqtNnHf3uu-BVs,59513
 mdbq/aggregation/df_types.py,sha256=oQJS2IBU3_IO6GMgbssHuC2yCjNnbta0QPGrFOwNLnU,7591
 mdbq/aggregation/mysql_types.py,sha256=3j_SUTi7qYJyY3JtV_lRLIyczIczmRPE_WaIrXiZ6Rw,11425
 mdbq/aggregation/optimize_data.py,sha256=u2Kl_MFtZueXJ57ycy4H2OhXD431RctUYJYCl637uT0,4176
-mdbq/aggregation/query_data.py,sha256=PBBbnwN8fHxd6H_k8gZygu41bFk0H4oL3sKULa9_YSM,31207
+mdbq/aggregation/query_data.py,sha256=JRHChU4u6e64sZCJ8kfVFNq_FAVuz_kFLwkwBehc0Sg,35762
 mdbq/bdup/__init__.py,sha256=AkhsGk81SkG1c8FqDH5tRq-8MZmFobVbN60DTyukYTY,28
 mdbq/bdup/bdup.py,sha256=LAV0TgnQpc-LB-YuJthxb0U42_VkPidzQzAagan46lU,4234
 mdbq/clean/__init__.py,sha256=A1d6x3L27j4NtLgiFV5TANwEkLuaDfPHDQNrPBbNWtU,41
@@ -14,7 +14,7 @@ mdbq/company/__init__.py,sha256=qz8F_GsP_pMB5PblgJAUAMjasuZbOEp3qQOCB39E8f0,21
 mdbq/company/copysh.py,sha256=RWlQqfpqDiRO1QaVCbPhgAYSopnMoOgcnFhRi0TNFnM,17181
 mdbq/config/__init__.py,sha256=jso1oHcy6cJEfa7udS_9uO5X6kZLoPBF8l3wCYmr5dM,18
 mdbq/config/get_myconf.py,sha256=bp6bVARZVm3ANj1pmM9hLB8Ao539TUWeM9xxeSsBpzw,5994
-mdbq/config/products.py,sha256=9gqXJMsw8KKuD4Xs6krNgcF7AuWDvV7clI6wVi3QjcA,4260
+mdbq/config/products.py,sha256=xJ5-5y3_yf0bU-w5dCe3X1O3iGjmRTTHAz9PFc_B9pU,4386
 mdbq/config/set_support.py,sha256=xkZCX6y9Bq1ppBpJAofld4B2YtchA7fl0eT3dx3CrSI,777
 mdbq/config/update_conf.py,sha256=taL3ZqKgiVWwUrDFuaYhim9a72Hm4BHRhhDscJTziR8,4535
 mdbq/dataframe/__init__.py,sha256=2HtCN8AdRj53teXDqzysC1h8aPL-mMFy561ESmhehGQ,22
@@ -35,7 +35,7 @@ mdbq/pbix/__init__.py,sha256=Trtfaynu9RjoTyLLYBN2xdRxTvm_zhCniUkVTAYwcjo,24
 mdbq/pbix/pbix_refresh.py,sha256=JUjKW3bNEyoMVfVfo77UhguvS5AWkixvVhDbw4_MHco,2396
 mdbq/pbix/refresh_all.py,sha256=tgy762608HMaXWynbOURIf2UVMuSPybzrDXQnOOcnZU,6102
 mdbq/spider/__init__.py,sha256=RBMFXGy_jd1HXZhngB2T2XTvJqki8P_Fr-pBcwijnew,18
-mdbq-1.4.7.dist-info/METADATA,sha256=LtBOaDQcn4v_dj9wjGnSYaoGqXAtzKDdllsXLlCjDFw,245
-mdbq-1.4.7.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-mdbq-1.4.7.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
-mdbq-1.4.7.dist-info/RECORD,,
+mdbq-1.4.9.dist-info/METADATA,sha256=dvW4SLr4_CITHSMOzrcQC3aMZNyvgqvqoOvUgIQQmyc,245
+mdbq-1.4.9.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+mdbq-1.4.9.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
+mdbq-1.4.9.dist-info/RECORD,,