mdbq 2.3.9__tar.gz → 2.4.1__tar.gz

{mdbq-2.3.9 → mdbq-2.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 2.3.9
+Version: 2.4.1
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-2.3.9 → mdbq-2.4.1}/mdbq/aggregation/query_data.py

@@ -736,6 +736,44 @@ class MysqlDatasQuery:
         )
         return df
 
+    def dmp_crowd(self):
+        start_date, end_date = self.months_data(num=self.months)
+        projection = {
+            '日期': 1,
+            '人群id': 1,
+            '人群规模': 1,
+            '用户年龄': 1,
+            '消费能力等级': 1,
+            '用户性别': 1,
+        }
+        # projection = {}
+        df_crowd = self.download.data_to_df(
+            db_name='达摩盘2',
+            table_name='我的人群属性',
+            start_date=start_date,
+            end_date=end_date,
+            projection=projection,
+        )
+        df_crowd.sort_values('日期', ascending=True, ignore_index=True, inplace=True)
+        df_crowd.drop_duplicates(subset=['人群id',], keep='last', inplace=True, ignore_index=True)
+        df_crowd.pop('日期')
+        # print(df_crowd)
+
+        projection = {}
+        df_dmp = self.download.data_to_df(
+            db_name='推广数据2',
+            table_name='达摩盘_dmp报表',
+            start_date=start_date,
+            end_date=end_date,
+            projection=projection,
+        )
+        df_dmp.sort_values('日期', ascending=True, ignore_index=True, inplace=True)
+        df_dmp.drop_duplicates(subset=['日期', '人群id', '消耗(元)'], keep='last', inplace=True, ignore_index=True)
+        df = pd.merge(df_dmp, df_crowd, left_on=['人群id'], right_on=['人群id'], how='left')
+        # df.to_csv('/Users/xigua/Downloads/test3.csv', index=False, header=True, encoding='utf-8_sig')
+        return df
+
+
 
 class GroupBy:
     """
@@ -881,7 +919,7 @@ class GroupBy:
                     '成交gmv',
                 ], keep='last', inplace=True, ignore_index=True)
             return df
-        elif '人群报表' in table_name:
+        elif '天猫_人群报表' in table_name and '达摩盘' not in table_name:
             df.rename(columns={
                 '场景名字': '营销场景',
                 '主体id': '商品id',
@@ -1012,11 +1050,16 @@ class GroupBy:
                 df_fl = pd.read_excel(dir_file, sheet_name='关键词分类', header=0)
                 df_fl.rename(columns={'分类1': '词分类'}, inplace=True)
                 df_fl = df_fl[['关键词', '词分类']]
+                # 合并并获取词分类信息
                 df = pd.merge(df, df_fl, left_on=['词名字/词包名字'], right_on=['关键词'], how='left')
                 df.pop('关键词')
                 df['词分类'].fillna('', inplace=True)
             if '词分类' in df.columns.tolist():
-                df['词分类'] = df.apply(lambda x: self.ret_keyword(keyword=str(x['词名字/词包名字']), as_file=False) if x['词分类'] == '' else x['词分类'], axis=1)
+                # 这行决定了，从文件中读取的词分类信息优先级高于 ret_keyword 函数的词分类
+                df['词分类'] = df.apply(
+                    lambda x: self.ret_keyword(keyword=str(x['词名字/词包名字']), as_file=False) if x['词分类'] == ''
+                    else x['词分类'], axis=1
+                )
             else:
                 df['词分类'] = df['词名字/词包名字'].apply(lambda x: self.ret_keyword(keyword=str(x), as_file=False))
             # df.to_csv('/Users/xigua/Downloads/test.csv', index=False, header=True, encoding='utf-8_sig')
@@ -1403,11 +1446,15 @@ class GroupBy:
             df.sort_values(['日期', '店铺', '花费'], ascending=[False, False, False], ignore_index=True, inplace=True)
             # df.to_csv('/Users/xigua/Downloads/test.csv', encoding='utf-8_sig', index=False, header=True)
             return df
+        elif '达摩盘_人群报表' in table_name:
+            return df
+
         else:
             print(f'<{table_name}>: Groupby 类尚未配置，数据为空')
             return pd.DataFrame({})
 
     def ret_keyword(self, keyword, as_file=False):
+        """ 推广关键词报表，关键词分类， """
         datas = [
             {
                 '类别': '品牌词',
@@ -1444,6 +1491,12 @@ class GroupBy:
                     '智选',
                 ]
             },
+            {
+                '类别': '智能',
+                '值': [
+                    '智能',
+                ]
+            },
             {
                 '类别': '年份',
                 '值': [
@@ -1942,6 +1995,12 @@ def data_aggregation(service_databases=[{}], months=1):
                     '唯一主键': [],
                     '数据主体': sdq.aikucun_bd_spu(),
                 },
+                {
+                    '数据库名': '聚合数据',
+                    '集合名': '达摩盘_人群报表',
+                    '唯一主键': [],
+                    '数据主体': sdq.dmp_crowd(),
+                },
             ]
             for items in data_dict:  # 遍历返回结果
                 db_name, table_name, unique_key_list, df = items['数据库名'], items['集合名'], items['唯一主键'], items['数据主体']

{mdbq-2.3.9 → mdbq-2.4.1}/mdbq/req_post/req_tb.py

@@ -574,8 +574,8 @@ def company_run(service_databases=[]):
         r.is_json_file = False
 
         my_data_list = [
-            r.ys_ll_data(),  # 双 11预售实时流量分析
-            r.qxg_hx_data(),  # 抢先购 预热期核心指标
+            # r.ys_ll_data(),  # 双 11预售实时流量分析
+            # r.qxg_hx_data(),  # 抢先购 预热期核心指标
             r.qxg_ll()  # 抢先购 流量来源
         ]
 

{mdbq-2.3.9 → mdbq-2.4.1}/mdbq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 2.3.9
+Version: 2.4.1
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-2.3.9 → mdbq-2.4.1}/setup.py

@@ -3,7 +3,7 @@
 from setuptools import setup, find_packages
 
 setup(name='mdbq',
-      version='2.3.9',
+      version='2.4.1',
       author='xigua, ',
       author_email="2587125111@qq.com",
       url='https://pypi.org/project/mdbsql',