mdbq 2.4.7__py3-none-any.whl → 2.4.8__py3-none-any.whl

mdbq/aggregation/query_data.py

@@ -1002,8 +1002,14 @@ class GroupBy:
             # 下面是添加人群 AIPL 分类
             dir_file = f'\\\\192.168.1.198\\时尚事业部\\01.运营部\\0-电商周报-每周五更新\\分类配置文件.xlsx'
             dir_file2 = '/Volumes/时尚事业部/01.运营部/0-电商周报-每周五更新/分类配置文件.xlsx'
+            if platform.system() == 'Windows':
+                dir_file3 = 'C:\\同步空间\\BaiduSyncdisk\\原始文件2\\分类配置文件.xlsx'
+            else:
+                dir_file3 = '/Users/xigua/数据中心/原始文件2/分类配置文件.xlsx'
             if not os.path.isfile(dir_file):
                 dir_file = dir_file2
+            if not os.path.isfile(dir_file):
+                dir_file = dir_file3
             if os.path.isfile(dir_file):
                 df_fl = pd.read_excel(dir_file, sheet_name='人群分类', header=0)
                 df_fl = df_fl[['人群名字', '人群分类']]
@@ -1012,12 +1018,22 @@ class GroupBy:
                 df['人群分类'].fillna('', inplace=True)
             if '人群分类' in df.columns.tolist():
                 # 这行决定了，从文件中读取的分类信息优先级高于内部函数的分类规则
+                # 这个 lambda 适配人群名字中带有特定标识的分类，强匹配
                 df['人群分类'] = df.apply(
                     lambda x: self.set_crowd(keyword=str(x['人群名字']), as_file=False) if x['人群分类'] == ''
                     else x['人群分类'], axis=1
                 )
+                # 这个 lambda 适配人群名字中聚类的特征字符，弱匹配
+                df['人群分类'] = df.apply(
+                    lambda x: self.set_crowd2(keyword=str(x['人群名字']), as_file=False) if x['人群分类'] == ''
+                    else x['人群分类'], axis=1
+                )
             else:
                 df['人群分类'] = df['人群名字'].apply(lambda x: self.set_crowd(keyword=str(x), as_file=False))
+                df['人群分类'] = df.apply(
+                    lambda x: self.set_crowd2(keyword=str(x['人群名字']), as_file=False) if x['人群分类'] == ''
+                    else x['人群分类'], axis=1
+                )
             df['人群分类'] = df['人群分类'].apply(lambda x: str(x).upper() if x else x)
             # df.to_csv('/Users/xigua/Downloads/test_人群分类.csv', index=False, header=True, encoding='utf-8_sig')
             # breakpoint()
@@ -1071,7 +1087,7 @@ class GroupBy:
                 dir_file = dir_file2
             if os.path.isfile(dir_file):
                 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.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')
@@ -1678,6 +1694,103 @@ class GroupBy:
         if not is_res:
             return ''
 
+    def set_crowd2(self, keyword, as_file=False):
+        """ 推广人群报表，人群分类， """
+        datas = [
+            {
+                '类别': 'A',
+                '值': [
+                    '相似宝贝',
+                    '相似店铺',
+                    '类目',
+                    '88VIP',
+                    '拉新',
+                    '潮流',
+                    '会场',
+                    '意向',
+                    '>>',  # 系统推荐的搜索相关人群
+                    '关键词：',  # 系统推荐的搜索相关人群
+                    '关键词_',  # 自建的搜索相关人群
+                    '扩展',
+                    '敏感人群',
+                    '尝鲜',
+                    '小二推荐',
+                    '竞争',
+                    '资深',
+                    '女王节',
+                    '本行业',
+                    '618',
+                    '包包树',
+                    '迪桑娜',
+                    '菲安妮',
+                    '卡思乐',
+                    '场景词',
+                    '竞对',
+                    '精选',
+                    '发现',
+                    '行业mvp'
+                    '特征继承',
+                    '机会',
+                    '推荐',
+                    '智能定向',
+                ]
+            },
+            {
+                '类别': 'I',
+                '值': [
+                    '行动',
+                    '收加',
+                    '收藏',
+                    '加购',
+                    '促首购',
+                    '店铺优惠券',
+                    '高转化',
+                    '认知',
+                    '喜欢我',  # 系统推荐的宝贝相关人群
+                    '未购买',
+                    '种草',
+                    '兴趣',
+                    '本店',
+                    '领券',
+                ]
+            },
+            {
+                '类别': 'P',
+                '值': [
+                    '万里马',
+                    '购买',
+                    '已购',
+                    '促复购'
+                    '店铺会员',
+                    '店铺粉丝',
+                    '转化',
+                ]
+            },
+            {
+                '类别': 'L',
+                '值': [
+                    'L人群',
+                ]
+            },
+        ]
+        if as_file:
+            with open(os.path.join(self.output, f'分类配置_推广人群分类_函数内置规则.json'), 'w') as f:
+                json.dump(datas, f, ensure_ascii=False, sort_keys=False, indent=4)
+            breakpoint()
+        result = ''
+        res = []
+        is_continue = False
+        for data in datas:
+            for item in data['值']:
+                res = re.findall(item, str(keyword), re.IGNORECASE)
+                if res:
+                    result = data['类别']
+                    is_continue = True
+                    break
+            if is_continue:
+                break
+        return result
+
     # @try_except
     def performance(self, bb_tg=True):
          # print(self.data_tgyj)

{mdbq-2.4.7.dist-info → mdbq-2.4.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 2.4.7
+Version: 2.4.8
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-2.4.7.dist-info → mdbq-2.4.8.dist-info}/RECORD

@@ -5,7 +5,7 @@ mdbq/aggregation/aggregation.py,sha256=nPp5fOLktxejNEak3SyTnKLjwzK1l2xjbV45X-I4L
 mdbq/aggregation/df_types.py,sha256=U9i3q2eRPTDY8qAPTw7irzu-Tlg4CIySW9uYro81wdk,8125
 mdbq/aggregation/mysql_types.py,sha256=DQYROALDiwjJzjhaJfIIdnsrNs11i5BORlj_v6bp67Y,11062
 mdbq/aggregation/optimize_data.py,sha256=Wis40oL04M7E1pkvgNPjyVFAUe-zgjimjIVAikxYY8Y,4418
-mdbq/aggregation/query_data.py,sha256=_RYPlUDg5Hmfm663gx7vGh0HHfgnik9BDqLPQCl9w5A,98932
+mdbq/aggregation/query_data.py,sha256=mL9kGu1sZf0bIRI_s2PwF12tPR0z7jGkC_qWAz_5wG8,103128
 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
@@ -41,7 +41,7 @@ mdbq/req_post/__init__.py,sha256=jso1oHcy6cJEfa7udS_9uO5X6kZLoPBF8l3wCYmr5dM,18
 mdbq/req_post/req_tb.py,sha256=PexWSCPJNM6Tv0ol4lAWIhlOwsAr_frnjtcdSHCFiek,36179
 mdbq/spider/__init__.py,sha256=RBMFXGy_jd1HXZhngB2T2XTvJqki8P_Fr-pBcwijnew,18
 mdbq/spider/aikucun.py,sha256=Olq7IJP9itM4wuNxZeHOG-Q3i8wWyB4hY8TUGGwCvQ0,14104
-mdbq-2.4.7.dist-info/METADATA,sha256=dBLtWhjOK1TZ87LrmoRgLAz7NHJYtQiC01dRimYwZ90,245
-mdbq-2.4.7.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-mdbq-2.4.7.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
-mdbq-2.4.7.dist-info/RECORD,,
+mdbq-2.4.8.dist-info/METADATA,sha256=1PkjCLlpg0ipzA5WgllXzHDYkMUb10_sMB0RU2xIIww,245
+mdbq-2.4.8.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+mdbq-2.4.8.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
+mdbq-2.4.8.dist-info/RECORD,,