mdbq 2.2.2__py3-none-any.whl → 2.2.4__py3-none-any.whl

mdbq/aggregation/query_data.py

@@ -1,4 +1,6 @@
 # -*- coding: UTF-8 –*-
+import re
+
 from mdbq.mongo import mongo
 from mdbq.mysql import mysql
 from mdbq.mysql import s_query
@@ -14,8 +16,6 @@ import getpass
 import json
 import os
 
-from sqlalchemy.event import remove
-
 """
 程序用于下载数据库(调用 s_query.py 下载并清洗), 并对数据进行聚合清洗, 不会更新数据库信息;
 
@@ -862,7 +862,47 @@ class GroupBy:
                        }
                 )
             df.insert(loc=1, column='推广渠道', value='万相台无界版')  # df中插入新列
+            # 1. 匹配 L后面接 2 个或以上数字，不区分大小写，示例：L345
+            # 2. 其余情况，L 后面接多个数字的都会被第一条 if 命中，不区分大小写
+            df['消费力层级'] = df.apply(
+                lambda x:
+                ''.join(re.findall(r'(l\d+)', x['人群名字'].upper(), re.IGNORECASE)) if re.findall(r'(l\d{2,})', x['人群名字'], re.IGNORECASE)
+                else 'L5' if re.findall(r'(l\d*5)', x['人群名字'], re.IGNORECASE)
+                else 'L4' if re.findall(r'(l\d*4)', x['人群名字'], re.IGNORECASE)
+                else 'L3' if re.findall(r'(l\d*3)', x['人群名字'], re.IGNORECASE)
+                else 'L2' if re.findall(r'(l\d*2)', x['人群名字'], re.IGNORECASE)
+                else 'L1' if re.findall(r'(l\d*1)', x['人群名字'], re.IGNORECASE)
+                else '', axis=1)
+            # 1. 匹配连续的 4 个数字且后面不能接数字或"元"或汉字，筛掉的人群示例：月均消费6000元｜受众20240729175213｜xxx2024真皮公文包
+            # 2. 匹配 2数字_2数字且前面不能是数字，合法匹配：人群_30_50_促； 非法示例：L345_3040 避免识别出 35～20 岁用户的情况
+            # pattern = r'(\d{4})(?!\d|[\u4e00-\u9fa5])'  # 匹配 4 个数字，后面不能接数字或汉字
+            # pattern = r'(?<![\d\u4e00-\u9fa5])(\d{4})' # 匹配前面不是数字或汉字的 4 个连续数字
+
+            # 匹配 4 个数字，前面和后面都不能是数字或汉字
+            pattern1 = r'(?<![\d\u4e00-\u9fa5])(\d{4})(?!\d|[\u4e00-\u9fa5])'
+            # 匹配指定字符，前面不能是数字或 l 或 L 开头
+            pattern2 = r'(?<![\dlL])(\d{2}_\d{2})'
+            df['用户年龄'] = df.apply(
+                lambda x:
+                ''.join(re.findall(pattern1, x['人群名字'].upper())) if re.findall(pattern1, x['人群名字'])
+                # else ''.join(re.findall(r'[^\d|l|L](\d{2}_\d{2})', x['人群名字'].upper())) if re.findall(r'[^\d|l|L](\d{2}_\d{2})', x['人群名字'])
+                else ''.join(re.findall(pattern2, x['人群名字'].upper())) if re.findall(pattern2, x['人群名字'])
+                else ''.join(re.findall(r'(\d{2}-\d{2})岁', x['人群名字'].upper())) if re.findall(r'(\d{2}-\d{2})岁', x['人群名字'])
+                else '', axis=1)
+            df['用户年龄'] = df['用户年龄'].apply(
+                lambda x: f'{x[:2]}~{x[2:4]}' if str(x).isdigit()
+                else str(x).replace('_', '~') if '_' in x
+                else str(x).replace('-', '~') if '-' in x
+                else x
+            )
+            # 年龄层不能是 0 开头
+            df['用户年龄'] = df['用户年龄'].apply(
+                lambda x: '' if str(x).startswith('0') else x)
+            # df = df.head(1000)
+            # df.to_csv('/Users/xigua/Downloads/test.csv', index=False, header=True, encoding='utf-8_sig')
+            # breakpoint()
             return df
+
         elif '天猫_关键词报表' in table_name:
             df.rename(columns={
                 '场景名字': '营销场景',
@@ -1774,4 +1814,3 @@ if __name__ == '__main__':
     data_aggregation(service_databases=[{'company': 'mysql'}], months=1)  # 正常的聚合所有数据
     # data_aggregation_one(service_databases=[{'company': 'mysql'}], months=1)  # 单独聚合某一个数据库，具体库进函数编辑
     # 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-2.2.2.dist-info → mdbq-2.2.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mdbq
-Version: 2.2.2
+Version: 2.2.4
 Home-page: https://pypi.org/project/mdbsql
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-2.2.2.dist-info → mdbq-2.2.4.dist-info}/RECORD

@@ -5,7 +5,7 @@ mdbq/aggregation/aggregation.py,sha256=98pECXV6yw7XSjoLnJBgHIQWM2s2aaB8ii5qNebAI
 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=h8AHq0v8xvsGjqoCZkAH1ZXZ3n05Q-JETVR6WDWzCyg,82334
+mdbq/aggregation/query_data.py,sha256=Za8shm_I9ESzfYUVPRPOh8kk3yVWwvWAvwV0mFVx5mI,85340
 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
@@ -38,7 +38,7 @@ mdbq/pbix/pbix_refresh.py,sha256=JUjKW3bNEyoMVfVfo77UhguvS5AWkixvVhDbw4_MHco,239
 mdbq/pbix/refresh_all.py,sha256=viOlLCmz9zg61Q2nzjgl8dChfQxnxRd1A_jmQMb2oDM,5918
 mdbq/pbix/refresh_all_old.py,sha256=_pq3WSQ728GPtEG5pfsZI2uTJhU8D6ra-htIk1JXYzw,7192
 mdbq/spider/__init__.py,sha256=RBMFXGy_jd1HXZhngB2T2XTvJqki8P_Fr-pBcwijnew,18
-mdbq-2.2.2.dist-info/METADATA,sha256=-_fzEPy1JZTOKPkqXghaBcg7ERBf8HzN3G3KOuX6Ino,245
-mdbq-2.2.2.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-mdbq-2.2.2.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
-mdbq-2.2.2.dist-info/RECORD,,
+mdbq-2.2.4.dist-info/METADATA,sha256=KiryBvuQemT-aGcf786FzHmwJJ3eXp7tAzIdHH6I4BM,245
+mdbq-2.2.4.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+mdbq-2.2.4.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
+mdbq-2.2.4.dist-info/RECORD,,