[init]

.gitignore

+.idea/

config.py

+#!/usr/bin/env python
+# coding=utf-8
+rl_db_host = 'irongliang-db1-g.mysql.zhangbei.rds.aliyuncs.com'
+# rl_db_host = '39.98.3.182'
+rl_db_port = '3306'
+rl_db_database = 'vision'
+rl_db_user = 'factor_edit'
+rl_db_pwd = 'tcdept_Factoredit'

factor_detail_doc.py

+import pandas as pd
+import sqlalchemy as sa
+from sqlalchemy.orm import sessionmaker
+import config
+
+
+class FactorDetailDoc(object):
+    def __init__(self):
+        db_url = '''mysql+mysqlconnector://{0}:{1}@{2}:{3}/{4}'''.format(config.rl_db_user,
+                                                                         config.rl_db_pwd,
+                                                                         config.rl_db_host,
+                                                                         config.rl_db_port,
+                                                                         config.rl_db_database)
+        self._destination = sa.create_engine(db_url)
+        self._destsession = sessionmaker(bind=self._destination, autocommit=False, autoflush=True)
+        self._factor_detail_columns = ['factor_type', 'factor_name', 'factor_en_name', 'factor_cn_name', 'direction',
+                                       'description','latxt_description', 'unit', 'view_dimension','tag']
+
+    def _exec_sql(self, sql):
+        session = self._destsession()
+        session.execute(sql)
+        session.commit()
+        session.close()
+
+    def update_factor_info(self, df):
+        sql = 'update factor_info set flag = null,is_verify=2'
+        self._exec_sql(sql)
+        df.to_sql(name='factor_info', con=self._destination, if_exists='append', index=False)
+
+    def update_factor_detail(self, df):
+        df = df[self._factor_detail_columns]
+        df.to_sql(name='factor_detail', con=self._destination, if_exists='append', index=False)
+
+    def update(self):
+        excel = pd.read_excel('factor_detail_doc.xlsx', sheet_name=None)
+        sheet_names = list(excel.keys())
+        factor_info = sheet_names.pop(0)
+        self.update_factor_info(excel[factor_info])
+        sql = f'update factor_detail set flag = null,is_verify=2'
+        self._exec_sql(sql)
+        for sheet_name in sheet_names:
+            self.update_factor_detail(excel[sheet_name])
+
+
+if __name__ == '__main__':
+    fd = FactorDetailDoc()
+    fd.update()

factor_direct.py

+#!/usr/bin/env python
+# coding: utf-8
+
+# In[1]:
+
+
+import pandas as pd
+import numpy as np
+import sqlalchemy as sa
+from sqlalchemy.ext.automap import automap_base
+from sqlalchemy.orm import sessionmaker
+from sqlalchemy import select, and_
+
+# In[2]:
+
+
+file_name = ['rl_data1.xlsx', 'rl_data2.xlsx']
+
+# In[3]:
+
+
+merge_data = []
+for file in file_name:
+    print('doc/' + file)
+    if file == 'rl_data1.xlsx':
+        df = pd.read_excel('doc/' + file, skiprows=1)[['因子名称', '因子中文', '类别', '方向']].rename(
+            columns={'因子名称': 'factor_name', '因子中文': 'factor_cn_name', '类别': 'factor_type', '方向': 'direction'})
+    else:
+        df = pd.read_excel('doc/' + file, skiprows=1)[['因子名', '因子中文名', '因子类别', '方向']].rename(
+            columns={'因子名': 'factor_name', '因子中文名': 'factor_cn_name', '因子类别': 'factor_type', '方向': 'direction'})
+    merge_data.append(df)
+merge_data = pd.concat(merge_data)
+
+# In[4]:
+
+
+DB_URL = '''mysql+mysqlconnector://{0}:{1}@{2}:{3}/{4}'''.format(config.rl_db_user,
+                                                                 config.rl_db_pwd,
+                                                                 config.rl_db_host,
+                                                                 config.rl_db_port,
+                                                                 config.rl_db_database)
+
+# In[5]:
+
+
+_engine = sa.create_engine(DB_URL)
+_session = sessionmaker(bind=_engine, autocommit=False, autoflush=True)
+_base = automap_base()
+_base.prepare(_engine, reflect=True)
+
+# In[6]:
+
+
+FactorDetail = _base.classes['factor_detail']
+query = select([FactorDetail]).where(
+    and_(
+        FactorDetail.flag == 1
+    ))
+factor_detail = pd.read_sql(query, _engine)
+factor_detail = factor_detail.drop(['direction'], axis=1)
+
+# In[7]:
+
+
+loads_data = merge_data[['factor_name', 'direction']].merge(factor_detail, on=['factor_name'],
+                                                            ).drop_duplicates(
+    subset=['factor_name'], keep='first').set_index('factor_name')
+
+# In[ ]:
+
+
+for factor_name in loads_data.index.tolist():
+    direction = loads_data.loc[factor_name]['direction']
+    print(factor_name, direction)
+    if np.isnan(direction):
+        continue
+    session = _session()
+    session.execute(
+        '''update {0} set flag = 1, direction = {1}, is_verify=1 where factor_name=\'{2}\' and flag=1'''.format(
+            'factor_detail', int(loads_data.loc[factor_name]['direction']), factor_name))
+    session.commit()
+    session.close()