33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
#!/usr/bin/env python
|
|
# -*- coding: UTF-8 -*-
|
|
|
|
from pycen import con_fon
|
|
import pandas as pd
|
|
|
|
dico_data = '/media/colas/SRV/FICHIERS/OUTILS/BASES DE DONNEES/BILAN_FEDE_CEN/2024/TDB2024_enquete_SIG/Dico_DATA_sites_CEN_v2024.xlsx'
|
|
bilan_2023 = '/media/colas/SRV/FICHIERS/OUTILS/BASES DE DONNEES/BILAN_FEDE_CEN/2024/TDB2024_enquete_SIG/DATA N-1/Sites_CEN_38_2023.csv'
|
|
|
|
dic = pd.read_excel(dico_data,sheet_name='sites_cen_xx_2024',header=0, usecols='F',nrows=50)
|
|
dic_head_name = dic.columns[0]
|
|
bil2023 = pd.read_csv(bilan_2023,sep=',',header=0,encoding='utf-8')
|
|
# Mise en forme des dates
|
|
date_cols = bil2023.columns[bil2023.columns.str.contains('date')]
|
|
bil2023[date_cols] = bil2023[date_cols].apply(pd.to_datetime)
|
|
# Mise en forme de la colonne remq_sensibilite
|
|
|
|
vm_site = pd.read_sql_table('vm_sites_cen_2024_csv',con_fon,'_tdbfcen')
|
|
|
|
|
|
dic_missing = (dic.loc[~dic[dic_head_name].isin(vm_site.columns),dic_head_name]
|
|
.tolist())
|
|
|
|
(bil2023[['id_site_cen',*dic_missing]]
|
|
.merge(vm_site[['id_site_cen']],how='inner',on='id_site_cen')
|
|
.to_sql(
|
|
'_sites_cen_2023_csv_complement',
|
|
con_fon,
|
|
schema='_tdbfcen',
|
|
if_exists='replace',
|
|
index=False))
|
|
|