Python_scripts/5_GEONATURE/pivot_bdc_status_v2.py
2024-05-15 17:04:52 +02:00

94 lines
2.7 KiB
Python

from pycen import con_gn
import numpy as np
import pandas as pd
import os
def get_status(lst):
sql = """
SELECT
t.cd_nom,
t.cd_ref,
t.regne,
t.phylum,
t.classe,
t.ordre,
t.famille,
t.group1_inpn,
t.group2_inpn,
t.nom_vern,
t.nom_complet,
t.nom_valide,
t.lb_nom,
--s.*
s.code_statut,
s.cd_type_statut,
s.label_statut
FROM taxonomie.v_taxref_all_listes t
JOIN taxonomie.v_bdc_status s USING (cd_nom)
WHERE t.cd_nom IN {cd_nom}
;""".format(cd_nom = tuple(lst))
return pd.read_sql_query(sql,con_gn)
if __name__ == "__main__":
PATH = '/media/colas/Disk2/tmp/NICO'
file = 'MAIR_FAUNE&FLORE_PG2024_V0.xlsx'
sheet = 'MAIR_FLORE'
# Liste des CD_NOM en entrée
taxlist = pd.read_excel(os.path.join(PATH,file),sheet,usecols=['cd_nom'],header=1)
df = get_status(taxlist.cd_nom.astype(str))
# df.to_csv('/media/colas/SRV/FICHIERS/TRANSFERTS-EQUIPE/LC/BOCA_CD_NOM_STATUS.csv')
pivot = pd.pivot_table(
df,
values='code_statut',
index=['cd_nom', 'cd_ref','lb_nom'#,'niveau_admin','lb_adm_tr'
],
columns=['cd_type_statut'],
aggfunc=list,fill_value=None)
for c in pivot.columns:
pivot[c] = [x[0] if x is not np.NaN and len(x)==1 else x for x in pivot[c]]
if 'DH' in pivot.columns:
pivot['DH'] = [','.join(x) if (x is not np.NaN) and (len(x)==2) else x for x in pivot['DH']]
pivot.DH.replace({'CDH':''},regex=True,inplace=True)
pivlib = pd.pivot_table(
df,
values='label_statut',
index=['cd_nom', 'cd_ref','lb_nom'#,'niveau_admin','lb_adm_tr'
],
columns=['cd_type_statut'],
aggfunc=list,fill_value=None)
for c in pivlib.columns:
pivlib[c] = [x[0] if x is not np.NaN and len(x)==1 else x for x in pivlib[c]]
if 'DH' in pivot.columns:
pivlib['DH'] = [','.join(x) if (x is not np.NaN) and (len(x)==2) else x for x in pivlib['DH']]
pivlib.DH.replace({'CDH':''},regex=True,inplace=True)
print('INIT writer')
NAME_OUT = os.path.join(PATH,sheet+'_status.xlsx')
with pd.ExcelWriter(NAME_OUT) as writer:
df.to_excel(
writer,sheet_name='v_bdc_status'
)
# writer.save()
print('v_bdc_status OK !')
pivot.to_excel(
writer,sheet_name='pivot_table'
)
# writer.save()
print('pivot_table OK !')
pivlib.to_excel(
writer,sheet_name='pivot_libel'
)
# writer.save()
print('pivot_libel OK !')