54 lines
2.3 KiB
Python
54 lines
2.3 KiB
Python
|
|
||
|
|
from pathlib import Path
|
||
|
|
import re
|
||
|
|
import pandas
|
||
|
|
|
||
|
|
|
||
|
|
def cnrsformat1_to_sheet(in_tsv_file_path: Path, out_tsv_file_path: Path):
|
||
|
|
with open(in_tsv_file_path) as inf, open(out_tsv_file_path, 'wt') as outf:
|
||
|
|
table_header_has_been_written = False
|
||
|
|
for line in inf.readlines():
|
||
|
|
ignore_line = False
|
||
|
|
# Entité dépensière : AESJULLIEN AES RENNES METROPOLE MC JULLIEN Crédits reçus : 40,000.00
|
||
|
|
# Disponible : 24,743.14
|
||
|
|
#
|
||
|
|
#
|
||
|
|
# N° commande Souche Libellé commande Date commande Raison sociale fournisseur Montant consommé sur exercice antérieur Montant consommé sur l'exercice Montant réservé Montant facturé Code origine Nature dépense Statut Cde groupée
|
||
|
|
if re.match(r'^Entité dépensière', line):
|
||
|
|
ignore_line = True
|
||
|
|
is_table_header = re.match(r'^N° commande', line) is not None
|
||
|
|
# 19,572.00 19AESMCJ CAMERA ZYLA 5.5 sCMOS 04/11/19 ANDOR TECHNOLOGY LIMITED 0.00 13,681.56 0.00 0.00 635991 IM
|
||
|
|
if is_table_header and not table_header_has_been_written:
|
||
|
|
outf.write('# %s' % line)
|
||
|
|
table_header_has_been_written = True
|
||
|
|
if re.match(r'^[0-9,./]+\t', line):
|
||
|
|
outf.write(line)
|
||
|
|
|
||
|
|
|
||
|
|
def main():
|
||
|
|
cnrsformat1_file_path = Path('./from-cloud.ipr/2019/commandes-2019-cnrs-t001.tsv')
|
||
|
|
sheet_file_path = Path('./tmp/commandes-2019-cnrs.tsv')
|
||
|
|
cnrsformat1_to_sheet(cnrsformat1_file_path, sheet_file_path)
|
||
|
|
|
||
|
|
df = pandas.read_csv(sheet_file_path, sep='\t')
|
||
|
|
|
||
|
|
# delete the colums for which the labve is of the form 'Unnamed: <n>'. They come from the csv export of libre office
|
||
|
|
unnamed_columns = [column_label for column_label in df.keys() if re.match(r'^Unnamed', column_label) is not None]
|
||
|
|
print(unnamed_columns)
|
||
|
|
df = df.drop(columns=unnamed_columns)
|
||
|
|
|
||
|
|
print(df.columns)
|
||
|
|
print(df.keys())
|
||
|
|
print(df)
|
||
|
|
it_df = df[(df['Raison sociale fournisseur'] == 'DELL SAS') | (df['Raison sociale fournisseur'] == 'ECONOCOM PRODUCTS & SOLUTIONS')]
|
||
|
|
# 'AMAZON EU SARL SUCCURSALE FRANCAISE'
|
||
|
|
# 'INMAC'
|
||
|
|
# 'RETIS'
|
||
|
|
# 'APIXIT'
|
||
|
|
print(it_df)
|
||
|
|
|
||
|
|
print(it_df[['Montant facturé', 'Raison sociale fournisseur', 'Libellé commande']])
|
||
|
|
|
||
|
|
|
||
|
|
main()
|