def calage_viellissement_depenses(year_data, year_calage, depenses, masses):
depenses_calees = pandas.DataFrame()
coicop_list = set(depenses.columns)
# print coicop_list
coicop_list.remove('pondmen')
for column in coicop_list:
coicop = normalize_coicop(column)
grosposte = int(coicop[0:2])
# print column, coicop, grosposte
# RAPPEL : 12 postes CN et COICOP
# 01 Produits alimentaires et boissons non alcoolisées
# 02 Boissons alcoolisées et tabac
# 03 Articles d'habillement et chaussures
# 04 Logement, eau, gaz, électricité et autres combustibles
# 05 Meubles, articles de ménage et entretien courant de l'habitation
# 06 Santé
# 07 Transports
# 08 Communication
# 09 Loisir et culture
# 10 Education
# 11 Hotels, cafés, restaurants
# 12 Biens et services divers
if grosposte != 99:
# print 'grosposte: ', grosposte
# print masses
ratio_bdf_cn = masses.at[grosposte, 'ratio_bdf{}_cn{}'.format(year_data, year_data)]
ratio_cn_cn = masses.at[grosposte, 'ratio_cn{}_cn{}'.format(year_data, year_calage)]
depenses_calees[column] = depenses[column] * ratio_bdf_cn * ratio_cn_cn
# print 'Pour le grosposte {}, le ratio de calage de la base bdf {} sur la cn est {}, le ratio de calage sur la cn pour l\'annee {} est {}'.format(grosposte, year_data, ratio_bdf_cn, year_calage,ratio_cn_cn)
return depenses_calees
def select_gros_postes(coicop):
try:
coicop = unicode(coicop)
except:
coicop = coicop
normalized_coicop = normalize_coicop(coicop)
grosposte = normalized_coicop[0:2]
return int(grosposte)
def build_menage_consumption_by_categorie_fiscale(temporary_store=None, year_calage=None, year_data=None):
"""Build menage consumption by categorie fiscale dataframe """
assert temporary_store is not None
assert year_calage is not None
assert year_data is not None
# Load matrices de passage
matrice_passage_data_frame, selected_parametres_fiscalite_data_frame = get_transfert_data_frames(year=year_data)
# Load data
coicop_data_frame = temporary_store["depenses_calees_{}".format(year_calage)]
# Grouping by categorie_fiscale
selected_parametres_fiscalite_data_frame = selected_parametres_fiscalite_data_frame[
["posteCOICOP", "categoriefiscale"]
]
# print selected_parametres_fiscalite_data_frame
selected_parametres_fiscalite_data_frame.set_index("posteCOICOP", inplace=True)
# Normalisation des coicop de la feuille excel pour être cohérent avec depenses_calees
normalized_coicop = [normalize_coicop(coicop) for coicop in selected_parametres_fiscalite_data_frame.index]
selected_parametres_fiscalite_data_frame.index = normalized_coicop
categorie_fiscale_by_coicop = selected_parametres_fiscalite_data_frame.to_dict()["categoriefiscale"]
for key in categorie_fiscale_by_coicop.keys():
import math
if not math.isnan(categorie_fiscale_by_coicop[key]):
categorie_fiscale_by_coicop[key] = int(categorie_fiscale_by_coicop[key])
if math.isnan(categorie_fiscale_by_coicop[key]):
categorie_fiscale_by_coicop[key] = 0
assert type(categorie_fiscale_by_coicop[key]) == int
# print categorie_fiscale_by_coicop
categorie_fiscale_labels = [categorie_fiscale_by_coicop.get(coicop) for coicop in coicop_data_frame.columns]
# TODO: gérer les catégorie fiscales "None" = dépenses énergétiques (4) & tabac (2)
# print categorie_fiscale_labels
tuples = zip(categorie_fiscale_labels, coicop_data_frame.columns)
coicop_data_frame.columns = pandas.MultiIndex.from_tuples(tuples, names=["categoriefiscale", "coicop"])
# print coicop_data_frame.columns
categorie_fiscale_data_frame = coicop_data_frame.groupby(level=0, axis=1).sum()
rename_columns = dict(
[(number, "categorie_fiscale_{}".format(number)) for number in categorie_fiscale_data_frame.columns]
)
categorie_fiscale_data_frame.rename(columns=rename_columns, inplace=True)
categorie_fiscale_data_frame["role_menage"] = 0
# categorie_fiscale_data_frame.reset_index(inplace = True)
categorie_fiscale_data_frame.index = categorie_fiscale_data_frame.index.astype(ident_men_dtype)
temporary_store["menage_consumption_by_categorie_fiscale_{}".format(year_calage)] = categorie_fiscale_data_frame
