x for x in header if x not in [
'CODGEO', 'LIBGEO', 'COM', 'LIBCOM', 'REG', 'DEP', 'ARR', 'CV',
'ZE2010', 'UU2010'
]
]
# Sum NB_F101 to NB_F118
sport['nb_sport'] = sport[[x for x in sport.columns if x[:5] == 'NB_F1' and len(x) == 7]]\
.applymap(lambda x: float(x)).sum(axis=1)
# Sum NB_F101_NB_AIREJEU to NB_F118_NB_AIREJEU
sport['nb_airjeu_sport'] = sport[[x for x in sport.columns if x[:5] == 'NB_F1' and x[-10:] == 'NB_AIREJEU']]\
.applymap(lambda x: float(x)).sum(axis=1)
[features.append(i) for i in ['nb_sport', 'CODGEO']]
print "il y a %d iris différentes pour le sport et %d features" % (len(
sport.CODGEO.unique()), len(features) - 1)
compare_geo(data, sport)
data = pd.merge(data, sport[features], on='CODGEO', how='outer')
## Enseignement 1er degré
enseignement_1 = pd.read_excel('data/equip-serv-ens-1er-degre-infra.xls',
sheetname='IRIS')
# creating header from file
header = enseignement_1.loc[4].tolist()
enseignement_1.columns = header
# to get real values
enseignement_1 = enseignement_1[5:]
# creating new feature : sum all features non aggregated
features = [
x for x in header if x not in [
'CODGEO', 'LIBGEO', 'COM', 'LIBCOM', 'REG', 'DEP', 'ARR', 'CV',
'ZE2010', 'UU2010'
header = sport.loc[4].tolist()
sport.columns = header
# to get real values
sport = sport[5:]
# creating new feature : sum all features non aggregated
features = [x for x in header if x not in ['CODGEO','LIBGEO','COM','LIBCOM','REG','DEP','ARR','CV','ZE2010','UU2010']]
# Sum NB_F101 to NB_F118
sport['nb_sport'] = sport[[x for x in sport.columns if x[:5] == 'NB_F1' and len(x) == 7]]\
.applymap(lambda x: float(x)).sum(axis=1)
# Sum NB_F101_NB_AIREJEU to NB_F118_NB_AIREJEU
sport['nb_airjeu_sport'] = sport[[x for x in sport.columns if x[:5] == 'NB_F1' and x[-10:] == 'NB_AIREJEU']]\
.applymap(lambda x: float(x)).sum(axis=1)
[features.append(i) for i in ['nb_sport', 'CODGEO']]
print "il y a %d iris différentes pour le sport et %d features" % (len(sport.CODGEO.unique()), len(features) - 1)
compare_geo(data, sport)
data = pd.merge(data, sport[features], on='CODGEO', how='outer')
## Enseignement 1er degré
enseignement_1 = pd.read_excel('data/equip-serv-ens-1er-degre-infra.xls', sheetname='IRIS')
# creating header from file
header = enseignement_1.loc[4].tolist()
enseignement_1.columns = header
# to get real values
enseignement_1 = enseignement_1[5:]
# creating new feature : sum all features non aggregated
features = [x for x in header if x not in ['CODGEO','LIBGEO','COM','LIBCOM','REG','DEP','ARR','CV','ZE2010','UU2010']]
# Sum NB_C101 to NB_C105
enseignement_1['nb_enseignement_1'] = enseignement_1[[x for x in enseignement_1.columns if x[:5] == 'NB_C1' and len(x) == 7]]\
.applymap(lambda x: float(x)).sum(axis=1)