# -*- coding: utf-8 -*- """ Created on Wed Jan 20 11:37:34 2016 @author: Alexis Eidelman """ #TODO: import unittest from anonymizer.anonymDF import AnonymDataFrame import anonymizer.transformations as transfo from generate_tab import random_table_test_anonym tab = random_table_test_anonym(1000, 8, 5) test = AnonymDataFrame(tab, ['identifiant'], 'sensible') test.get_k() test.get_l() nb_cols = 4 tab = random_table_test_anonym((1000, nb_cols), 8, 5) nom_cols = ['ident_' + str(k) for k in range(nb_cols)] tab = tab.astype(str) test = AnonymDataFrame(tab, nom_cols, 'sensible') test.get_k() test.get_l()
var = avantages.columns.tolist()
var.remove('ligne_type')
var.remove('avant_nature')
# ## II. Traitement des données brutes (sans INSEE)
# On k-anonymise dès maintenant la base brute.
# On définit ici k = 5
ordre_aggregation = [
'benef_dept', 'benef_categorie_code', 'qualite', 'benef_pays_code',
'benef_titre_code', 'benef_identifiant_type_code'
]
Avantages = AnonymDataFrame(avantages.copy(),
ordre_aggregation,
unknown='non renseigné')
k = 5
def aggregation_serie(x):
return (local_aggregation(x, k, 'regroup_with_smallest', 'non renseigné'))
def aggregation_year(x):
return (local_aggregation(x, k, 'with_closest', 'non renseigné'))
method_anonymisation = [
(name, aggregation_serie) for name in ordre_aggregation[:-1]
] + [('date', aggregation_year)]
# -*- coding: utf-8 -*- """ Created on Wed Jan 20 11:37:34 2016 @author: Alexis Eidelman """ #TODO: import unittest from anonymizer.anonymDF import AnonymDataFrame import anonymizer.transformations as transfo from generate_tab import random_table_test_anonym tab = random_table_test_anonym(1000, 8, 5) test = AnonymDataFrame(tab, ['identifiant'], 'sensible') test.get_k() test.get_l() nb_cols = 4 tab = random_table_test_anonym((1000, nb_cols), 8, 5) nom_cols = ['ident_' + str(k) for k in range(nb_cols)] tab = tab.astype(str) test = AnonymDataFrame(tab, nom_cols, 'sensible') test.get_k() test.get_l()
# ## II. Traitement des données brutes (sans INSEE)
# On k-anonymise dès maintenant la base brute.
# On définit ici k = 5
ordre_aggregation = ['benef_dept',
'benef_categorie_code',
'qualite',
'benef_pays_code',
'benef_titre_code',
'benef_identifiant_type_code']
Avantages = AnonymDataFrame(avantages.copy(), ordre_aggregation, unknown='non renseigné')
k = 5
def aggregation_serie(x):
return(local_aggregation(x, k, 'regroup_with_smallest', 'non renseigné'))
def aggregation_year(x):
return(local_aggregation(x, k, 'with_closest', 'non renseigné'))
method_anonymisation = [(name, aggregation_serie) for name in ordre_aggregation[:-1]] + [('date', aggregation_year)]
Avantages.local_transform(method_anonymisation, k)
modalites_modifiees = (Avantages.anonymized_df.values != avantages.values).sum()
modalites_intactes = (Avantages.anonymized_df.values == avantages.values).sum()
len(liste_races)
# ## II. Anonymisation
# On définit les variables à anonymiser
ordre_aggregation = ['Race',
'Sexe',
'Robe',
'Pays de naissance',
'Destiné à la consommation humaine',
'Date de naissance']
Equides = AnonymDataFrame(equides, ordre_aggregation, unknown='non renseigné')
def aggregation_serie(x):
return(local_aggregation(x, 5, 'regroup_with_smallest', 'non renseigné'))
method_anonymisation = [(name, aggregation_serie) for name in ordre_aggregation[:-1]]
def aggregation_year(x):
return(local_aggregation(x, 5, 'with_closest', 'non renseigné'))
method_anonymisation += [('Date de naissance', aggregation_year)]
Equides.local_transform(method_anonymisation, 5)
Equides.df = Equides.anonymized_df
Equides.get_k()
# -*- coding: utf-8 -*- """ Created on Wed Jan 20 11:37:34 2016 @author: Alexis Eidelman """ #TODO: import unittest from anonymizer.anonymDF import AnonymDataFrame from generate_tab import random_table_test_anonym tab = random_table_test_anonym(1000, 8, 5) test = AnonymDataFrame(tab, ['identifiant'], 'sensible') test.get_k() test.get_l()
