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()
def transfo_0(x):
return transfo.local_aggregation(x, 5, 'with_closest', unknown='')
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()
def transfo_0(x):
return transfo.local_aggregation(x, 5, 'with_closest', unknown='')
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()