def age_group_initiate_average(df_train, age_list, age_group_number, k, l):
age_list.sort()
age_group_dict = {} ## key: age; value: group
group_age_dict = {} ## key: group; value: age list
age_group_len = int(len(age_list) / age_group_number)
age_group_code = 0
age_min = age_list[0]
for i in range(age_group_number):
if i < age_group_number - 1:
group_age_dict[i] = age_list[age_group_len * i:age_group_len *
(i + 1)]
else:
group_age_dict[i] = age_list[age_group_len * i:]
k_cur = funcs.k_anonymity(df_train, group_age_dict[i])
if k_cur < k:
print("k-anominity: age group initiate failure...")
group_age_dict = {}
break
else:
l_cur = funcs.l_diversity(df_train, group_age_dict[i])
if l_cur >= l:
age_group_code = age_group_code + 1
else:
print("l-diversity: age group initiate failure...")
group_age_dict = {}
break
for group, group_age_list in group_age_dict.items():
for age in group_age_list:
age_group_dict[age] = group
return age_group_dict, group_age_dict
def HyObscure(df_train, grid_area_dict, area_grid_dict, cluster_num,
grid_area_number, grid_list, area_reducibility,
area_grid_rowcol_dict, area_grid_colrow_dict, method,
grid_rowcol, grid_colrow, l_threshold, k_threshold, deltaX, pp):
df_train_copy = copy.deepcopy(df_train)
df_train_copy['grid_group'] = pd.Series(np.zeros(df_train_copy.shape[0]),
index=df_train_copy.index,
dtype='int32')
user_num = df_train_copy.shape[0]
X_ori = {}
for k in range(user_num):
user_id = df_train_copy['uid'][k]
X_ori[user_id] = df_train_copy[df_train_copy['uid'] == user_id].values[
0, :-1]
for k in X_ori.keys():
user_grid = X_ori[k][-2]
X_ori[k][-3] = grid_area_dict[user_grid]
for i in area_grid_dict:
print("user number in area ", i, " is ",
funcs.k_anonymity(df_train, area_grid_dict[i]))
print("start solving xpgg...")
xpgg = np.ones((cluster_num * grid_area_number,
cluster_num * grid_area_number)) * 0.00000001
JSD_Mat = np.ones(
(cluster_num * grid_area_number, cluster_num * grid_area_number))
pgy = np.ones(
(len(grid_list), cluster_num * grid_area_number)) * 0.00000001
JSD_Mat_dict = {}
pgy_dict = {}
for op in range(0, 6):
## compute JSD and pgy
JSD_Mat, pgy, JSD_Mat_dict, pgy_dict = funcs.get_JSD_PGY(
df_train, area_grid_dict, JSD_Mat_dict, cluster_num, pgy_dict,
JSD_Mat, pgy, method)
print('op:', op)
grid_xpgg_dict = {}
## compute xpgg
for gg in range(0, grid_area_number):
eng = matlab.engine.start_matlab()
eng.edit('../../matlab/checkin_clusternum_scenario_II/HyObscure',
nargout=0)
eng.cd('../../matlab/checkin_clusternum_scenario_II', nargout=0)
grid_xpgg_dict[gg] = np.array(eng.HyObscure(deltaX, gg))
for row in range(cluster_num):
for col in range(cluster_num):
xpgg[gg + row * grid_area_number,
gg + col * grid_area_number] = grid_xpgg_dict[gg][row,
col]
mean_Utility = funcs.Mean_JSD(JSD_Mat, xpgg)
mean_Privacy = funcs.Mean_KL_div(pgy, xpgg)
min_mean_Utility = mean_Utility
min_mean_Privacy = mean_Privacy
## area_grid_rowcol_dict, area_grid_colrow_dict, area_grid_dict, grid_area_dict, area_reducibility
areas = list(area_grid_dict.keys())
random.shuffle(areas)
### change grid group (area) by stochastic privacy-utility boosting
for area_code in areas: ##select one area to adjust
area_grids = area_grid_dict[
area_code] ## get all the grids in the area
l_cur = funcs.l_diversity(df_train,
area_grids) ## check l diversity
l_range = int(np.exp(l_cur) - np.exp(np.log(l_threshold)))
print('start adjusting area: ', area_code)
if l_range > 0:
### select one direction to adjust: left (0); right (1); up (2); down(3)
d = np.random.choice([0, 1, 2, 3],
p=area_reducibility[area_code] /
np.sum(area_reducibility[area_code]))
# the selected area can be reduced through the selected direction
if d < 2: ## change left or right
area_grid_line_list_dict = area_grid_rowcol_dict
line_list_to_grid = funcs.rowcol_to_grid
grid_linelist = grid_rowcol
else: ## change up or down
area_grid_line_list_dict = area_grid_colrow_dict
line_list_to_grid = funcs.colrow_to_grid
grid_linelist = grid_colrow
area_lines = list(area_grid_line_list_dict[area_code].keys())
area_lines.sort()
for line in area_lines:
# recheck area l diversity
area_grids = area_grid_dict[
area_code] ## get all the grids in the area
l_cur = funcs.l_diversity(df_train,
area_grids) ## check l diversity
l_range = int(np.exp(l_cur) - np.exp(np.log(l_threshold)))
change_range = l_range
line_lists = area_grid_line_list_dict[area_code][line]
line_lists.sort()
line_lists_len = len(line_lists)
if change_range > line_lists_len:
change_range = line_lists_len
for i in range(1, change_range + 1):
if d == 0 or d == 3:
moveout_grid_lists = line_lists[-i:]
elif d == 1 or d == 2:
moveout_grid_lists = line_lists[:i]
moveout_grids = []
for mgc in moveout_grid_lists:
moveout_grids.append(line_list_to_grid(line, mgc))
adjusted_area_grids = list(
set(area_grids) - set(moveout_grids))
## check k anonymity
k_adjust = funcs.k_anonymity(df_train,
adjusted_area_grids)
## the adjusted schema meets both k-anonymity and l-diversity
if k_adjust >= k_threshold:
if d == 0:
to_area = area_code + 1
elif d == 1:
to_area = area_code - 1
elif d == 2:
to_area = area_code - int(
grid_area_number /
int(np.sqrt(grid_area_number)))
elif d == 3:
to_area = area_code + int(
grid_area_number /
int(np.sqrt(grid_area_number)))
## adjust grid groups (areas): update area_grid_dict and grid_area_dict
area_grid_dict_cur = copy.deepcopy(area_grid_dict)
adjusted_area_grids.sort()
area_grid_dict_cur[area_code] = adjusted_area_grids
area_grid_dict_cur[to_area] = list(
set(area_grid_dict_cur[to_area])
| set(moveout_grids))
area_grid_dict_cur[to_area].sort()
grid_area_dict_cur = copy.deepcopy(grid_area_dict)
for grid in moveout_grids:
grid_area_dict_cur[grid] = to_area
for i in area_grid_dict_cur:
print("area:", i, "grid number:",
len(area_grid_dict_cur[i]))
print('from area: ', area_code, 'to area: ',
to_area, 'change line: ', line,
'moveout_grids: ', moveout_grids)
df_train_new = funcs.update_grid_group(
df_train, grid_area_dict_cur)
# try:
new_JSD_Mat, new_pgy, new_JSD_Mat_dict, new_pgy_dict = funcs.get_JSD_PGY(
df_train_new, area_grid_dict_cur, JSD_Mat_dict,
cluster_num, pgy_dict, JSD_Mat, pgy, method)
new_mean_Utility = funcs.Mean_JSD(
new_JSD_Mat, xpgg)
new_mean_Privacy = funcs.Mean_KL_div(new_pgy, xpgg)
if new_mean_Privacy < min_mean_Privacy and new_mean_Utility < min_mean_Utility:
min_mean_Utility = new_mean_Utility
min_mean_Privacy = new_mean_Privacy
min_grid_area_dict = grid_area_dict_cur
min_area_grid_dict = area_grid_dict_cur
min_df_train = df_train_new
grid_area_dict = min_grid_area_dict
area_grid_dict = min_area_grid_dict
df_train = min_df_train
min_distortion_budget = min_mean_Utility
area_grid_rowcol_dict, area_grid_colrow_dict = funcs.update_rowcol_colrow_dict(
area_grid_dict)
print("! Find a better area group")
break
print(op, area_code, to_area, line, mgc,
mean_Privacy, mean_Utility, min_mean_Privacy,
min_mean_Utility, new_mean_Privacy,
new_mean_Utility)
else:
print("*** area not meet k_anonymity requirement")
else:
print("*** area not meet l_diversity requirement")
df_train = funcs.update_grid_group(df_train, grid_area_dict)
X_obf_dict = {}
for i in range(25):
X_obf_dict[i], _ = funcs.get_obf_X(df_train, xpgg, pp)
return X_obf_dict, X_ori