expt: Testing epsilon percentages
This commit is contained in:
154
code/expt/copenhagen-sel-eps.py
Normal file
154
code/expt/copenhagen-sel-eps.py
Normal file
@ -0,0 +1,154 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
import sys
|
||||
sys.path.insert(1, '../lib')
|
||||
import argparse
|
||||
import ast
|
||||
from datetime import datetime
|
||||
from geopy.distance import distance
|
||||
import lmdk_bgt
|
||||
import lmdk_lib
|
||||
import lmdk_sel
|
||||
import exp_mech
|
||||
import math
|
||||
import numpy as np
|
||||
from matplotlib import pyplot as plt
|
||||
import time
|
||||
|
||||
|
||||
def main(args):
|
||||
# Contacts for all users
|
||||
cont_data = lmdk_lib.load_data(args, 'cont')
|
||||
# Contacts for landmark's percentages for all users
|
||||
lmdk_data = lmdk_lib.load_data(args, 'usrs_data')
|
||||
# The name of the dataset
|
||||
d = 'Copenhagen'
|
||||
# The user's id
|
||||
uid = '449'
|
||||
# The landmarks percentages
|
||||
lmdks_pct = [0, 20, 40, 60, 80, 100]
|
||||
# The privacy budget
|
||||
epsilon = 1.0
|
||||
eps_pct = [20, 40, 60, 80]
|
||||
|
||||
markers = [
|
||||
'^', # 20
|
||||
'v', # 40
|
||||
'D', # 60
|
||||
's' # 80
|
||||
]
|
||||
|
||||
print('\n##############################', d, '\n')
|
||||
# Get user's contacts sequence
|
||||
seq = cont_data[cont_data[:, 1] == float(uid)][:1000]
|
||||
|
||||
# Initialize plot
|
||||
lmdk_lib.plot_init()
|
||||
# The x axis
|
||||
x_i = np.arange(len(lmdks_pct))
|
||||
plt.xticks(x_i, np.array(lmdks_pct, int))
|
||||
plt.xlabel('Landmarks (%)') # Set x axis label.
|
||||
plt.xlim(x_i.min(), x_i.max())
|
||||
# The y axis
|
||||
plt.ylabel('Mean absolute error (%)') # Set y axis label.
|
||||
# plt.yscale('log')
|
||||
plt.ylim(0, 100)
|
||||
|
||||
mae_evt = 0
|
||||
mae_usr = 0
|
||||
|
||||
for i_e, e in enumerate(eps_pct):
|
||||
mae = np.zeros(len(lmdks_pct))
|
||||
|
||||
for i, pct in enumerate(lmdks_pct):
|
||||
# Find landmarks
|
||||
lmdks = lmdk_lib.find_lmdks_cont(lmdk_data, seq, uid, pct)
|
||||
|
||||
for _ in range(args.iter):
|
||||
|
||||
lmdks_sel = lmdk_sel.find_lmdks_eps(seq, lmdks, epsilon*e/100)
|
||||
|
||||
# Uniform
|
||||
rls_data, _ = lmdk_bgt.uniform_cont(seq, lmdks_sel, epsilon*(1 - e/100))
|
||||
mae[i] += (lmdk_bgt.mae_cont(rls_data)/args.iter)*100
|
||||
|
||||
# Calculate once
|
||||
if e == eps_pct[0] and pct == lmdks_pct[0]:
|
||||
# Event
|
||||
rls_data_evt, _ = lmdk_bgt.uniform_cont(seq, lmdks, epsilon)
|
||||
mae_evt += (lmdk_bgt.mae_cont(rls_data_evt)/args.iter)*100
|
||||
elif e == eps_pct[-1] and pct == lmdks_pct[-1]:
|
||||
# User
|
||||
rls_data_usr, _ = lmdk_bgt.uniform_cont(seq, lmdks, epsilon)
|
||||
mae_usr += (lmdk_bgt.mae_cont(rls_data_usr)/args.iter)*100
|
||||
|
||||
# Plot line
|
||||
plt.plot(
|
||||
x_i,
|
||||
mae,
|
||||
label=str(e/100) + 'ε',
|
||||
marker=markers[i_e],
|
||||
markersize=lmdk_lib.marker_size,
|
||||
markeredgewidth=0,
|
||||
linewidth=lmdk_lib.line_width
|
||||
)
|
||||
|
||||
|
||||
plt.axhline(
|
||||
y = mae_evt,
|
||||
color = '#212121',
|
||||
linewidth=lmdk_lib.line_width
|
||||
)
|
||||
plt.text(x_i[-1] + x_i[-1]*.01, mae_evt - mae_evt*.05, 'event')
|
||||
|
||||
plt.axhline(
|
||||
y = mae_usr,
|
||||
color = '#616161',
|
||||
linewidth=lmdk_lib.line_width
|
||||
)
|
||||
plt.text(x_i[-1] + x_i[-1]*.01, mae_usr - mae_usr*.05, 'user')
|
||||
|
||||
path = str('../../rslt/lmdk_sel_eps/' + d)
|
||||
# Plot legend
|
||||
lmdk_lib.plot_legend()
|
||||
# # Show plot
|
||||
# plt.show()
|
||||
# Save plot
|
||||
lmdk_lib.save_plot(path + '-sel-eps.pdf')
|
||||
print('[OK]', flush=True)
|
||||
|
||||
|
||||
def parse_args():
|
||||
'''
|
||||
Parse arguments.
|
||||
|
||||
Optional:
|
||||
res - The results archive file.
|
||||
iter - The total iterations.
|
||||
'''
|
||||
# Create argument parser.
|
||||
parser = argparse.ArgumentParser()
|
||||
|
||||
# Mandatory arguments.
|
||||
|
||||
# Optional arguments.
|
||||
parser.add_argument('-r', '--res', help='The results archive file.', type=str, default='/home/manos/Cloud/Data/Copenhagen/Results.zip')
|
||||
parser.add_argument('-i', '--iter', help='The total iterations.', type=int, default=1)
|
||||
|
||||
# Parse arguments.
|
||||
args = parser.parse_args()
|
||||
|
||||
return args
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
try:
|
||||
start_time = time.time()
|
||||
main(parse_args())
|
||||
end_time = time.time()
|
||||
print('##############################')
|
||||
print('Time elapsed: %s' % (time.strftime('%H:%M:%S', time.gmtime(end_time - start_time))))
|
||||
print('##############################')
|
||||
except KeyboardInterrupt:
|
||||
print('Interrupted by user.')
|
||||
exit()
|
||||
149
code/expt/hue-sel-eps.py
Normal file
149
code/expt/hue-sel-eps.py
Normal file
@ -0,0 +1,149 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
import sys
|
||||
sys.path.insert(1, '../lib')
|
||||
import argparse
|
||||
import ast
|
||||
from datetime import datetime
|
||||
from geopy.distance import distance
|
||||
import lmdk_bgt
|
||||
import lmdk_lib
|
||||
import lmdk_sel
|
||||
import exp_mech
|
||||
import math
|
||||
import numpy as np
|
||||
from matplotlib import pyplot as plt
|
||||
import time
|
||||
|
||||
|
||||
def main(args):
|
||||
# User's consumption
|
||||
seq = lmdk_lib.load_data(args, 'cons')
|
||||
# The name of the dataset
|
||||
d = 'HUE'
|
||||
# The landmarks percentages
|
||||
lmdks_pct = [0, 20, 40, 60, 80, 100]
|
||||
# Landmarks' thresholds
|
||||
lmdks_th = [0, .54, .68, .88, 1.12, 10]
|
||||
# The privacy budget
|
||||
epsilon = 1.0
|
||||
eps_pct = [20, 40, 60, 80]
|
||||
|
||||
markers = [
|
||||
'^', # 20
|
||||
'v', # 40
|
||||
'D', # 60
|
||||
's' # 80
|
||||
]
|
||||
|
||||
print('\n##############################', d, '\n')
|
||||
|
||||
# Initialize plot
|
||||
lmdk_lib.plot_init()
|
||||
# The x axis
|
||||
x_i = np.arange(len(lmdks_pct))
|
||||
plt.xticks(x_i, np.array(lmdks_pct, int))
|
||||
plt.xlabel('Landmarks (%)') # Set x axis label.
|
||||
plt.xlim(x_i.min(), x_i.max())
|
||||
# The y axis
|
||||
plt.ylabel('Mean absolute error (kWh)') # Set y axis label.
|
||||
plt.yscale('log')
|
||||
plt.ylim(.1, 100000)
|
||||
|
||||
mae_evt = 0
|
||||
mae_usr = 0
|
||||
|
||||
for i_e, e in enumerate(eps_pct):
|
||||
mae = np.zeros(len(lmdks_pct))
|
||||
|
||||
for i, pct in enumerate(lmdks_pct):
|
||||
# Find landmarks
|
||||
lmdks = seq[seq[:, 1] < lmdks_th[i]]
|
||||
|
||||
for _ in range(args.iter):
|
||||
|
||||
lmdks = lmdk_sel.find_lmdks_eps(seq, lmdks, epsilon*e/100)
|
||||
|
||||
# Uniform
|
||||
rls_data, _ = lmdk_bgt.uniform_cons(seq, lmdks, epsilon*(1 - e/100))
|
||||
mae[i] += lmdk_bgt.mae_cons(seq, rls_data)/args.iter
|
||||
|
||||
# Calculate once
|
||||
if e == eps_pct[0] and pct == lmdks_pct[0]:
|
||||
# Event
|
||||
rls_data_evt, _ = lmdk_bgt.uniform_cons(seq, lmdks, epsilon)
|
||||
mae_evt += lmdk_bgt.mae_cons(seq, rls_data_evt)/args.iter
|
||||
elif e == eps_pct[-1] and pct == lmdks_pct[-1]:
|
||||
# User
|
||||
rls_data_usr, _ = lmdk_bgt.uniform_cons(seq, lmdks, epsilon)
|
||||
mae_usr += lmdk_bgt.mae_cons(seq, rls_data_usr)/args.iter
|
||||
|
||||
# Plot line
|
||||
plt.plot(
|
||||
x_i,
|
||||
mae,
|
||||
label=str(e/100) + 'ε',
|
||||
marker=markers[i_e],
|
||||
markersize=lmdk_lib.marker_size,
|
||||
markeredgewidth=0,
|
||||
linewidth=lmdk_lib.line_width
|
||||
)
|
||||
|
||||
plt.axhline(
|
||||
y = mae_evt,
|
||||
color = '#212121',
|
||||
linewidth=lmdk_lib.line_width
|
||||
)
|
||||
plt.text(x_i[-1] + x_i[-1]*.01, mae_evt - mae_evt*.14, 'event')
|
||||
|
||||
plt.axhline(
|
||||
y = mae_usr,
|
||||
color = '#616161',
|
||||
linewidth=lmdk_lib.line_width
|
||||
)
|
||||
plt.text(x_i[-1] + x_i[-1]*.01, mae_usr - mae_usr*.14, 'user')
|
||||
|
||||
path = str('../../rslt/lmdk_sel_eps/' + d)
|
||||
# Plot legend
|
||||
lmdk_lib.plot_legend()
|
||||
# Show plot
|
||||
# plt.show()
|
||||
# Save plot
|
||||
lmdk_lib.save_plot(path + '-sel-eps.pdf')
|
||||
print('[OK]', flush=True)
|
||||
|
||||
|
||||
def parse_args():
|
||||
'''
|
||||
Parse arguments.
|
||||
|
||||
Optional:
|
||||
res - The results archive file.
|
||||
iter - The total iterations.
|
||||
'''
|
||||
# Create argument parser.
|
||||
parser = argparse.ArgumentParser()
|
||||
|
||||
# Mandatory arguments.
|
||||
|
||||
# Optional arguments.
|
||||
parser.add_argument('-r', '--res', help='The results archive file.', type=str, default='/home/manos/Cloud/Data/HUE/Results.zip')
|
||||
parser.add_argument('-i', '--iter', help='The total iterations.', type=int, default=1)
|
||||
|
||||
# Parse arguments.
|
||||
args = parser.parse_args()
|
||||
|
||||
return args
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
try:
|
||||
start_time = time.time()
|
||||
main(parse_args())
|
||||
end_time = time.time()
|
||||
print('##############################')
|
||||
print('Time elapsed: %s' % (time.strftime('%H:%M:%S', time.gmtime(end_time - start_time))))
|
||||
print('##############################')
|
||||
except KeyboardInterrupt:
|
||||
print('Interrupted by user.')
|
||||
exit()
|
||||
179
code/expt/t-drive-sel-eps.py
Normal file
179
code/expt/t-drive-sel-eps.py
Normal file
@ -0,0 +1,179 @@
|
||||
#!/usr/bin/env python3
|
||||
|
||||
import sys
|
||||
sys.path.insert(1, '../lib')
|
||||
import argparse
|
||||
from datetime import datetime
|
||||
from geopy.distance import distance
|
||||
import lmdk_bgt
|
||||
import lmdk_lib
|
||||
import lmdk_sel
|
||||
import exp_mech
|
||||
import numpy as np
|
||||
from matplotlib import pyplot as plt
|
||||
import time
|
||||
|
||||
|
||||
def main(args):
|
||||
# The data files
|
||||
data_files = {
|
||||
'T-drive': '/home/manos/Cloud/Data/T-drive/Results.zip',
|
||||
}
|
||||
# Data related info
|
||||
data_info = {
|
||||
'T-drive': {
|
||||
'uid': 2,
|
||||
'lmdks': {
|
||||
0: {'dist': 0, 'per': 1000}, # 0.0%
|
||||
20: {'dist': 2095, 'per': 30}, # 19.6%
|
||||
40: {'dist': 2790, 'per': 30}, # 40.2%
|
||||
60: {'dist': 3590, 'per': 30}, # 59.9%
|
||||
80: {'dist': 4825, 'per': 30}, # 79.4%
|
||||
100: {'dist': 10350, 'per': 30} # 100.0%
|
||||
}
|
||||
}
|
||||
}
|
||||
# The data sets
|
||||
data_sets = {}
|
||||
# Load data sets
|
||||
for df in data_files:
|
||||
args.res = data_files[df]
|
||||
data_sets[df] = lmdk_lib.load_data(args, 'usrs_data')
|
||||
# Geo-I configuration
|
||||
# epsilon = level/radius
|
||||
# Radius is in meters
|
||||
bgt_conf = [
|
||||
{'epsilon': 1},
|
||||
]
|
||||
eps_pct = [20, 40, 60, 80]
|
||||
|
||||
markers = [
|
||||
'^', # 20
|
||||
'v', # 40
|
||||
'D', # 60
|
||||
's' # 80
|
||||
]
|
||||
|
||||
# The x axis
|
||||
x_i = np.arange(len(list(data_info.values())[0]['lmdks']))
|
||||
|
||||
for d in data_sets:
|
||||
print('\n##############################', d, '\n')
|
||||
args.res = data_files[d]
|
||||
data = data_sets[d]
|
||||
# Truncate trajectory according to arguments
|
||||
seq = data[data[:,0]==data_info[d]['uid'], :][:args.time]
|
||||
|
||||
# Initialize plot
|
||||
lmdk_lib.plot_init()
|
||||
# The x axis
|
||||
plt.xticks(x_i, np.array([key for key in data_info[d]['lmdks']]).astype(int))
|
||||
plt.xlabel('Landmarks (%)') # Set x axis label.
|
||||
plt.xlim(x_i.min(), x_i.max())
|
||||
# The y axis
|
||||
plt.ylabel('Mean absolute error (m)') # Set y axis label.
|
||||
plt.yscale('log')
|
||||
plt.ylim(1, 1000000)
|
||||
|
||||
mae_evt = 0
|
||||
mae_usr = 0
|
||||
|
||||
for i_e, e in enumerate(eps_pct):
|
||||
mae = np.zeros(len(data_info[d]['lmdks']))
|
||||
for i, lmdk in enumerate(data_info[d]['lmdks']):
|
||||
# Find landmarks
|
||||
args.dist = data_info[d]['lmdks'][lmdk]['dist']
|
||||
args.per = data_info[d]['lmdks'][lmdk]['per']
|
||||
lmdks = lmdk_lib.find_lmdks(seq, args)[:args.time]
|
||||
for bgt in bgt_conf:
|
||||
for _ in range(args.iter):
|
||||
|
||||
lmdks = lmdk_sel.find_lmdks_eps(seq, lmdks, bgt['epsilon']*e/100)
|
||||
|
||||
# Uniform
|
||||
rls_data_u, _ = lmdk_bgt.uniform_r(seq, lmdks, bgt['epsilon']*(1 - e/100))
|
||||
mae[i] += lmdk_bgt.mae(seq, rls_data_u)/args.iter
|
||||
|
||||
# Calculate once
|
||||
if e == eps_pct[0] and lmdk == min(data_info[d]['lmdks']):
|
||||
# Event
|
||||
rls_data_evt, _ = lmdk_bgt.uniform_r(seq, lmdks, bgt['epsilon'])
|
||||
mae_evt += lmdk_bgt.mae(seq, rls_data_evt)/args.iter
|
||||
elif e == eps_pct[-1] and lmdk == max(data_info[d]['lmdks']):
|
||||
# User
|
||||
rls_data_usr, _ = lmdk_bgt.uniform_r(seq, lmdks, bgt['epsilon'])
|
||||
mae_usr += lmdk_bgt.mae(seq, rls_data_usr)/args.iter
|
||||
|
||||
# Plot line
|
||||
plt.plot(
|
||||
x_i,
|
||||
mae,
|
||||
label=str(e/100) + 'ε',
|
||||
marker=markers[i_e],
|
||||
markersize=lmdk_lib.marker_size,
|
||||
markeredgewidth=0,
|
||||
linewidth=lmdk_lib.line_width
|
||||
)
|
||||
|
||||
plt.axhline(
|
||||
y = mae_evt,
|
||||
color = '#212121',
|
||||
linewidth=lmdk_lib.line_width
|
||||
)
|
||||
plt.text(x_i[-1] + x_i[-1]*.01, mae_evt - mae_evt*.05, 'event')
|
||||
|
||||
plt.axhline(
|
||||
y = mae_usr,
|
||||
color = '#616161',
|
||||
linewidth=lmdk_lib.line_width
|
||||
)
|
||||
plt.text(x_i[-1] + x_i[-1]*.01, mae_usr - mae_usr*.05, 'user')
|
||||
|
||||
path = str('../../rslt/lmdk_sel_eps/' + d)
|
||||
# Plot legend
|
||||
lmdk_lib.plot_legend()
|
||||
# # Show plot
|
||||
# plt.show()
|
||||
# Save plot
|
||||
lmdk_lib.save_plot(path + '-sel-eps.pdf')
|
||||
|
||||
|
||||
def parse_args():
|
||||
'''
|
||||
Parse arguments.
|
||||
|
||||
Optional:
|
||||
dist - The coordinates distance threshold in meters.
|
||||
per - The timestaps period threshold in mimutes.
|
||||
time - The total timestamps.
|
||||
iter - The total iterations.
|
||||
'''
|
||||
# Create argument parser.
|
||||
parser = argparse.ArgumentParser()
|
||||
|
||||
# Mandatory arguments.
|
||||
|
||||
# Optional arguments.
|
||||
parser.add_argument('-l', '--dist', help='The coordinates distance threshold in meters.', type=int, default=200)
|
||||
parser.add_argument('-p', '--per', help='The timestaps period threshold in mimutes.', type=int, default=30)
|
||||
parser.add_argument('-r', '--res', help='The results archive file.', type=str, default='/home/manos/Cloud/Data/T-drive/Results.zip')
|
||||
parser.add_argument('-t', '--time', help='The total timestamps.', type=int, default=1000)
|
||||
parser.add_argument('-i', '--iter', help='The total iterations.', type=int, default=1)
|
||||
|
||||
# Parse arguments.
|
||||
args = parser.parse_args()
|
||||
|
||||
return args
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
try:
|
||||
start_time = time.time()
|
||||
main(parse_args())
|
||||
end_time = time.time()
|
||||
print('##############################')
|
||||
print('Time elapsed: %s' % (time.strftime('%H:%M:%S', time.gmtime(end_time - start_time))))
|
||||
print('##############################')
|
||||
except KeyboardInterrupt:
|
||||
print('Interrupted by user.')
|
||||
exit()
|
||||
@ -391,6 +391,60 @@ def find_lmdks(seq, lmdks, epsilon):
|
||||
lmdks_new = seq[lmdks_seq_new - 1]
|
||||
return lmdks_new, epsilon - eps_sel
|
||||
|
||||
|
||||
def find_lmdks_eps(seq, lmdks, epsilon):
|
||||
'''
|
||||
Add dummy landmarks to original landmarks.
|
||||
|
||||
Parameters:
|
||||
seq - All of the data points.
|
||||
lmdks - The original landmarks.
|
||||
epsilon - The available privacy budget.
|
||||
|
||||
Returns:
|
||||
lmdks_new - The new landmarks.
|
||||
'''
|
||||
# The new landmarks
|
||||
lmdks_new = lmdks
|
||||
if len(lmdks) > 0 and len(seq) != len(lmdks):
|
||||
# Get landmarks timestamps in sequence
|
||||
lmdks_seq = find_lmdks_seq(seq, lmdks)
|
||||
# Turn landmarks to histogram
|
||||
hist, h = get_hist(get_seq(1, len(seq)), lmdks_seq)
|
||||
# Find all possible options
|
||||
opts = get_opts_from_top_h(get_seq(1, len(seq)), lmdks_seq)
|
||||
# Get landmarks histogram with dummy landmarks
|
||||
hist_new, _ = exp_mech.exponential(hist, opts, exp_mech.score, 1.0, epsilon)
|
||||
# Split sequence in parts of size h
|
||||
pt_idx = []
|
||||
for idx in range(1, len(seq), h):
|
||||
pt_idx.append([idx, idx + h - 1])
|
||||
pt_idx[-1][1] = len(seq)
|
||||
# Get new landmarks indexes
|
||||
lmdks_seq_new = np.array([], dtype=int)
|
||||
for i, pt in enumerate(pt_idx):
|
||||
# Already landmarks
|
||||
lmdks_seq_pt = lmdks_seq[(lmdks_seq >= pt[0]) & (lmdks_seq <= pt[1])]
|
||||
# Sample randomly from the rest of the sequence
|
||||
size = hist_new[i] - len(lmdks_seq_pt)
|
||||
rglr = np.setdiff1d(np.arange(pt[0], pt[1] + 1), lmdks_seq_pt)
|
||||
# Add already landmarks
|
||||
lmdks_seq_new = np.concatenate([lmdks_seq_new, lmdks_seq_pt])
|
||||
# Add new landmarks
|
||||
if size > 0 and len(rglr) > size:
|
||||
lmdks_seq_new = np.concatenate([lmdks_seq_new,
|
||||
np.random.choice(
|
||||
rglr,
|
||||
size = size,
|
||||
replace = False
|
||||
)
|
||||
])
|
||||
# Get actual landmarks values
|
||||
lmdks_new = seq[lmdks_seq_new - 1]
|
||||
return lmdks_new
|
||||
|
||||
|
||||
|
||||
def test():
|
||||
# Start and end points of the sequence
|
||||
# # Nonrandom
|
||||
|
||||
Reference in New Issue
Block a user