the-last-thing/code/expt/expt_lmdk_sel.py

125 lines
3.7 KiB
Python

#!/usr/bin/env python3
import sys
sys.path.insert(1, '../lib')
import argparse
import lmdk_lib
import lmdk_sel
import exp_mech
import numpy as np
import os
from matplotlib import pyplot as plt
import time
def main(args):
# Privacy goal
epsilon = [.01, .1, 1.0, 10.0, 100.0]
# Number of timestamps
seq = lmdk_lib.get_seq(1, args.time)
# Distribution type
dist_type = np.array(range(-1, 4))
# Number of landmarks
lmdk_n = np.array(range(int(.2*args.time), args.time, int(args.time/5)))
# Width of bars
bar_width = 1/(len(epsilon) + 1)
# The x axis
x_i = np.arange(len(lmdk_n))
x_margin = bar_width*(len(epsilon)/2 + 1)
for d_i, d in enumerate(dist_type):
# Logging
title = lmdk_lib.dist_type_to_str(d) + ' landmark distribution'
print('(%d/%d) %s... ' %(d_i + 1, len(dist_type), title), end='', flush=True)
# Initialize plot
lmdk_lib.plot_init()
# The x axis
plt.xticks(x_i, ((lmdk_n/len(seq))*100).astype(int))
plt.xlabel('Landmarks (%)') # Set x axis label.
plt.xlim(x_i.min() - x_margin, x_i.max() + x_margin)
# The y axis
plt.ylabel('Mean absolute error') # Set y axis label.
# plt.ylim(0, len(seq)/3)
# Bar offset
x_offset = -(bar_width/2)*(len(epsilon) - 1)
for e_i, e in enumerate(epsilon):
mae = np.zeros(len(lmdk_n))
for n_i, n in enumerate(lmdk_n):
for r in range(args.reps):
lmdks = lmdk_lib.get_lmdks(seq, n, d)
hist, h = lmdk_lib.get_hist(seq, lmdks)
res = np.zeros([len(hist)])
# Split sequence in parts of size h
pt_idx = []
for idx in range(h, len(seq), h):
pt_idx.append(idx)
seq_pt = np.split(seq, pt_idx)
for pt_i, pt in enumerate(seq_pt):
# Find this part's landmarks
lmdks_pt = np.intersect1d(pt, lmdks)
# Find possible options for this part
opts = lmdk_sel.get_opts_from_top_h(pt, lmdks_pt)
# Turn part to histogram
hist_pt, _ = lmdk_lib.get_hist(pt, lmdks_pt)
# Get an option for this part
res_pt = opts[0]
if len(opts) > 1:
res_pt, _ = exp_mech.exponential(hist_pt, opts, exp_mech.score, 1.0, e)
# Merge options of all parts
res[pt_i] = np.sum(res_pt)
# Calculate MAE
mae[n_i] += lmdk_lib.get_norm(hist, res)/args.reps
# Plot bar for current epsilon
plt.bar(
x_i + x_offset,
mae,
bar_width,
label=u'\u03B5 = ' + str("{:.0e}".format(e)),
linewidth=lmdk_lib.line_width
)
# Change offset for next bar
x_offset += bar_width
path = str('../../rslt/lmdk_sel/' + title)
# Plot legend
lmdk_lib.plot_legend()
# Show plot
# plt.show()
# Save plot
lmdk_lib.save_plot(path + '.pdf')
print('[OK]', flush=True)
'''
Parse arguments.
Optional:
reps - The number of repetitions.
time - The time limit of the sequence.
'''
def parse_args():
# Create argument parser.
parser = argparse.ArgumentParser()
# Mandatory arguments.
# Optional arguments.
parser.add_argument('-r', '--reps', help='The number of repetitions.', type=int, default=1)
parser.add_argument('-t', '--time', help='The time limit of the sequence.', type=int, default=100)
# 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()