the-last-thing/code/expt/copenhagen-sel.py

#!/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 math
import numpy as np
from matplotlib import pyplot as plt
import time


def main(args):
  res_file = '/home/manos/Cloud/Data/Copenhagen/Results.zip'
  # 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

  # Number of methods
  n = 3
  # Width of bars
  bar_width = 1/(n + 1)
  # The x axis
  x_i = np.arange(len(lmdks_pct))
  x_margin = bar_width*(n/2 + 1)

  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
  plt.xticks(x_i, np.array(lmdks_pct, 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.yscale('log')
  plt.ylim(0, 100)
  # Bar offset
  x_offset = -(bar_width/2)*(n - 1)

  mae_u = np.zeros(len(lmdks_pct))
  mae_s = np.zeros(len(lmdks_pct))
  mae_a = np.zeros(len(lmdks_pct))
  mae_evt = 0
  mae_usr = 0

  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):

      eps_sel = 0
      if pct != 0 and pct != 100:
        # Get landmarks timestamps in sequence
        lmdks_seq = lmdk_lib.find_lmdks_seq(seq, lmdks)
        # Turn landmarks to histogram
        hist, h = lmdk_lib.get_hist(lmdk_lib.get_seq(1, len(seq)), lmdks_seq)
        # Find all possible options
        opts = lmdk_sel.get_opts_from_top_h(lmdk_lib.get_seq(1, len(seq)), lmdks_seq)
        # Landmarks selection budget
        eps_sel = epsilon/(len(lmdks_seq) + 1)
        # Get private landmarks timestamps
        lmdks_seq, _ = exp_mech.exponential_pareto(hist, opts, exp_mech.score, 1.0, eps_sel)
        # Get actual landmarks values
        lmdks = seq[lmdks_seq] 

      # Skip
      rls_data_s, bgts_s = lmdk_bgt.skip_cont(seq, lmdks, epsilon - eps_sel)
      # lmdk_bgt.validate_bgts(seq, lmdks, epsilon, bgts_s)
      mae_s[i] += lmdk_bgt.mae_cont(rls_data_s)/args.iter

      # Uniform
      rls_data_u, bgts_u = lmdk_bgt.uniform_cont(seq, lmdks, epsilon - eps_sel)
      # lmdk_bgt.validate_bgts(seq, lmdks, epsilon, bgts_u)
      mae_u[i] += lmdk_bgt.mae_cont(rls_data_u)/args.iter

      # Adaptive
      rls_data_a, _, _ = lmdk_bgt.adaptive_cont(seq, lmdks, epsilon - eps_sel, .5, .5)
      mae_a[i] += lmdk_bgt.mae_cont(rls_data_a)/args.iter

      # Calculate once
      if i == 0:
        # Event
        rls_data_evt, _ = lmdk_bgt.uniform_cont(seq, lmdk_lib.find_lmdks_cont(lmdk_data, seq, uid, 0), epsilon)
        mae_evt += lmdk_bgt.mae_cont(rls_data_evt)/args.iter
        # User
        rls_data_usr, _ = lmdk_bgt.uniform_cont(seq, lmdk_lib.find_lmdks_cont(lmdk_data, seq, uid, 100), epsilon)
        mae_usr += lmdk_bgt.mae_cont(rls_data_usr)/args.iter

  mae_u *= 100
  mae_s *= 100
  mae_a *= 100
  mae_evt *= 100
  mae_usr *= 100

  plt.axhline(
    y = mae_evt,
    color = '#212121',
    linewidth=lmdk_lib.line_width
  )
  plt.text(x_i[-1] + x_i[-1]*.14, 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]*.14, mae_usr - mae_usr*.05, 'user')

  plt.bar(
    x_i + x_offset,
    mae_s,
    bar_width,
    label='Skip',
    linewidth=lmdk_lib.line_width
  )
  x_offset += bar_width
  plt.bar(
    x_i + x_offset,
    mae_u,
    bar_width,
    label='Uniform',
    linewidth=lmdk_lib.line_width
  )
  x_offset += bar_width
  plt.bar(
    x_i + x_offset,
    mae_a,
    bar_width,
    label='Adaptive',
    linewidth=lmdk_lib.line_width
  )
  x_offset += bar_width

  path = str('../../rslt/bgt_cmp/' + d)
  # Plot legend
  lmdk_lib.plot_legend()
  # # Show plot
  # plt.show()
  # Save plot
  lmdk_lib.save_plot(path + '-sel.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()