code: WIP

code/expt/copenhagen-sel.py

@@ -0,0 +1,195 @@
+#!/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()

code/expt/hue-sel.py

@@ -0,0 +1,185 @@
+#!/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/HUE/Results.zip'
+  # 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 = 10.0
+
+  # 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')
+
+  # 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 (kWh)')  # Set y axis label.
+  plt.yscale('log')
+  # plt.ylim(.01, 10000)
+  # 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 = seq[seq[:, 1] < lmdks_th[i]]
+
+    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_cons(seq, lmdks, epsilon - eps_sel)
+      # lmdk_bgt.validate_bgts(seq, lmdks, epsilon, bgts_s)
+      mae_s[i] += lmdk_bgt.mae_cons(seq, rls_data_s)/args.iter
+
+      # Uniform
+      rls_data_u, bgts_u = lmdk_bgt.uniform_cons(seq, lmdks, epsilon - eps_sel)
+      mae_u[i] += lmdk_bgt.mae_cons(seq, rls_data_u)/args.iter
+
+      # Adaptive
+      rls_data_a, _, _ = lmdk_bgt.adaptive_cons(seq, lmdks, epsilon - eps_sel, .5, .5)
+      mae_a[i] += lmdk_bgt.mae_cons(seq, rls_data_a)/args.iter
+
+      # Calculate once
+      # Event
+      if i == 0:
+        rls_data_evt, _ = lmdk_bgt.uniform_cons(seq, seq[seq[:, 1] < lmdks_th[0]], epsilon)
+        mae_evt += lmdk_bgt.mae_cons(seq, rls_data_evt)/args.iter
+      # User
+      if i == 0:
+        rls_data_usr, _ = lmdk_bgt.uniform_cons(seq, seq[seq[:, 1] < lmdks_th[len(lmdks_th)-1]], epsilon)
+        mae_usr += lmdk_bgt.mae_cons(seq, rls_data_usr)/args.iter
+
+  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*.14, '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*.14, '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/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()

code/expt/t-drive-sel.py

@@ -0,0 +1,211 @@
+#!/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 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},
+  ]
+
+  # Number of methods
+  n = 3
+  # Width of bars
+  bar_width = 1/(n + 1)
+  # The x axis
+  x_i = np.arange(len(list(data_info.values())[0]['lmdks']))
+  x_margin = bar_width*(n/2 + 1)
+
+  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_margin, x_i.max() + x_margin)
+    # The y axis
+    plt.ylabel('Mean absolute error (m)')  # Set y axis label.
+    plt.yscale('log')
+    # plt.ylim(1, 100000000)
+    # Bar offset
+    x_offset = -(bar_width/2)*(n - 1)
+
+    mae_u = np.zeros(len(data_info[d]['lmdks']))
+    mae_s = np.zeros(len(data_info[d]['lmdks']))
+    mae_a = np.zeros(len(data_info[d]['lmdks']))
+    mae_evt = 0
+    mae_usr = 0
+    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):
+
+          eps_sel = 0
+          if lmdk != 0 and lmdk != 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 = bgt['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, _ = lmdk_bgt.skip(seq, lmdks, bgt['epsilon'] - eps_sel)
+          mae_s[i] += lmdk_bgt.mae(seq, rls_data_s)/args.iter
+
+          # Uniform
+          rls_data_u, _ = lmdk_bgt.uniform_r(seq, lmdks, bgt['epsilon'] - eps_sel)
+          mae_u[i] += lmdk_bgt.mae(seq, rls_data_u)/args.iter
+
+          # Adaptive
+          rls_data_a, _, _ = lmdk_bgt.adaptive(seq, lmdks, bgt['epsilon'] - eps_sel, .5, .5)
+          mae_a[i] += lmdk_bgt.mae(seq, rls_data_a)/args.iter
+
+          # Event
+          if lmdk == 0:
+            rls_data_evt, _ = lmdk_bgt.uniform_r(seq, lmdks, bgt['epsilon'])
+            mae_evt += lmdk_bgt.mae(seq, rls_data_evt)/args.iter
+          # User
+          if lmdk == 100:
+            rls_data_usr, _ = lmdk_bgt.uniform_r(seq, lmdks, bgt['epsilon'])
+            mae_usr += lmdk_bgt.mae(seq, rls_data_usr)/args.iter
+
+    # Plot lines
+    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*.14, '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*.14, 'user')
+
+    # Plot bars
+    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
+    )
+
+    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:
+      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()

code/lib/lmdk_lib.py

@@ -907,6 +907,14 @@ def find_lmdks(usrs_data, args):
   return usrs_lmdks
 
 
+def find_lmdks_seq(seq, lmdks):
+  lmdks_seq = []
+  for i, p in enumerate(seq):
+    if any(np.equal(lmdks, p).all(1)):
+      lmdks_seq.append(i + 1)
+  return np.numpy(lmdks_seq, dtype = int)
+
+
 def find_lmdks_tim(lmdk_data, seq, uid, pct):
   '''
     Find user's landmarks timestamps.