code: Experimenting with copenhagen data

code/expt/bgt_cmp_copenhagen.py

@@ -0,0 +1,187 @@
+#!/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):
+  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_expt')
+  # The name of the dataset
+  d = 'Copenhagen'
+  # The user's id
+  uid = '623'
+  # The landmarks percentages
+  lmdks_pct = [0, 20, 40, 60, 80, 100]
+  # The privacy budget
+  epsilon = 1.0
+
+  # Number of methods
+  n = 6
+  # 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)]
+
+  # Initialize plot
+  lmdk_lib.plot_init()
+  # The x axis
+  plt.xticks(x_i, np.array(lmdks_pct, int))
+  plt.xlabel('Landmarks percentage')  # 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(lmdks_pct))
+  mae_s = np.zeros(len(lmdks_pct))
+  mae_a = np.zeros(len(lmdks_pct))
+  mae_r = np.zeros(len(lmdks_pct))
+  mae_d = np.zeros(len(lmdks_pct))
+  mae_i = 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)
+
+    print(pct, np.shape(lmdks)[0]/np.shape(seq)[0])
+
+    # for _ in range(args.iter):
+    #   # Skip
+    #   rls_data_s, _ = lmdk_bgt.skip(seq, lmdks, epsilon)
+    #   mae_s[i] += lmdk_bgt.mae(seq, rls_data_s)/args.iter
+
+    #   # Uniform
+    #   rls_data_u, _ = lmdk_bgt.uniform_r(seq, lmdks, epsilon)
+    #   mae_u[i] += lmdk_bgt.mae(seq, rls_data_u)/args.iter
+
+    #   # Adaptive
+    #   rls_data_a, _, _ = lmdk_bgt.adaptive(seq, lmdks, epsilon, .5, .5)
+    #   mae_a[i] += lmdk_bgt.mae(seq, rls_data_a)/args.iter
+
+    #   # Sample
+    #   rls_data_r, _, _ = lmdk_bgt.sample(seq, lmdks, epsilon)
+    #   mae_r[i] += lmdk_bgt.mae(seq, rls_data_r)/args.iter
+
+    #   # Discount
+    #   rls_data_d, _, _ = lmdk_bgt.discount(seq, lmdks, epsilon)
+    #   mae_d[i] += lmdk_bgt.mae(seq, rls_data_d)/args.iter
+
+    #   # Incremental
+    #   rls_data_i, _, _ = lmdk_bgt.incremental(seq, lmdks, epsilon, .5)
+    #   mae_i[i] += lmdk_bgt.mae(seq, rls_data_i)/args.iter
+
+  # plt.bar(
+  #   x_i + x_offset,
+  #   mae_s,
+  #   bar_width,
+  #   label='Skip',
+  #   linewidth=lmdk_lib.line_width
+  # )
+  # x_offset += bar_width
+  # # Plot bars
+  # 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
+  # plt.bar(
+  #   x_i + x_offset,
+  #   mae_r,
+  #   bar_width,
+  #   label='Sample',
+  #   linewidth=lmdk_lib.line_width
+  # )
+  # x_offset += bar_width
+  # plt.bar(
+  #   x_i + x_offset,
+  #   mae_d,
+  #   bar_width,
+  #   label='Discount',
+  #   linewidth=lmdk_lib.line_width
+  # )
+  # x_offset += bar_width
+  # plt.bar(
+  #   x_i + x_offset,
+  #   mae_i,
+  #   bar_width,
+  #   label='Incremental',
+  #   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 + '.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   : %.4fs' % (end_time - start_time))
+    print('##############################')
+  except KeyboardInterrupt:
+    print('Interrupted by user.')
+    exit()