if not len(sys.argv) == 1:
leave_k_out = int(sys.argv[1]);
print 'Use default leave k out: k=' + str(leave_k_out);
if not len(sys.argv) <= 2:
lafactor = int(sys.argv[2]);
print 'Use default latent factor: ' + str(lafactor);
max_rank = 2000;
# number of repetitions.
total_iteration = 2;
# recommendation algorithms %RandUV(latent_factor=lafactor),
method_list = [ LMaFit(latent_factor=lafactor), item_item_sim(N = lafactor), \
HierLat(latent_factor=lafactor), NMF(latent_factor=lafactor),
PMF(latent_factor=lafactor), TriUHV(latent_factor=lafactor) ];
# main method.
result = experiment_leave_k_out_map(exp_name, daily_data_file, \
min_occ_user, min_occ_prog, num_user, num_prog,\
method_list, leave_k_out, total_iteration, max_rank, binary = True);
matlab_output = {};
for method_name, method_iter_perf in result.items():
print 'Method: '+ method_name;
rmse = sum( x['RMSE'] for x in method_iter_perf)/len(method_iter_perf);
print '>>Average RMSE : %.5f' % rmse;
perf_recall = np.zeros(len(method_iter_perf[0]['recall']));
if not len(sys.argv) == 1:
leave_k_out = int(sys.argv[1]);
print 'Use default leave k out: k=' + str(leave_k_out);
if not len(sys.argv) <= 2:
lafactor = int(sys.argv[2]);
print 'Use default latent factor: ' + str(lafactor);
max_rank = 2000;
# number of repetitions.
total_iteration = 2;
# recommendation algorithms RandUV(latent_factor=lafactor),
method_list = [ LMaFit(latent_factor=lafactor), item_item_sim(N = lafactor),\
HierLat(latent_factor=lafactor), NMF(latent_factor=lafactor),
PMF(latent_factor=lafactor), TriUHV(latent_factor=lafactor) ];
# main method.
result = experiment_leave_k_out_map(exp_name, daily_data_file, \
min_occ_user, min_occ_prog, num_user, num_prog,\
method_list, leave_k_out, total_iteration, max_rank, binary = False);
matlab_output = {};
for method_name, method_iter_perf in result.items():
print 'Method: '+ method_name;
rmse = sum( x['RMSE'] for x in method_iter_perf)/len(method_iter_perf);
print '>>Average RMSE : %.5f' % rmse;
perf_recall = np.zeros(len(method_iter_perf[0]['recall']));
raise ValueError('Cannot find data file. ')
exp_name = 'bin_exp_mid_prec_rec'
# something meaningful.
leave_k_out = 10
# perform leave k out.
# number of repetitions.
total_iteration = 3
# recommendation algorithms
method_list = [ LMaFit(latent_factor=lafactor), RandUV(latent_factor=lafactor), \
HierLat(latent_factor=lafactor), NMF(latent_factor=lafactor),
PMF(latent_factor=lafactor), TriUHV(latent_factor=lafactor),
item_item_sim(N = lafactor) ]
#method_list = [ item_item_sim(N = lafactor) ];
#method_list = [ PMF(latent_factor=lafactor), TriUHV(latent_factor=lafactor) ];
# main method.
result = experiment_leave_k_out(exp_name, daily_data_file, min_occ_user, min_occ_prog, \
method_list, leave_k_out, total_iteration, top_n, True)
# display results (average RMSE).
for method_name, method_iter_perf in result.items():
print 'Method: ' + method_name
print '>>Average precision : %.5f' % (sum(x['prec']
for x in method_iter_perf) /
len(method_iter_perf))
print 'processing file', daily_data_file;
if not os.path.isfile(daily_data_file):
raise ValueError('Cannot find data file. ');
exp_name = 'bin_exp_mid_prec_rec'; # something meaningful.
leave_k_out = 10; # perform leave k out.
# number of repetitions.
total_iteration = 3;
# recommendation algorithms
method_list = [ LMaFit(latent_factor=lafactor), RandUV(latent_factor=lafactor), \
HierLat(latent_factor=lafactor), NMF(latent_factor=lafactor),
PMF(latent_factor=lafactor), TriUHV(latent_factor=lafactor),
item_item_sim(N = lafactor) ];
#method_list = [ item_item_sim(N = lafactor) ];
#method_list = [ PMF(latent_factor=lafactor), TriUHV(latent_factor=lafactor) ];
# main method.
result = experiment_leave_k_out(exp_name, daily_data_file, min_occ_user, min_occ_prog, \
method_list, leave_k_out, total_iteration, top_n, True);
# display results (average RMSE).
for method_name, method_iter_perf in result.items():
print 'Method: '+ method_name;
print '>>Average precision : %.5f' % (sum( x['prec'] for x in method_iter_perf)/len(method_iter_perf));
print '>>Average recall : %.5f' % (sum( x['recall'] for x in method_iter_perf)/len(method_iter_perf));
print '>>Average rmse : %.5f' % (sum( x['rmse'] for x in method_iter_perf)/len(method_iter_perf));
exp_name = 'test_exp_mid_prec_rec'; # something meaningful.
# filtering criteria
min_occ_user = 2; # should be more than leave_k_out.
min_occ_prog = 2;
top_n = 50; # performance computed on top N;
leave_k_out = 1; # perform leave k out.
# number of repetitions.
total_iteration = 3;
# recommendation algorithms
method_list = [ LMaFit(latent_factor=lafactor), RandUV(latent_factor=lafactor), \
NMF(latent_factor=lafactor), PMF(latent_factor=lafactor), item_item_sim(N = lafactor) ];
# main method.
result = experiment_leave_k_out(exp_name, daily_data_file, min_occ_user, min_occ_prog, \
method_list, leave_k_out, total_iteration, top_n);
# display results (average RMSE).
for method_name, method_iter_perf in result.items():
print 'Method: '+ method_name;
print '>>Average precision : %.5f' % (sum( x['prec'] for x in method_iter_perf)/len(method_iter_perf));
print '>>Average recall : %.5f' % (sum( x['recall'] for x in method_iter_perf)/len(method_iter_perf));
print '>>Average rmse : %.5f' % (sum( x['rmse'] for x in method_iter_perf)/len(method_iter_perf));
#print method_iter_perf;
#print result;
''' This is a testing pipeline for KDD_2014 algorithm. Created on Feb 17, 2014 @author: Shiyu C. ([email protected]) ''' from rs.data.daily_watchtime import DailyWatchTimeReader from rs.algorithms.recommendation.item_item_sim import item_item_sim if __name__ == '__main__': filename = "../../../datasample/agg_duid_pid_watchtime_genre/20131209_100000"; # load data. reader = DailyWatchTimeReader(); feedback_data = reader.read_file_with_minval(filename, 1, 1); feedback_data.normalize_row(); N = 3; item_item_sim_model = item_item_sim(N); item_item_sim_model.train(feedback_data); # test. loc_row = [200, 4, 105]; loc_col = [ 10, 22, 4]; print 'Prediction:' print item_item_sim_model.predict(loc_row, loc_col);
''' This is a testing pipeline for KDD_2014 algorithm. Created on Feb 17, 2014 @author: Shiyu C. ([email protected]) ''' from rs.data.daily_watchtime import DailyWatchTimeReader from rs.algorithms.recommendation.item_item_sim import item_item_sim if __name__ == '__main__': filename = "../../../datasample/agg_duid_pid_watchtime_genre/20131209_100000" # load data. reader = DailyWatchTimeReader() feedback_data = reader.read_file_with_minval(filename, 1, 1) feedback_data.normalize_row() N = 3 item_item_sim_model = item_item_sim(N) item_item_sim_model.train(feedback_data) # test. loc_row = [200, 4, 105] loc_col = [10, 22, 4] print 'Prediction:' print item_item_sim_model.predict(loc_row, loc_col)
