reader = DailyWatchTimeReader()
feedback_data = reader.read_file_with_minval(filename, 1, 1)
# build model with 3 latent factors.
r = 10
# the L_2 norm regularizer
lamb = 0.1
# the stopping delta value
delta = 1e-5
# the maximium iteration number
maxiter = 300
# PMF_model = PMF(r,lamb,delta,maxiter, verbose = True);
# print PMF_model.unique_str();
#
# PMF_model.train(feedback_data);
#
# # test.
# loc_row = [200, 4, 105];
# loc_col = [ 10, 22, 4];
# print 'Prediction:'
# print PMF_model.predict(loc_row, loc_col);
# test cold start.
row = [0, 0, 1, 1, 2, 3, 3]
col = [0, 3, 1, 4, 0, 1, 3]
data = [1, 1, 1, 1, 1, 1, 1]
fbdata = FeedbackData(row, col, data, 4, 5, {}, {}, {})
LMaFit_model = PMF(r, lamb, delta, maxiter, verbose=True)
LMaFit_model.train(fbdata)
else:
min_occ_user = 35
min_occ_prog = 300
leave_k_out = 10
# perform leave k out.
top_n = 10
# performance computed on top N;
# 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) ]
#method_list = [ NMF(latent_factor=lafactor),\
# 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']
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;
exp_name = 'loc_rec_exp'; # something meaningful.
# filtering criteria
min_occ_user = 4;
min_occ_prog = 1;
# specify the percentage of training and (1 - training_prec) is testing.
training_prec = 0.5;
# number of repetitions.
total_iteration = 3;
lafactor = 5;
# recommendation algorithms
method_list = [ LMaFit(latent_factor=lafactor), item_item_sim(N = lafactor), \
NMF(latent_factor=lafactor), \
PMF(latent_factor=lafactor), \
RandUV(latent_factor=lafactor) \
];
# main method.
result = experiment_rand_split(exp_name, daily_data_file, min_occ_user, min_occ_prog, \
method_list, training_prec, total_iteration);
# display results (average RMSE).
for method_name, method_iter_perf in result.items():
print 'Method: '+ method_name;
print '>>Average performance RMSE: %.5f' % (sum( x for x in method_iter_perf)/len(method_iter_perf));
#print result;
reader = DailyWatchTimeReader();
feedback_data = reader.read_file_with_minval(filename, 1, 1);
# build model with 3 latent factors.
r = 10;
# the L_2 norm regularizer
lamb = 0.1;
# the stopping delta value
delta = 1e-5;
# the maximium iteration number
maxiter = 300;
# PMF_model = PMF(r,lamb,delta,maxiter, verbose = True);
# print PMF_model.unique_str();
#
# PMF_model.train(feedback_data);
#
# # test.
# loc_row = [200, 4, 105];
# loc_col = [ 10, 22, 4];
# print 'Prediction:'
# print PMF_model.predict(loc_row, loc_col);
# test cold start.
row = [0, 0, 1, 1, 2, 3, 3];
col = [0, 3, 1, 4, 0, 1, 3];
data = [1, 1, 1, 1, 1, 1, 1];
fbdata = FeedbackData(row, col, data, 4, 5, {}, {}, {});
LMaFit_model = PMF(r,lamb,delta,maxiter, verbose = True);
LMaFit_model.train(fbdata);