def given_alpha(alpha, dataset, recom_list, risk):
n_users, n_items, n_rates, indexes, cmpl_rates = dataset
risk_name, risk = risk
outfile = path.join(alpha_dir, '%s_%.1f.p' % (risk_name, alpha))
# if path.isfile(outfile):
# print('%s exists' % (path.basename(outfile)))
# return
cmpl_cnt = config.count_index(indexes)
cmpl_dist = cmpl_cnt / cmpl_cnt.sum()
k = config.solve_k(alpha, n_users, n_items, n_rates, cmpl_cnt)
cmpl_props = config.complete_prop(alpha, k, indexes)
n_rmse, p_rmse, s_rmse, d_rmse = 0.0, 0.0, 0.0, 0.0
for recom in recom_list:
recom_name, pred_rates = recom
t_risk = config.compute_t(pred_rates, cmpl_rates, risk)
dataset = n_users, n_items, n_rates, cmpl_rates, cmpl_cnt, t_risk
while True:
res = config.eval_wo_error(recom, dataset, cmpl_props,
(risk_name, risk))
n_mse, p_mse, s_mse, d_mse, rerun = res
if not rerun:
break
else:
print('rerun %s %s' % (risk_name, recom_name))
n_rmse += n_mse
p_rmse += p_mse
s_rmse += s_mse
d_rmse += d_mse
n_recoms = len(recom_list)
n_rmse = math.sqrt(n_rmse / n_recoms)
p_rmse = math.sqrt(p_rmse / n_recoms)
s_rmse = math.sqrt(s_rmse / n_recoms)
d_rmse = math.sqrt(d_rmse / n_recoms)
print('%s alpha=%.1f k=%.4f' % (risk_name, alpha, k))
print(' n=%.4f p=%.4f s=%.4f d=%.4f' % (n_rmse, p_rmse, s_rmse, d_rmse))
print('\n' + '#' * n_hashtag + '\n')
return
config.make_file_dir(outfile)
data = {
'a': alpha,
'k': k,
'n': n_rmse,
'p': p_rmse,
's': s_rmse,
'd': d_rmse,
}
pickle.dump(data, open(outfile, 'wb'))
def vary_gamma(alpha, gammas, dataset, recom_list, risk):
n_users, n_items, n_rates, indexes, cmpl_rates = dataset
risk_name, risk = risk
cmpl_cnt = config.count_index(indexes)
cmpl_dist = cmpl_cnt / cmpl_cnt.sum()
k = config.solve_k(alpha, n_users, n_items, n_rates, cmpl_cnt)
cmpl_props = config.complete_prop(alpha, k, indexes)
outfile = path.join(gamma_dir, '%s_%.1f.p' % (risk_name, alpha))
# if path.isfile(outfile):
# print('%s exists' % (path.basename(outfile)))
# return
n_rmse, p_rmse, s_rmse = 0.0, 0.0, 0.0
d_rmses = np.zeros(len(gammas))
for recom in recom_list:
recom_name, pred_rates = recom
t_risk = config.compute_t(pred_rates, cmpl_rates, risk)
dataset = n_users, n_items, n_rates, cmpl_rates, cmpl_cnt, t_risk
res = config.eval_wt_gamma(recom, dataset, cmpl_props,
(risk_name, risk), gammas)
n_mse, p_mse, s_mse, d_mses = res
n_rmse += n_mse
p_rmse += p_mse
s_rmse += s_mse
d_rmses += d_mses
n_recoms = len(recom_list)
n_rmse = math.sqrt(n_rmse / n_recoms)
p_rmse = math.sqrt(p_rmse / n_recoms)
s_rmse = math.sqrt(s_rmse / n_recoms)
d_rmses = np.sqrt(d_rmses / n_recoms)
print('%s alpha=%.1f k=%.4f' % (risk_name, alpha, k))
print(' n=%.4f p=%.4f s=%.4f' % (n_rmse, p_rmse, s_rmse))
for gamma, d_rmse in zip(gammas, d_rmses):
print(' gamma=%.1f d=%.4f' % (gamma, d_rmse))
print('\n' + '#' * n_hashtag + '\n')
config.make_file_dir(outfile)
data = {
'a': alpha,
'k': k,
'n': n_rmse,
'p': p_rmse,
's': s_rmse,
'd': d_rmses,
}
pickle.dump(data, open(outfile, 'wb'))
def vary_error(n_mcar, dataset, recom_list, risk):
n_users, n_items, n_rates, indexes, cmpl_rates= dataset
risk_name, risk = risk
cmpl_cnt = config.count_index(indexes)
cmpl_dist = cmpl_cnt / cmpl_cnt.sum()
k = config.solve_k(alpha, n_users, n_items, n_rates, cmpl_cnt)
cmpl_props = config.complete_prop(alpha, k, indexes)
# [stdout.write('%.4f ' % p) for p in set(cmpl_props)]
# stdout.write('\n')
outfile = path.join(error_dir, '%s_%03d.p' % (risk_name, n_mcar))
p_o = n_rates / (n_users * n_items)
# print('p_o: %.4f' % p_o)
p_r = np.copy(cmpl_dist)
stdout.write('p_r:')
[stdout.write(' %.4f' % p) for p in p_r]
stdout.write('\n')
p_o_r = config.compute_prop(alpha, k)
stdout.write('p_o_r:')
[stdout.write(' %.4f' % p) for p in p_o_r]
stdout.write('\n')
p_r_o = p_o_r * p_r / p_o
# stdout.write('p_r_o:')
# [stdout.write(' %.4f' % p) for p in p_r_o]
# stdout.write('\n')
np.random.seed(0)
while True:
mcar_rates = np.random.choice(max_rate-min_rate+1, n_mcar, p=list(p_r))
p_r = np.zeros(max_rate-min_rate+1)
for rid in mcar_rates:
p_r[rid] += 1
p_r /= p_r.sum()
success = True
if p_r.min() == 0.0:
success = False
if p_r[0] <= p_r[1]:
# if p_r[0] < p_r[1]:
success = False
if p_r[1] <= p_r[2]:
# if p_r[1] < p_r[2]:
success = False
if p_r[2] <= p_r[3]:
# if p_r[2] < p_r[3]:
success = False
if p_r[3] <= p_r[4]:
# if p_r[3] < p_r[4]:
success = False
if success:
break
stdout.write('p_r:')
[stdout.write(' %.4f' % p) for p in p_r]
stdout.write('\n')
p_o_r = p_r_o * p_o / p_r
# p_o_r = np.asarray([0.0163, 0.0697, 0.1140, 0.0268, 0.0113])
stdout.write('p_o_r:')
[stdout.write(' %.4f' % p) for p in p_o_r]
stdout.write('\n')
rate_props = config.complete_prop(alpha, k, indexes, rate_props=p_o_r)
# [stdout.write('%.4f ' % p) for p in set(rate_props)]
# stdout.write('\n')
e_rmses, d_rmses, omegas = [], [], []
for omega in v_omegas:
e_rmse = 0.0
d_rmse = 0.0
for recom in recom_list:
recom_name, pred_rates = recom
t_risk = config.compute_t(pred_rates, cmpl_rates, risk)
dataset = n_users, n_items, n_rates, cmpl_rates, cmpl_cnt, t_risk
res = config.eval_wt_mcar(recom, dataset, cmpl_props, rate_props, (risk_name, risk), omega)
e_mse, d_mse = res
e_rmse += e_mse
d_rmse += d_mse
n_recoms = len(recom_list)
e_rmse = math.sqrt(e_rmse / n_recoms)
d_rmse = math.sqrt(d_rmse / n_recoms)
print('%s alpha=%.1f k=%.4f' % (risk_name, alpha, k))
print(' o=%.2f e=%.4f d=%.4f' % (omega, e_rmse, d_rmse))
print('\n' + '#'*n_hashtag + '\n')
e_rmses.append(e_rmse)
d_rmses.append(d_rmse)
omegas.append(omega)
# break
if path.isfile(outfile):
print('%s exists' % path.basename(outfile))
return
data = {
'e': e_rmses,
'd': d_rmses,
'o': omegas,
}
config.make_file_dir(outfile)
pickle.dump(data, open(outfile, 'wb'))
p_o_r = p_r_o * p_o / p_r
stdout.write('p_o_r:')
[stdout.write(' %.4f' % p) for p in p_o_r]
stdout.write('\n')
rate_props = config.complete_prop(alpha, k, indexes, rate_props=p_o_r)
[stdout.write('%.4f ' % p) for p in set(rate_props)]
stdout.write('\n')
e_rmses, d_rmses, omegas = [], [], []
for omega in np.arange(0.0, 1.05, 0.1):
e_rmse = 0.0
d_rmse = 0.0
for recom in recom_list:
recom_name, pred_rates = recom
t_risk = config.compute_t(pred_rates, cmpl_rates, risk)
dataset = n_users, n_items, n_rates, cmpl_rates, cmpl_cnt, t_risk
res = config.eval_wt_mcar(recom, dataset, cmpl_props, rate_props,
(risk_name, risk), omega)
e_mse, d_mse = res
e_rmse += e_mse
d_rmse += d_mse
n_recoms = len(recom_list)
e_rmse = math.sqrt(e_rmse / n_recoms)
d_rmse = math.sqrt(d_rmse / n_recoms)
print('%s alpha=%.1f k=%.4f' % (risk_name, alpha, k))
print(' e=%.4f d=%.4f' % (e_rmse, d_rmse))
print('\n' + '#' * n_hashtag + '\n')
e_rmses.append(e_rmse)
def given_beta(alpha, beta, dataset, recom_list, risk):
n_users, n_items, n_rates, indexes, cmpl_rates= dataset
risk_name, risk = risk
outfile = path.join(beta_dir, '%s_%.1f.p' % (risk_name, beta))
# if path.isfile(outfile):
# print('%s exists' % (path.basename(outfile)))
# return
cmpl_cnt = config.count_index(indexes)
cmpl_dist = cmpl_cnt / cmpl_cnt.sum()
k = config.solve_k(alpha, n_users, n_items, n_rates, cmpl_cnt)
cmpl_props = config.complete_prop(alpha, k, indexes)
n_rmse, p_rmse, s_rmse, d_rmse = 0.0, 0.0, 0.0, 0.0
for recom in recom_list:
recom_name, pred_rates = recom
t_risk = config.compute_t(pred_rates, cmpl_rates, risk)
dataset = n_users, n_items, n_rates, cmpl_rates, cmpl_cnt, t_risk
res = config.eval_wo_error(recom, dataset, cmpl_props, (risk_name, risk), beta=beta)
n_mse, p_mse, s_mse, d_mse, rerun = res
print('%s %s p=%.8f s=%.8f d=%.8f' % (risk_name, recom_name, p_mse, s_mse, d_mse))
'''
max_try = 1
n_mses, p_mses, s_mses, d_mses = [], [], [], []
for i in range(max_try):
res = config.eval_wo_error(recom, dataset, cmpl_props, (risk_name, risk), beta=beta)
n_mse, p_mse, s_mse, d_mse, rerun = res
n_mses.append(n_mse)
p_mses.append(p_mse)
s_mses.append(s_mse)
d_mses.append(d_mse)
d_minus_s, min_idx = d_mses[0] - s_mses[0], 0
for i in range(1, max_try):
if d_mses[i] - s_mses[i] < d_minus_s:
d_minus_s, min_idx = d_mses[i] - s_mses[i], i
i = min_idx
n_mse, p_mse, s_mse, d_mse = n_mses[i], p_mses[i], s_mses[i], d_mses[i]
print('select %s %s p=%.8f s=%.8f d=%.8f' % (risk_name, recom_name, p_mse, s_mse, d_mse))
'''
n_rmse += n_mse
p_rmse += p_mse
s_rmse += s_mse
d_rmse += d_mse
n_recoms = len(recom_list)
n_rmse = math.sqrt(n_rmse / n_recoms)
p_rmse = math.sqrt(p_rmse / n_recoms)
s_rmse = math.sqrt(s_rmse / n_recoms)
d_rmse = math.sqrt(d_rmse / n_recoms)
print('%s alpha=%.1f k=%.4f beta=%.1f' % (risk_name, alpha, k, beta))
print(' n=%.4f p=%.4f s=%.4f d=%.4f' % (n_rmse, p_rmse, s_rmse, d_rmse))
print('\n' + '#'*n_hashtag + '\n')
return
config.make_file_dir(outfile)
data = {
'a': alpha,
'k': k,
'b': beta,
'n': n_rmse,
'p': p_rmse,
's': s_rmse,
'd': d_rmse,
}
pickle.dump(data, open(outfile, 'wb'))