lda_rels = []
for balance in range(10, 201, 10):
print(balance)
n_dw_matrix = _n_dw_matrix[topic_0_indices +
topic_1_indices * balance, :]
regularization_list = [regularizers.Additive(-0.1, 0.)] * 100
lda_phi, lda_theta = experiments.default_sample(
n_dw_matrix,
T=2,
seed=42,
optimizer=default.Optimizer(regularization_list, verbose=False))
thetaless_phi, thetaless_theta = experiments.default_sample(
n_dw_matrix,
T=2,
seed=42,
optimizer=thetaless.Optimizer(regularization_list, verbose=False))
# print(np.argmax(thetaless_theta[:len(topic_0_indices), :2], axis=1).mean())
# print(np.argmax(thetaless_theta[len(topic_0_indices):, :2], axis=1).mean())
# print('!')
# for topic_set in metrics.get_top_words(thetaless_phi, 10):
# print('\n\t'.join(map(num_2_token.get, topic_set)))
# print()
# for topic_set in metrics.get_top_words(thetaless_phi, 5):
# print('\n\t'.join(map(num_2_token.get, topic_set)))
# print()
print('lda')
# #print(np.sum(lda_theta[:, 1]) / np.sum(lda_theta[:, 0]))
# print(np.argmax(lda_theta, axis=1).mean())
print(metrics.calc_avg_top_words_jaccards(lda_phi, 20))
print('thetaless')
# #print(np.sum(thetaless_theta[:, 1]) / np.sum(thetaless_theta[:, 0]))
'rec.sport.hockey', 'sci.crypt', 'sci.electronics', 'sci.med',
'sci.space'
],
train_proportion=0.8)[:2]
args_list = list()
for T in [10, 25]:
for theta_alpha in [0.1, 0.01, 0.1]:
regularization_list = [regularizers.Additive(0, theta_alpha)
] * ITERS_COUNT
args_list.append(
(train_n_dw_matrix, test_n_dw_matrix,
default.Optimizer(regularization_list), T, SAMPLES,
'20news_experiment/20news_{}t_default_{}_{}.pkl'.format(
T, 0., theta_alpha)))
args_list.append(
(train_n_dw_matrix, test_n_dw_matrix,
thetaless.Optimizer(regularization_list), T, SAMPLES,
'20news_experiment/20news_{}t_thetaless_{}_{}.pkl'.format(
T, 0., theta_alpha)))
args_list.append(
(train_n_dw_matrix, test_n_dw_matrix,
transfer_thetaless.Optimizer(regularization_list), T, SAMPLES,
'20news_experiment/20news_{}t_transfer_thetaless_{}_{}.pkl'.
format(T, 0., theta_alpha)))
#manager.perform_experiment(args_list[0])
#manager.perform_experiment(args_list[1])
manager.perform_experiment(args_list[2])
#Pool(processes=5).map(manager.perform_experiment, args_list)
def perform_doc_experiment(
(n_dw_matrix_doc_train, doc_targets_doc_train, n_dw_matrix_doc_test,
doc_targets_doc_test, optimizer, T, samples, output_path)):
D, _ = n_dw_matrix_doc_test.shape
svm_train_score = metrics.create_svm_score_function(doc_targets_doc_train,
verbose=False)
opt_plsa_not_const_phi = default.Optimizer(
regularization_list=optimizer.regularization_list[:10],
const_phi=False)
opt_plsa_const_phi = default.Optimizer(
regularization_list=optimizer.regularization_list[:10], const_phi=True)
opt_artm_thetaless = thetaless.Optimizer(
regularization_list=optimizer.regularization_list[:10])
res_plsa_not_const_phi = []
res_plsa_const_phi = []
res_artm_thetaless = []
cv_fold_scores = []
cv_test_scores = []
for seed in range(samples):
print(seed)
phi, theta = experiments.default_sample(n_dw_matrix_doc_train, T, seed,
optimizer)
(best_C, best_gamma, cv_fold_score,
cv_test_score) = svm_train_score(theta)
cv_fold_scores.append(cv_fold_score)
cv_test_scores.append(cv_test_score)
print('Fold score: {}\tTest score: {}'.format(cv_fold_score,
cv_test_score))
algo = SVC(C=best_C, gamma=best_gamma).fit(theta,
doc_targets_doc_train)
init_theta = common.get_prob_matrix_by_counters(
np.ones(shape=(D, T), dtype=np.float64))
plsa_not_const_phi = []
plsa_const_phi = []
artm_thetaless = []
opt_plsa_not_const_phi.iteration_callback = (
lambda it, phi, theta: plsa_not_const_phi.append(
accuracy_score(algo.predict(theta), doc_targets_doc_test)))
opt_plsa_const_phi.iteration_callback = (
lambda it, phi, theta: plsa_const_phi.append(
accuracy_score(algo.predict(theta), doc_targets_doc_test)))
opt_artm_thetaless.iteration_callback = (
lambda it, phi, theta: artm_thetaless.append(
accuracy_score(algo.predict(theta), doc_targets_doc_test)))
for opt in [
opt_plsa_not_const_phi, opt_plsa_const_phi, opt_artm_thetaless
]:
opt.run(n_dw_matrix_doc_test, phi, init_theta)
res_plsa_not_const_phi.append(plsa_not_const_phi)
res_plsa_const_phi.append(plsa_const_phi)
res_artm_thetaless.append(artm_thetaless)
callbacks.save_results(
{
'res_plsa_not_const_phi': res_plsa_not_const_phi,
'res_plsa_const_phi': res_plsa_const_phi,
'res_artm_thetaless': res_artm_thetaless,
'cv_fold_scores': cv_fold_scores,
'cv_test_scores': cv_test_scores
}, output_path)
train_proportion=0.8)[:2]
args_list = list()
for T in [20, 50]:
for phi_alpha in [-0.1, 0., 0.1]:
for theta_alpha in [-0.1, 0., 0.1]:
regularization_list = [
regularizers.Additive(phi_alpha, theta_alpha)
] * ITERS_COUNT
args_list.append(
(train_n_dw_matrix, test_n_dw_matrix,
default.Optimizer(regularization_list), T, SAMPLES,
'nips_experiment/NIPS_{}t_base_{}_{}.pkl'.format(
T, phi_alpha, theta_alpha)))
args_list.append(
(train_n_dw_matrix, test_n_dw_matrix,
naive_thetaless.Optimizer(regularization_list), T,
SAMPLES,
'nips_experiment/NIPS_{}t_naive_{}_{}.pkl'.format(
T, phi_alpha, theta_alpha)))
for use_B_cheat in [False, True]:
args_list.append(
(train_n_dw_matrix, test_n_dw_matrix,
thetaless.Optimizer(regularization_list,
use_B_cheat=use_B_cheat), T,
SAMPLES,
'nips_experiment/NIPS_{}t_artm_{}_{}_{}.pkl'.format(
T, phi_alpha, theta_alpha, use_B_cheat)))
Pool(processes=5).map(manager.perform_experiment, args_list)
'results/{}'.format(name)
)
if __name__ == '__main__':
n_ww_matrix = main_cases.get_wntm_matrix()
args_list = [
create_exp_args(n_ww_matrix, 'plsa', reg_funcs.plsa),
create_exp_args(n_ww_matrix, 'plsa_honest', reg_funcs.plsa_honest),
create_exp_args(n_ww_matrix, 'plsa_origin', reg_funcs.plsa_origin),
create_exp_args(
n_ww_matrix, 'plsa_semi_honest', reg_funcs.plsa_semi_honest
),
create_exp_args(
n_ww_matrix, 'tARTM',
optimizer=thetaless.Optimizer(
[reg_funcs.trivial] * ITERS_COUNT,
use_B_cheat=False
),
),
create_exp_args(
n_ww_matrix, 'tARTM_cheat',
optimizer=thetaless.Optimizer(
[reg_funcs.trivial] * ITERS_COUNT,
use_B_cheat=True
)
)
]
Pool(processes=3).map(manager.perform_ww_experiment, args_list)