def run_gridsearch_single_core():
print("========== Tune parameters for IGKOL for classification ==========")
data_name = 'svmguide1'
n_features = 4
train_file_name = os.path.join(data_dir(), data_name + '_train.libsvm')
test_file_name = os.path.join(data_dir(), data_name + '_test.libsvm')
print(train_file_name)
print(test_file_name)
if not os.path.exists(train_file_name):
raise Exception('File not found')
if not os.path.exists(test_file_name):
raise Exception('File not found')
x_train, y_train = load_svmlight_file(train_file_name,
n_features=n_features)
x_test, y_test = load_svmlight_file(test_file_name, n_features=n_features)
x_train = x_train.toarray()
x_test = x_test.toarray()
x_total = np.vstack((x_train, x_test))
y_total = np.concatenate((y_train, y_test))
print("Number of total samples = {}".format(x_total.shape[0]))
params = {'regular_param': [0.0001, 0.00001], 'gamma': [0.25, 0.5, 1, 2]}
candidate_params_lst = list(ParameterGrid(params))
mistake_rate_lst = []
run_param_lst = []
for candidate_params in candidate_params_lst:
clf = OnlineDualSVRG(
# regular_param=0.01,
learning_rate_scale=0.8,
# gamma=2.0,
rf_dim=400,
num_epochs=1,
freq_update_full_model=100,
oracle='coverage',
core_max=100,
coverage_radius=0.9,
loss_func='logistic',
smooth_hinge_theta=0.5,
smooth_hinge_tau=0.5,
random_state=3333,
**candidate_params,
)
clf.fit(x_total, y_total)
print('Params:', candidate_params, 'Mistake rate:', clf.mistake_rate)
mistake_rate_lst.append(clf.mistake_rate)
run_param_lst.append(candidate_params)
idx_best = np.argmin(np.array(mistake_rate_lst))
print('Best mistake rate: {}'.format(mistake_rate_lst[idx_best]))
print('Best params: {}'.format(run_param_lst[idx_best]))
def run_one_candidate(candidate_params):
np.random.seed(random_seed())
mistake_rate_avg = 0
train_time_avg = 0
num_runs = 3
for ri in range(num_runs):
print('----------------------------------')
print('Run #{0}:'.format(ri + 1))
# np.random.seed(5555)
# np.random.seed(4444)
data_name = dataset
n_features = 300
train_file_name = os.path.join(data_dir(), data_name + '_train.libsvm')
test_file_name = os.path.join(data_dir(), data_name + '_test.libsvm')
if not os.path.exists(train_file_name):
raise Exception('File not found')
if not os.path.exists(test_file_name):
raise Exception('File not found')
x_train, y_train = load_svmlight_file(train_file_name,
n_features=n_features)
x_test, y_test = load_svmlight_file(test_file_name,
n_features=n_features)
x_train = x_train.toarray()
x_test = x_test.toarray()
x_total = np.vstack((x_train, x_test))
y_total = np.concatenate((y_train, y_test))
print('Num total samples: {}'.format(x_total.shape[0]))
clf = OnlineDualSVRG(
# regular_param=0.01,
learning_rate_scale=0.8,
# gamma=2.0,
rf_dim=4000,
num_epochs=1,
freq_update_full_model=100,
oracle=oracle,
core_max=100,
coverage_radius=40.0,
loss_func=loss_func,
smooth_hinge_theta=0.5,
smooth_hinge_tau=0.5,
random_state=3333,
**candidate_params,
)
print('Running ...')
clf.fit(x_total, y_total)
print('Mistake rate: {0:.2f}%, Training time: {1} seconds'.format(
clf.mistake_rate * 100, int(clf.train_time)))
mistake_rate_avg += clf.mistake_rate
train_time_avg += clf.train_time
return mistake_rate_avg / num_runs, train_time_avg / num_runs, candidate_params
def run_grid_search_multicore():
if not os.path.exists(os.path.join(data_dir(), dataset + '_train.libsvm')):
dataset_info = data_info(dataset)
get_file(dataset, origin=dataset_info['origin'], untar=True, md5_hash=dataset_info['md5_hash'])
params = {'regular_param': [3.8639876352395671e-06],
'gamma': [0.015625]}
candidate_params_lst = list(ParameterGrid(params))
pool = mp.Pool(processes=20) # maximum of workers
for candidate_params in candidate_params_lst:
pool.apply_async(run_one_candidate, args=(candidate_params,), callback=log_result)
# for candidate_params in candidate_params_lst:
# run_one_candidate(candidate_params)
pool.close()
pool.join()
if len(candidate_params_lst) > 1:
print("========== FINAL RESULT ==========")
idx_best = np.argmin(np.array(mistake_rate_lst))
print('Data set: {}'.format(dataset))
print('Oracle: {}'.format('budget'))
print('Loss func: {}'.format(loss_func))
print('Best mistake rate: {}'.format(mistake_rate_lst[idx_best]))
print('Best params: {}'.format(run_param_lst[idx_best]))
print('Time per candidate param: {}'.format(time_lst[idx_best]))