def test_linked_nltcs_kernel_spn_perf():
print('Loading datasets')
train, valid, test = dataset.load_train_val_test_csvs('nltcs')
n_instances = train.shape[0]
# estimating the frequencies for the features
print('Estimating features')
freqs, features = dataset.data_2_freqs(train)
print('ninst', n_instances, 'feats', features)
print('Build kernel density estimation')
spn = SpnFactory.linked_kernel_density_estimation(n_instances,
features)
print(spn.stats())
print('Evaluating on test')
# evaluating one at a time since we are using a sparse representation
lls = []
eval_start_t = perf_counter()
for i in range(test.shape[0]):
print('instance', i)
lls.append(spn.eval(test[i, :]))
print('Mean lls')
# avg_ll = sum(lls) / float(len(lls))
avg_ll = numpy.mean(lls)
eval_end_t = perf_counter()
print('AVG LL {0} in {1} secs'.format(avg_ll, eval_end_t - eval_start_t))
def test_linked_kernel_density_estimation():
num_instances = 5
spn = SpnFactory.linked_kernel_density_estimation(num_instances,
vars)
print('Kernel density estimation')
print(spn)
print(spn.stats())
def test_linked_nltcs_kernel_spn_perf():
print('Loading datasets')
train, valid, test = dataset.load_train_val_test_csvs('nltcs')
n_instances = train.shape[0]
# estimating the frequencies for the features
print('Estimating features')
freqs, features = dataset.data_2_freqs(train)
print('ninst', n_instances, 'feats', features)
print('Build kernel density estimation')
spn = SpnFactory.linked_kernel_density_estimation(n_instances,
features)
print(spn.stats())
print('Evaluating on test')
# evaluating one at a time since we are using a sparse representation
lls = []
eval_start_t = perf_counter()
for i in range(test.shape[0]):
print('instance', i)
lls.append(spn.eval(test[i, :]))
print('Mean lls')
# avg_ll = sum(lls) / float(len(lls))
avg_ll = numpy.mean(lls)
eval_end_t = perf_counter()
print('AVG LL {0} in {1} secs'.format(avg_ll, eval_end_t - eval_start_t))
def test_linked_kernel_density_estimation():
num_instances = 5
spn = SpnFactory.linked_kernel_density_estimation(num_instances,
vars)
print('Kernel density estimation')
print(spn)
print(spn.stats())
def atest_nltcs_em_fit():
print('Loading datasets')
train, valid, test = dataset.load_train_val_test_csvs('nltcs')
n_instances = train.shape[0]
# estimating the frequencies for the features
print('Estimating features')
freqs, features = dataset.data_2_freqs(train)
print('Build kernel density estimation')
spn = SpnFactory.linked_kernel_density_estimation(n_instances, features)
print('EM training')
spn.fit_em(train, valid, test, hard=True, epochs=2)
def test_sgd():
print('Loading datasets')
train, valid, test = dataset.load_train_val_test_csvs('nltcs')
n_instances = train.shape[0]
n_test_instances = test.shape[0]
# estimating the frequencies for the features
print('Estimating features')
freqs, features = dataset.data_2_freqs(train)
print('Build kernel density estimation')
spn = SpnFactory.linked_kernel_density_estimation(n_instances, features)
print('Created SPN with\n' + spn.stats())
print('Starting SGD')
spn.fit_sgd(train,
valid,
test,
learning_rate=0.1,
n_epochs=20,
batch_size=1,
hard=False)
