def test_select_sample_size_none(seed_random):
input_matrix, target_matrix = datasets.get_xor()
new_inp_matrix, new_tar_matrix = base.select_sample(
input_matrix, target_matrix)
assert new_inp_matrix.shape == input_matrix.shape
assert new_tar_matrix.shape == target_matrix.shape
for inp_vec in input_matrix: # all in
assert inp_vec in new_inp_matrix
for tar_vec in target_matrix: # all in
assert tar_vec in new_tar_matrix
assert not (new_inp_matrix == input_matrix).all() # order different
assert not (new_tar_matrix == target_matrix).all() # order different
def test_select_sample_size_none(seed_random):
# Default to size smaller than number of samples
input_matrix, target_matrix = datasets.get_random_classification(
1000, 1, 2)
new_inp_matrix, new_tar_matrix = base.select_sample(
input_matrix, target_matrix)
assert len(new_inp_matrix) < len(input_matrix)
assert len(new_inp_matrix) == base._selection_size_heuristic(
len(input_matrix))
assert len(new_tar_matrix) < len(input_matrix)
assert len(new_tar_matrix) == base._selection_size_heuristic(
len(input_matrix))
def test_select_sample_size_none_few_samples(seed_random):
# When number of samples is low, default to all samples
input_matrix, target_matrix = datasets.get_xor()
new_inp_matrix, new_tar_matrix = base.select_sample(
input_matrix, target_matrix)
assert new_inp_matrix.shape == input_matrix.shape
assert new_tar_matrix.shape == target_matrix.shape
for inp_vec in input_matrix: # all in
assert inp_vec in new_inp_matrix
for tar_vec in target_matrix: # all in
assert tar_vec in new_tar_matrix
assert not (new_inp_matrix == input_matrix).all() # Different order
assert not (new_tar_matrix == target_matrix).all() # Different order
def test_Model_stochastic_train():
"""Train with stochastic gradient descent."""
from learning import transfer, error, validation, MLP
dataset = datasets.get_iris()
model = MLP((len(dataset[0][0]), 2, len(dataset[1][0])),
transfers=transfer.SoftmaxTransfer(),
error_func=error.CrossEntropyError())
# Model should be able to converge with mini-batches
model.stochastic_train(
*dataset,
error_break=0.02,
pattern_selection_func=lambda X, Y: base.select_sample(X, Y, size=30),
train_kwargs={
'iterations': 100,
'error_break': 0.02
})
assert validation.get_error(model, *dataset) <= 0.03
def test_select_sample(seed_random):
input_matrix, target_matrix = datasets.get_xor()
# Test size param
new_inp_matrix, new_tar_matrix = base.select_sample(input_matrix,
target_matrix,
size=2)
assert new_inp_matrix.shape[0] == 2
assert new_tar_matrix.shape[0] == 2
# No duplicates
count = 0
for inp_vec in new_inp_matrix:
if inp_vec in input_matrix:
count += 1
assert count == 2
count = 0
for tar_vec in new_tar_matrix:
if tar_vec in target_matrix:
count += 1
assert count == 2