def test_load_multi_file_training_data(default_domain):
# the stories file in `data/test_multifile_stories` is the same as in
# `data/test_stories/stories.md`, but split across multiple files
featurizer = MaxHistoryTrackerFeaturizer(BinarySingleStateFeaturizer(),
max_history=2)
trackers = training.load_data("data/test_stories/stories.md",
default_domain,
augmentation_factor=0)
(tr_as_sts, tr_as_acts) = featurizer.training_states_and_actions(
trackers, default_domain)
hashed = []
for sts, acts in zip(tr_as_sts, tr_as_acts):
hashed.append(json.dumps(sts + acts, sort_keys=True))
hashed = sorted(hashed, reverse=True)
data = featurizer.featurize_trackers(trackers, default_domain)
featurizer_mul = MaxHistoryTrackerFeaturizer(BinarySingleStateFeaturizer(),
max_history=2)
trackers_mul = training.load_data("data/test_multifile_stories",
default_domain,
augmentation_factor=0)
(tr_as_sts_mul, tr_as_acts_mul) = featurizer.training_states_and_actions(
trackers_mul, default_domain)
hashed_mul = []
for sts_mul, acts_mul in zip(tr_as_sts_mul, tr_as_acts_mul):
hashed_mul.append(json.dumps(sts_mul + acts_mul, sort_keys=True))
hashed_mul = sorted(hashed_mul, reverse=True)
data_mul = featurizer_mul.featurize_trackers(trackers_mul, default_domain)
assert hashed == hashed_mul
assert np.all(data.X.sort(axis=0) == data_mul.X.sort(axis=0))
assert np.all(data.y.sort(axis=0) == data_mul.y.sort(axis=0))
def test_load_multi_file_training_data(default_domain):
# the stories file in `data/test_multifile_stories` is the same as in
# `data/test_stories/stories.md`, but split across multiple files
featurizer = MaxHistoryTrackerFeaturizer(
BinarySingleStateFeaturizer(), max_history=2)
trackers = training.load_data(
"data/test_stories/stories.md",
default_domain,
augmentation_factor=0
)
(tr_as_sts, tr_as_acts) = featurizer.training_states_and_actions(
trackers, default_domain)
hashed = []
for sts, acts in zip(tr_as_sts, tr_as_acts):
hashed.append(json.dumps(sts + acts, sort_keys=True))
hashed = sorted(hashed, reverse=True)
data = featurizer.featurize_trackers(trackers,
default_domain)
featurizer_mul = MaxHistoryTrackerFeaturizer(
BinarySingleStateFeaturizer(), max_history=2)
trackers_mul = training.load_data(
"data/test_multifile_stories",
default_domain,
augmentation_factor=0
)
(tr_as_sts_mul, tr_as_acts_mul) = featurizer.training_states_and_actions(
trackers_mul, default_domain)
hashed_mul = []
for sts_mul, acts_mul in zip(tr_as_sts_mul, tr_as_acts_mul):
hashed_mul.append(json.dumps(sts_mul + acts_mul, sort_keys=True))
hashed_mul = sorted(hashed_mul, reverse=True)
data_mul = featurizer_mul.featurize_trackers(trackers_mul,
default_domain)
assert hashed == hashed_mul
assert np.all(data.X.sort(axis=0) == data_mul.X.sort(axis=0))
assert np.all(data.y.sort(axis=0) == data_mul.y.sort(axis=0))
def test_load_training_data_handles_hidden_files(tmpdir, default_domain):
# create a hidden file
open(os.path.join(tmpdir.strpath, ".hidden"), 'a').close()
# create a normal file
normal_file = os.path.join(tmpdir.strpath, "normal_file")
open(normal_file, 'a').close()
featurizer = MaxHistoryTrackerFeaturizer(BinarySingleStateFeaturizer(),
max_history=2)
trackers = training.load_data(tmpdir.strpath, default_domain)
data = featurizer.featurize_trackers(trackers, default_domain)
assert len(data.X) == 0
assert len(data.y) == 0
def test_load_training_data_handles_hidden_files(tmpdir, default_domain):
# create a hidden file
open(os.path.join(tmpdir.strpath, ".hidden"), 'a').close()
# create a normal file
normal_file = os.path.join(tmpdir.strpath, "normal_file")
open(normal_file, 'a').close()
featurizer = MaxHistoryTrackerFeaturizer(BinarySingleStateFeaturizer(),
max_history=2)
trackers = training.load_data(
tmpdir.strpath,
default_domain
)
data = featurizer.featurize_trackers(trackers,
default_domain)
assert len(data.X) == 0
assert len(data.y) == 0
def test_generate_training_data_with_cycles(tmpdir, default_domain):
featurizer = MaxHistoryTrackerFeaturizer(BinarySingleStateFeaturizer(),
max_history=4)
training_trackers = training.load_data(
"data/test_stories/stories_with_cycle.md",
default_domain,
augmentation_factor=0)
training_data = featurizer.featurize_trackers(training_trackers,
default_domain)
y = training_data.y.argmax(axis=-1)
# how many there are depends on the graph which is not created in a
# deterministic way but should always be 3 or
assert len(training_trackers) == 3 or len(training_trackers) == 4
# if we have 4 trackers, there is going to be one example more for label 2
num_twos = len(training_trackers) - 1
assert Counter(y) == {0: 6, 1: 2, 2: num_twos, 3: 1, 4: 3}
def test_generate_training_data_with_cycles(tmpdir, default_domain):
featurizer = MaxHistoryTrackerFeaturizer(BinarySingleStateFeaturizer(),
max_history=4)
training_trackers = training.load_data(
"data/test_stories/stories_with_cycle.md",
default_domain,
augmentation_factor=0
)
training_data = featurizer.featurize_trackers(training_trackers,
default_domain)
y = training_data.y.argmax(axis=-1)
# how many there are depends on the graph which is not created in a
# deterministic way but should always be 3 or
assert len(training_trackers) == 3 or len(training_trackers) == 4
# if we have 4 trackers, there is going to be one example more for label 3
num_threes = len(training_trackers) - 1
assert Counter(y) == {0: 6, 1: 2, 3: num_threes, 4: 1, 5: 3}