async def test_create_train_data_with_history(default_domain):
featurizer = MaxHistoryTrackerFeaturizer(max_history=4)
training_trackers = await training.load_data(DEFAULT_STORIES_FILE,
default_domain,
augmentation_factor=0)
assert len(training_trackers) == 3
(decoded,
_) = featurizer.training_states_and_actions(training_trackers,
default_domain)
# decoded needs to be sorted
hashed = []
for states in decoded:
hashed.append(json.dumps(states, sort_keys=True))
hashed = sorted(hashed)
assert hashed == [
'[{"prev_action": {"action_name": "action_listen"}, "slots": {"name": [1.0]}, "user": {"entities": ["name"], "intent": "greet"}}, {"prev_action": {"action_name": "utter_greet"}, "slots": {"name": [1.0]}, "user": {"entities": ["name"], "intent": "greet"}}, {"prev_action": {"action_name": "action_listen"}, "slots": {"name": [1.0]}, "user": {"intent": "default"}}, {"prev_action": {"action_name": "utter_default"}, "slots": {"name": [1.0]}, "user": {"intent": "default"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"intent": "default"}}, {"prev_action": {"action_name": "utter_default"}, "user": {"intent": "default"}}, {"prev_action": {"action_name": "action_listen"}, "user": {"intent": "goodbye"}}, {"prev_action": {"action_name": "utter_goodbye"}, "user": {"intent": "goodbye"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"intent": "greet"}}, {"prev_action": {"action_name": "utter_greet"}, "user": {"intent": "greet"}}, {"prev_action": {"action_name": "action_listen"}, "user": {"intent": "default"}}, {"prev_action": {"action_name": "utter_default"}, "user": {"intent": "default"}}]',
'[{"prev_action": {"action_name": "utter_greet"}, "user": {"intent": "greet"}}, {"prev_action": {"action_name": "action_listen"}, "user": {"intent": "default"}}, {"prev_action": {"action_name": "utter_default"}, "user": {"intent": "default"}}, {"prev_action": {"action_name": "action_listen"}, "user": {"intent": "goodbye"}}]',
'[{}, {"prev_action": {"action_name": "action_listen"}, "slots": {"name": [1.0]}, "user": {"entities": ["name"], "intent": "greet"}}, {"prev_action": {"action_name": "utter_greet"}, "slots": {"name": [1.0]}, "user": {"entities": ["name"], "intent": "greet"}}, {"prev_action": {"action_name": "action_listen"}, "slots": {"name": [1.0]}, "user": {"intent": "default"}}]',
'[{}, {"prev_action": {"action_name": "action_listen"}, "slots": {"name": [1.0]}, "user": {"entities": ["name"], "intent": "greet"}}, {"prev_action": {"action_name": "utter_greet"}, "slots": {"name": [1.0]}, "user": {"entities": ["name"], "intent": "greet"}}]',
'[{}, {"prev_action": {"action_name": "action_listen"}, "slots": {"name": [1.0]}, "user": {"entities": ["name"], "intent": "greet"}}]',
'[{}, {"prev_action": {"action_name": "action_listen"}, "user": {"intent": "greet"}}, {"prev_action": {"action_name": "utter_greet"}, "user": {"intent": "greet"}}, {"prev_action": {"action_name": "action_listen"}, "user": {"intent": "default"}}]',
'[{}, {"prev_action": {"action_name": "action_listen"}, "user": {"intent": "greet"}}, {"prev_action": {"action_name": "utter_greet"}, "user": {"intent": "greet"}}]',
'[{}, {"prev_action": {"action_name": "action_listen"}, "user": {"intent": "greet"}}]',
"[{}]",
]
async def test_create_train_data_no_history(domain: Domain,
stories_path: Text):
featurizer = MaxHistoryTrackerFeaturizer(max_history=1)
training_trackers = await training.load_data(stories_path,
domain,
augmentation_factor=0)
assert len(training_trackers) == 4
(decoded,
_) = featurizer.training_states_and_actions(training_trackers, domain)
# decoded needs to be sorted
hashed = []
for states in decoded:
hashed.append(json.dumps(states, sort_keys=True))
hashed = sorted(hashed, reverse=True)
assert hashed == [
"[{}]",
'[{"prev_action": {"action_name": "utter_greet"}, "user": {"intent": "greet"}}]',
'[{"prev_action": {"action_name": "utter_greet"}, "slots": {"name": [1.0]}, "user": {"entities": ["name"], "intent": "greet"}}]',
'[{"prev_action": {"action_name": "utter_goodbye"}, "user": {"intent": "goodbye"}}]',
'[{"prev_action": {"action_name": "utter_default"}, "user": {"intent": "default"}}]',
'[{"prev_action": {"action_name": "utter_default"}, "slots": {"name": [1.0]}, "user": {"intent": "default"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"intent": "greet"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"intent": "goodbye"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"intent": "default"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "slots": {"name": [1.0]}, "user": {"intent": "default"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "slots": {"name": [1.0]}, "user": {"entities": ["name"], "intent": "greet"}}]',
]
def test_slots_states_before_user_utterance(default_domain):
featurizer = MaxHistoryTrackerFeaturizer()
tracker = DialogueStateTracker.from_events(
"bla",
evts=[
SlotSet(default_domain.slots[0].name, "some_value"),
ActionExecuted("utter_default"),
],
slots=default_domain.slots,
)
trackers_as_states, _ = featurizer.training_states_and_actions(
[tracker], default_domain)
expected_states = [[{"slots": {"name": (1.0, )}}]]
assert trackers_as_states == expected_states
async def test_create_train_data_unfeaturized_entities():
import copy
domain_file = "data/test_domains/default_unfeaturized_entities.yml"
stories_file = "data/test_stories/stories_unfeaturized_entities.md"
domain = Domain.load(domain_file)
featurizer = MaxHistoryTrackerFeaturizer(max_history=1)
training_trackers = await training.load_data(stories_file,
domain,
augmentation_factor=0)
assert len(training_trackers) == 2
(decoded,
_) = featurizer.training_states_and_actions(training_trackers, domain)
# decoded needs to be sorted
hashed = []
for states in decoded:
new_states = [
check_for_too_many_entities_and_remove_them(state)
for state in states
]
hashed.append(json.dumps(new_states, sort_keys=True))
hashed = sorted(hashed, reverse=True)
assert hashed == [
"[{}]",
'[{"prev_action": {"action_name": "utter_greet"}, "user": {"intent": "greet"}}]',
'[{"prev_action": {"action_name": "utter_greet"}, "user": {"entities": ["name"], "intent": "greet"}}]',
'[{"prev_action": {"action_name": "utter_goodbye"}, "user": {"intent": "goodbye"}}]',
'[{"prev_action": {"action_name": "utter_default"}, "user": {"intent": "why"}}]',
'[{"prev_action": {"action_name": "utter_default"}, "user": {"intent": "thank"}}]',
'[{"prev_action": {"action_name": "utter_default"}, "user": {"entities": [], "intent": "default"}}]',
'[{"prev_action": {"action_name": "utter_default"}, "user": {"entities": [], "intent": "ask"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"intent": "why"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"intent": "thank"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"intent": "greet"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"intent": "goodbye"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"entities": [], "intent": "default"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"entities": [], "intent": "ask"}}]',
'[{"prev_action": {"action_name": "action_listen"}, "user": {"entities": ["name"], "intent": "greet"}}]',
]
async def test_load_multi_file_training_data(
stories_resources: List, default_domain: 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(SingleStateFeaturizer(), max_history=2)
trackers = await training.load_data(
stories_resources[0], 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, label_ids = featurizer.featurize_trackers(
trackers, default_domain, interpreter=RegexInterpreter()
)
featurizer_mul = MaxHistoryTrackerFeaturizer(SingleStateFeaturizer(), max_history=2)
trackers_mul = await training.load_data(
stories_resources[1], 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, label_ids_mul = featurizer_mul.featurize_trackers(
trackers_mul, default_domain, interpreter=RegexInterpreter()
)
assert hashed == hashed_mul
# we check for intents, action names and entities -- the features which
# are included in the story files
data = surface_attributes(data)
data_mul = surface_attributes(data_mul)
for attribute in [INTENT, ACTION_NAME, ENTITIES]:
if attribute not in data or attribute not in data_mul:
continue
assert len(data.get(attribute)) == len(data_mul.get(attribute))
for idx_tracker in range(len(data.get(attribute))):
for idx_dialogue in range(len(data.get(attribute)[idx_tracker])):
f1 = data.get(attribute)[idx_tracker][idx_dialogue]
f2 = data_mul.get(attribute)[idx_tracker][idx_dialogue]
if f1 is None or f2 is None:
assert f1 == f2
continue
for idx_turn in range(len(f1)):
f1 = data.get(attribute)[idx_tracker][idx_dialogue][idx_turn]
f2 = data_mul.get(attribute)[idx_tracker][idx_dialogue][idx_turn]
assert np.all((f1 == f2).data)
assert np.all(label_ids == label_ids_mul)
