def process(self, message: Message, **kwargs: Any) -> None:
entities = self.extract_entities(message)
entities = self.add_extractor_name(entities)
message.set(ENTITIES, message.get(ENTITIES, []) + entities, add_to_output=True)
def _tokens_of_message(message: Message) -> List[Text]:
return [token.text for token in message.get(TOKENS_NAMES[TEXT], [])]
def process(self, message: Message, **kwargs: Any) -> None:
for attribute in DENSE_FEATURIZABLE_ATTRIBUTES:
if message.get(attribute):
message.set(SPACY_DOCS[attribute],
self.doc_for_text(message.get(attribute)))
def process(self, message: Message, **kwargs: Any) -> None:
updated_entities = message.get(ENTITIES, [])[:]
self.replace_synonyms(updated_entities)
message.set(ENTITIES, updated_entities, add_to_output=True)
def tokenize(self, message: Message, attribute: Text) -> List[Token]:
text = message.get(attribute)
words = word_tokenize(text)
# words = ViTokenizer.tokenize(text).split(' ')
return self._convert_words_to_tokens(words, text)
def get_doc(self, message: Message, attribute: Text) -> Any:
return message.get(SPACY_DOCS[attribute])
def compute_similarity_for_pair(self, a: Message, b: Message):
features_a = a.get("sentence_features").vector
features_b = b.get("sentence_features").vector
return self.compute_similarity_score(features_a, features_b)
def _get_doc(self, message: Message, attribute: Text) -> Optional["Doc"]:
return message.get(SPACY_DOCS[attribute])
def _unpack(self, message: Message, domain: Domain) -> Message:
"""Unpacks the messsage if `TEXT` contains an encoding of attributes.
Args:
message: some message
domain: the domain
Returns:
the given message if that message does not need to be unpacked, and a new
message with the extracted attributes otherwise
"""
user_text = message.get(TEXT).strip()
# If the prefix doesn't match, we don't even need to try to match the pattern.
if not user_text.startswith(self._prefix):
return message
# Try to match the pattern.
match = self._pattern.match(user_text)
# If it doesn't match, then (potentially) something went wrong, because the
# message text did start with the special prefix -- however, a user might
# just have decided to start their text this way.
if not match:
logger.warning(
f"Failed to parse intent end entities from '{user_text}'.")
return message
# Extract attributes from the match - and validate it via the domain.
intent_name = self._parse_intent_name(match, domain)
confidence = self._parse_optional_confidences(match)
entities = self._parse_optional_entities(match, domain)
# The intent name is *not* optional, but during parsing we might find out
# that the given intent is unknown (and warn). In this case, stop here.
if intent_name is None:
return message
if match.group("rest"):
rasa.shared.utils.io.raise_warning(
f"Failed to parse arguments in line '{match.string}'. "
f"Failed to interpret some parts. "
f"Continuing without {match.group('rest')}. ",
docs=DOCS_URL_STORIES,
)
# Add the results to the message.
intent_data = {
INTENT_NAME_KEY: intent_name,
PREDICTED_CONFIDENCE_KEY: confidence,
}
intent_ranking = [{
INTENT_NAME_KEY: intent_name,
PREDICTED_CONFIDENCE_KEY: confidence,
}]
message_data = {}
message_data[TEXT] = user_text
message_data[INTENT] = intent_data
message_data[INTENT_RANKING_KEY] = intent_ranking
message_data[ENTITIES] = entities
return Message(message_data,
output_properties=set(message_data.keys()))
def process(self, message: Message, **kwargs: Any) -> None:
extracted = self._match_entities(message)
message.set("entities",
message.get("entities", []) + extracted,
add_to_output=True)
def test_base_examples(example):
message = Message({TEXT: example["text"]})
tok = BlankSpacyTokenizer(component_config={"lang": example["lang"]})
tok.process(message)
tokens = message.get(TOKENS_NAMES[TEXT])
assert [t.text for t in tokens] == example["result"]
def test_classification(self, trained_classifier, message, intent):
text = Message(data={TEXT: message})
trained_classifier.process(text)
assert text.get("intent").get("name", "NOT_CLASSIFIED") == intent
def process(self, message: Message, **kwargs: Any) -> None:
if message.get(TEXT) != None:
message.set(TEXT, message.get(TEXT).title())
async def test_adjusting_layers_incremental_training(
create_response_selector: Callable[[Dict[Text, Any]], ResponseSelector],
load_response_selector: Callable[[Dict[Text, Any]], ResponseSelector],
train_and_preprocess: Callable[..., Tuple[TrainingData,
List[GraphComponent]]],
process_message: Callable[..., Message],
):
"""Tests adjusting sparse layers of `ResponseSelector` to increased sparse
feature sizes during incremental training.
Testing is done by checking the layer sizes.
Checking if they were replaced correctly is also important
and is done in `test_replace_dense_for_sparse_layers`
in `test_rasa_layers.py`.
"""
iter1_data_path = "data/test_incremental_training/iter1/"
iter2_data_path = "data/test_incremental_training/"
pipeline = [
{
"component": WhitespaceTokenizer
},
{
"component": LexicalSyntacticFeaturizer
},
{
"component": RegexFeaturizer
},
{
"component": CountVectorsFeaturizer
},
{
"component": CountVectorsFeaturizer,
"analyzer": "char_wb",
"min_ngram": 1,
"max_ngram": 4,
},
]
training_data, loaded_pipeline = train_and_preprocess(
pipeline, iter1_data_path)
response_selector = create_response_selector({EPOCHS: 1})
response_selector.train(training_data=training_data)
old_data_signature = response_selector.model.data_signature
old_predict_data_signature = response_selector.model.predict_data_signature
message = Message(data={TEXT: "Rasa is great!"})
message = process_message(loaded_pipeline, message)
message2 = copy.deepcopy(message)
classified_message = response_selector.process([message])[0]
old_sparse_feature_sizes = classified_message.get_sparse_feature_sizes(
attribute=TEXT)
initial_rs_layers = response_selector.model._tf_layers[
"sequence_layer.text"]._tf_layers["feature_combining"]
initial_rs_sequence_layer = initial_rs_layers._tf_layers[
"sparse_dense.sequence"]._tf_layers["sparse_to_dense"]
initial_rs_sentence_layer = initial_rs_layers._tf_layers[
"sparse_dense.sentence"]._tf_layers["sparse_to_dense"]
initial_rs_sequence_size = initial_rs_sequence_layer.get_kernel().shape[0]
initial_rs_sentence_size = initial_rs_sentence_layer.get_kernel().shape[0]
assert initial_rs_sequence_size == sum(
old_sparse_feature_sizes[FEATURE_TYPE_SEQUENCE])
assert initial_rs_sentence_size == sum(
old_sparse_feature_sizes[FEATURE_TYPE_SENTENCE])
loaded_selector = load_response_selector({EPOCHS: 1})
classified_message2 = loaded_selector.process([message2])[0]
assert classified_message2.fingerprint() == classified_message.fingerprint(
)
training_data2, loaded_pipeline2 = train_and_preprocess(
pipeline, iter2_data_path)
response_selector.train(training_data=training_data2)
new_message = Message.build(text="Rasa is great!")
new_message = process_message(loaded_pipeline2, new_message)
classified_new_message = response_selector.process([new_message])[0]
new_sparse_feature_sizes = classified_new_message.get_sparse_feature_sizes(
attribute=TEXT)
final_rs_layers = response_selector.model._tf_layers[
"sequence_layer.text"]._tf_layers["feature_combining"]
final_rs_sequence_layer = final_rs_layers._tf_layers[
"sparse_dense.sequence"]._tf_layers["sparse_to_dense"]
final_rs_sentence_layer = final_rs_layers._tf_layers[
"sparse_dense.sentence"]._tf_layers["sparse_to_dense"]
final_rs_sequence_size = final_rs_sequence_layer.get_kernel().shape[0]
final_rs_sentence_size = final_rs_sentence_layer.get_kernel().shape[0]
assert final_rs_sequence_size == sum(
new_sparse_feature_sizes[FEATURE_TYPE_SEQUENCE])
assert final_rs_sentence_size == sum(
new_sparse_feature_sizes[FEATURE_TYPE_SENTENCE])
# check if the data signatures were correctly updated
new_data_signature = response_selector.model.data_signature
new_predict_data_signature = response_selector.model.predict_data_signature
iter2_data = load_data(iter2_data_path)
expected_sequence_lengths = len([
message for message in iter2_data.training_examples
if message.get(INTENT_RESPONSE_KEY)
])
def test_data_signatures(
new_signature: Dict[Text, Dict[Text, List[FeatureArray]]],
old_signature: Dict[Text, Dict[Text, List[FeatureArray]]],
):
# Wherever attribute / feature_type signature is not
# expected to change, directly compare it to old data signature.
# Else compute its expected signature and compare
attributes_expected_to_change = [TEXT]
feature_types_expected_to_change = [
FEATURE_TYPE_SEQUENCE,
FEATURE_TYPE_SENTENCE,
]
for attribute, signatures in new_signature.items():
for feature_type, feature_signatures in signatures.items():
if feature_type == "sequence_lengths":
assert feature_signatures[
0].units == expected_sequence_lengths
elif feature_type not in feature_types_expected_to_change:
assert feature_signatures == old_signature.get(
attribute).get(feature_type)
else:
for index, feature_signature in enumerate(
feature_signatures):
if (feature_signature.is_sparse and attribute
in attributes_expected_to_change):
assert feature_signature.units == sum(
new_sparse_feature_sizes.get(feature_type))
else:
# dense signature or attributes that are not
# expected to change can be compared directly
assert (
feature_signature.units == old_signature.get(
attribute).get(feature_type)[index].units)
test_data_signatures(new_data_signature, old_data_signature)
test_data_signatures(new_predict_data_signature,
old_predict_data_signature)
def compute_features(self, example: Message):
features = self.model[example.get("text")]
example.set("sentence_features", features)
def process(self, message: Message, **kwargs: Any) -> None:
from tokenizer_tools.tagset.NER.BILUO import BILUOSequenceEncoderDecoder
from tokenizer_tools.tagset.offset.sequence import Sequence
decoder = BILUOSequenceEncoderDecoder()
real_result_dir = os.path.join(self.model_dir, self.result_dir)
print(real_result_dir)
input_text = message.text
input_feature = {
'words': [[i for i in input_text]],
'words_len': [len(input_text)],
}
print(input_feature)
predictions = self.predict_fn(input_feature)
tags = predictions['tags'][0]
# print(predictions['tags'])
# decode Unicode
tags_seq = [i.decode() for i in tags]
print(tags_seq)
# BILUO to offset
failed = False
try:
seq = decoder.to_offset(tags_seq, input_text)
except Exception as e:
# invalid tag sequence will raise exception
# so return a empty result
logger.error("Decode error: {}".format(e))
seq = Sequence(input_text)
failed = True
# print(seq)
print(seq, tags_seq, failed)
entity_set = []
seq.span_set.fill_text(input_text)
for span in seq.span_set:
ent = {
"entity": span.entity,
"value": span.value,
"start": span.start,
"confidence": None,
"end": span.end
}
entity_set.append(ent)
extracted = self.add_extractor_name(entity_set)
message.set("entities",
message.get("entities", []) + extracted,
add_to_output=True)
def test_duckling_entity_extractor(component_builder):
with responses.RequestsMock() as rsps:
rsps.add(
responses.POST,
"http://localhost:8000/parse",
json=[
{
"body": "Today",
"start": 0,
"value": {
"values": [{
"value": "2018-11-13T00:00:00.000-08:00",
"grain": "day",
"type": "value",
}],
"value":
"2018-11-13T00:00:00.000-08:00",
"grain":
"day",
"type":
"value",
},
"end": 5,
"dim": "time",
"latent": False,
},
{
"body": "the 5th",
"start": 9,
"value": {
"values": [
{
"value": "2018-12-05T00:00:00.000-08:00",
"grain": "day",
"type": "value",
},
{
"value": "2019-01-05T00:00:00.000-08:00",
"grain": "day",
"type": "value",
},
{
"value": "2019-02-05T00:00:00.000-08:00",
"grain": "day",
"type": "value",
},
],
"value":
"2018-12-05T00:00:00.000-08:00",
"grain":
"day",
"type":
"value",
},
"end": 16,
"dim": "time",
"latent": False,
},
{
"body": "5th of May",
"start": 13,
"value": {
"values": [
{
"value": "2019-05-05T00:00:00.000-07:00",
"grain": "day",
"type": "value",
},
{
"value": "2020-05-05T00:00:00.000-07:00",
"grain": "day",
"type": "value",
},
{
"value": "2021-05-05T00:00:00.000-07:00",
"grain": "day",
"type": "value",
},
],
"value":
"2019-05-05T00:00:00.000-07:00",
"grain":
"day",
"type":
"value",
},
"end": 23,
"dim": "time",
"latent": False,
},
{
"body": "tomorrow",
"start": 37,
"value": {
"values": [{
"value": "2018-11-14T00:00:00.000-08:00",
"grain": "day",
"type": "value",
}],
"value":
"2018-11-14T00:00:00.000-08:00",
"grain":
"day",
"type":
"value",
},
"end": 45,
"dim": "time",
"latent": False,
},
],
)
_config = RasaNLUModelConfig(
{"pipeline": [{
"name": "DucklingEntityExtractor"
}]})
_config.set_component_attr(0,
dimensions=["time"],
timezone="UTC",
url="http://localhost:8000")
duckling = component_builder.create_component(_config.for_component(0),
_config)
message = Message(
data={TEXT: "Today is the 5th of May. Let us meet tomorrow."})
duckling.process(message)
entities = message.get("entities")
assert len(entities) == 4
# Test duckling with a defined date
with responses.RequestsMock() as rsps:
rsps.add(
responses.POST,
"http://localhost:8000/parse",
json=[{
"body": "tomorrow",
"start": 12,
"value": {
"values": [{
"value": "2013-10-13T00:00:00.000Z",
"grain": "day",
"type": "value",
}],
"value":
"2013-10-13T00:00:00.000Z",
"grain":
"day",
"type":
"value",
},
"end": 20,
"dim": "time",
"latent": False,
}],
)
# 1381536182 == 2013/10/12 02:03:02
message = Message(data={TEXT: "Let us meet tomorrow."},
time="1381536182")
duckling.process(message)
entities = message.get("entities")
assert len(entities) == 1
assert entities[0]["text"] == "tomorrow"
assert entities[0]["value"] == "2013-10-13T00:00:00.000Z"
# Test dimension filtering includes only specified dimensions
_config = RasaNLUModelConfig(
{"pipeline": [{
"name": "DucklingEntityExtractor"
}]})
_config.set_component_attr(0,
dimensions=["number"],
url="http://localhost:8000")
duckling_number = component_builder.create_component(
_config.for_component(0), _config)
with responses.RequestsMock() as rsps:
rsps.add(
responses.POST,
"http://localhost:8000/parse",
json=[
{
"body": "Yesterday",
"start": 0,
"value": {
"values": [{
"value": "2019-02-28T00:00:00.000+01:00",
"grain": "day",
"type": "value",
}],
"value":
"2019-02-28T00:00:00.000+01:00",
"grain":
"day",
"type":
"value",
},
"end": 9,
"dim": "time",
},
{
"body": "5",
"start": 21,
"value": {
"value": 5,
"type": "value"
},
"end": 22,
"dim": "number",
},
],
)
message = Message(
data={TEXT: "Yesterday there were 5 people in a room"})
duckling_number.process(message)
entities = message.get("entities")
assert len(entities) == 1
assert entities[0]["text"] == "5"
assert entities[0]["value"] == 5
def _features_for_patterns(
self, message: Message, attribute: Text
) -> Tuple[Optional[scipy.sparse.coo_matrix],
Optional[scipy.sparse.coo_matrix]]:
"""Checks which known patterns match the message.
Given a sentence, returns a vector of {1,0} values indicating which
regexes did match. Furthermore, if the
message is tokenized, the function will mark all tokens with a dict
relating the name of the regex to whether it was matched.
Args:
message: Message to be featurized.
attribute: Attribute of message to be featurized.
Returns:
Token and sentence level features of message attribute.
"""
# Attribute not set (e.g. response not present)
if not message.get(attribute):
return None, None
tokens = message.get(TOKENS_NAMES[attribute], [])
if not tokens:
# nothing to featurize
return None, None
flags = 0 # default flag
if not self.case_sensitive:
flags = re.IGNORECASE
sequence_length = len(tokens)
num_patterns = len(self.known_patterns)
sequence_features = np.zeros([sequence_length, num_patterns])
sentence_features = np.zeros([1, num_patterns])
for pattern_index, pattern in enumerate(self.known_patterns):
matches = re.finditer(pattern["pattern"],
message.get(attribute),
flags=flags)
matches = list(matches)
for token_index, t in enumerate(tokens):
patterns = t.get("pattern", default={})
patterns[pattern["name"]] = False
for match in matches:
if t.start < match.end() and t.end > match.start():
patterns[pattern["name"]] = True
sequence_features[token_index][pattern_index] = 1.0
if attribute in [RESPONSE, TEXT, ACTION_TEXT]:
# sentence vector should contain all patterns
sentence_features[0][pattern_index] = 1.0
t.set("pattern", patterns)
return (
scipy.sparse.coo_matrix(sequence_features),
scipy.sparse.coo_matrix(sentence_features),
)
def unpack_regex_message(
message: Message,
domain: Optional[Domain] = None,
entity_extractor_name: Optional[Text] = None,
) -> Message:
"""Unpacks the message if `TEXT` contains an encoding of attributes.
Args:
message: some message
domain: the domain
entity_extractor_name: An extractor name which should be added for the
entities.
Returns:
the given message if that message does not need to be unpacked, and a new
message with the extracted attributes otherwise
"""
user_text = message.get(TEXT).strip()
# If the prefix doesn't match, we don't even need to try to match the pattern.
if not user_text.startswith(INTENT_MESSAGE_PREFIX):
return message
# Try to match the pattern.
match = YAMLStoryReader._regex_message_pattern().match(user_text)
# If it doesn't match, then (potentially) something went wrong, because the
# message text did start with the special prefix -- however, a user might
# just have decided to start their text this way.
if not match:
logger.warning(f"Failed to parse intent end entities from '{user_text}'.")
return message
# Extract attributes from the match - and validate it via the domain.
intent_name = YAMLStoryReader._intent_name_from_regex_match(match, domain)
confidence = YAMLStoryReader._confidences_from_regex_match(match)
entities = YAMLStoryReader._entities_from_regex_match(
match, domain, entity_extractor_name
)
# The intent name is *not* optional, but during parsing we might find out
# that the given intent is unknown (and warn). In this case, stop here.
if intent_name is None:
return message
if match.group("rest"):
rasa.shared.utils.io.raise_warning(
f"Failed to parse arguments in line '{match.string}'. "
f"Failed to interpret some parts. "
f"Make sure your regex string is in the following format:"
f"{INTENT_MESSAGE_PREFIX}"
f"<intent_name>@<confidence-value><dictionary of entities> "
f"Continuing without {match.group('rest')}. "
)
# Add the results to the message.
intent_data = {
INTENT_NAME_KEY: intent_name,
PREDICTED_CONFIDENCE_KEY: confidence,
}
intent_ranking = [
{INTENT_NAME_KEY: intent_name, PREDICTED_CONFIDENCE_KEY: confidence}
]
message_data = {}
message_data[TEXT] = user_text
message_data[INTENT] = intent_data
message_data[INTENT_RANKING_KEY] = intent_ranking
message_data[ENTITIES] = entities
return Message(message_data, output_properties=set(message_data.keys()))
