def test_regex_featurizer_case_sensitive(
sentence: Text,
expected_sequence_features: List[float],
expected_sentence_features: List[float],
case_sensitive: bool,
spacy_nlp: Any,
create_featurizer: Callable[..., RegexFeaturizerGraphComponent],
spacy_tokenizer: SpacyTokenizerGraphComponent,
):
patterns = [
{"pattern": "[0-9]+", "name": "number", "usage": "intent"},
{"pattern": "\\bhey*", "name": "hello", "usage": "intent"},
{"pattern": "[0-1]+", "name": "binary", "usage": "intent"},
]
ftr = create_featurizer(
{"case_sensitive": case_sensitive}, known_patterns=patterns,
)
# adds tokens to the message
message = Message(data={TEXT: sentence})
message.set(SPACY_DOCS[TEXT], spacy_nlp(sentence))
spacy_tokenizer.process([message])
sequence_features, sentence_features = ftr._features_for_patterns(message, TEXT)
assert np.allclose(
sequence_features.toarray()[0], expected_sequence_features, atol=1e-10
)
assert np.allclose(
sentence_features.toarray()[-1], expected_sentence_features, atol=1e-10
)
def test_lookup_with_and_without_boundaries(
sentence: Text,
expected_sequence_features: List[List[float]],
expected_sentence_features: List[float],
labeled_tokens: List[float],
use_word_boundaries: bool,
spacy_nlp: Any,
create_featurizer: Callable[..., RegexFeaturizerGraphComponent],
spacy_tokenizer: SpacyTokenizerGraphComponent,
):
ftr = create_featurizer({"use_word_boundaries": use_word_boundaries})
training_data = TrainingData()
# we use lookups because the "use_word_boundaries" flag is only used when
# producing patterns from lookup tables
lookups = [{"name": "how", "elements": ["how"]}]
training_data.lookup_tables = lookups
ftr.train(training_data)
# adds tokens to the message
message = Message(data={TEXT: sentence})
message.set(SPACY_DOCS[TEXT], spacy_nlp(sentence))
spacy_tokenizer.process([message])
(sequence_features,
sentence_features) = ftr._features_for_patterns(message, TEXT)
sequence_features = sequence_features.toarray()
sentence_features = sentence_features.toarray()
num_of_patterns = sum([len(lookup["elements"]) for lookup in lookups])
assert sequence_features.shape == (
len(message.get(TOKENS_NAMES[TEXT])),
num_of_patterns,
)
num_of_lookup_tables = len(lookups)
assert sentence_features.shape == (num_of_lookup_tables, num_of_patterns)
# sequence_features should be {0,1} for each token: 1 if match, 0 if not
assert np.allclose(sequence_features,
expected_sequence_features,
atol=1e-10)
# sentence_features should be {0,1} for each lookup table: 1 if sentence
# contains match from that table, 0 if not
assert np.allclose(sentence_features,
expected_sentence_features,
atol=1e-10)
# the tokenizer should have added tokens
assert len(message.get(TOKENS_NAMES[TEXT], [])) > 0
# the number of regex matches on each token should match
for i, token in enumerate(message.get(TOKENS_NAMES[TEXT])):
token_matches = token.get("pattern").values()
num_matches = sum(token_matches)
# labeled_tokens should list the token(s) which match a pattern
assert num_matches == labeled_tokens.count(i)
async def test_train_persist_with_different_configurations(
crf_entity_extractor: Callable[[Dict[Text, Any]],
CRFEntityExtractorGraphComponent],
config_params: Dict[Text, Any],
default_model_storage: ModelStorage,
default_execution_context: ExecutionContext,
spacy_tokenizer: SpacyTokenizerGraphComponent,
spacy_nlp: Language,
):
crf_extractor = crf_entity_extractor(config_params)
importer = RasaFileImporter(training_data_paths=["data/examples/rasa"])
training_data = importer.get_nlu_data()
spacy_model = SpacyModel(model=spacy_nlp, model_name="en_core_web_md")
training_data = SpacyPreprocessor({}).process_training_data(
training_data, spacy_model)
training_data = spacy_tokenizer.process_training_data(training_data)
crf_extractor.train(training_data)
message = Message(data={TEXT: "I am looking for an italian restaurant"})
messages = SpacyPreprocessor({}).process([message], spacy_model)
message = spacy_tokenizer.process(messages)[0]
message2 = copy.deepcopy(message)
processed_message = crf_extractor.process([message])[0]
loaded_extractor = CRFEntityExtractorGraphComponent.load(
{
**CRFEntityExtractorGraphComponent.get_default_config(),
**config_params
},
default_model_storage,
Resource("CRFEntityExtractor"),
default_execution_context,
)
processed_message2 = loaded_extractor.process([message2])[0]
assert processed_message2.fingerprint() == processed_message.fingerprint()
detected_entities = processed_message2.get(ENTITIES)
assert len(detected_entities) == 1
assert detected_entities[0]["entity"] == "cuisine"
assert detected_entities[0]["value"] == "italian"
def test_regex_featurizer(
sentence: Text,
expected_sequence_features: List[float],
expected_sentence_features: List[float],
labeled_tokens: List[int],
spacy_nlp: Any,
create_featurizer: Callable[..., RegexFeaturizerGraphComponent],
spacy_tokenizer: SpacyTokenizerGraphComponent,
):
patterns = [
{
"pattern": "[0-9]+",
"name": "number",
"usage": "intent"
},
{
"pattern": "\\bhey*",
"name": "hello",
"usage": "intent"
},
{
"pattern": "[0-1]+",
"name": "binary",
"usage": "intent"
},
]
ftr = create_featurizer(known_patterns=patterns)
# adds tokens to the message
message = Message(data={TEXT: sentence, RESPONSE: sentence})
message.set(SPACY_DOCS[TEXT], spacy_nlp(sentence))
spacy_tokenizer.process([message])
sequence_features, sentence_features = ftr._features_for_patterns(
message, TEXT)
assert np.allclose(sequence_features.toarray(),
expected_sequence_features,
atol=1e-10)
assert np.allclose(sentence_features.toarray(),
expected_sentence_features,
atol=1e-10)
# the tokenizer should have added tokens
assert len(message.get(TOKENS_NAMES[TEXT], [])) > 0
# the number of regex matches on each token should match
for i, token in enumerate(message.get(TOKENS_NAMES[TEXT])):
token_matches = token.get("pattern").values()
num_matches = sum(token_matches)
assert num_matches == labeled_tokens.count(i)
def test_lookup_tables(
sentence: Text,
expected_sequence_features: List[float],
expected_sentence_features: List[float],
labeled_tokens: List[float],
spacy_nlp: Any,
spacy_tokenizer: SpacyTokenizerGraphComponent,
):
from rasa.nlu.featurizers.sparse_featurizer.regex_featurizer import RegexFeaturizer
lookups = [
{
"name":
"drinks",
"elements":
["mojito", "lemonade", "sweet berry wine", "tea", "club?mate"],
},
{
"name": "plates",
"elements": "data/test/lookup_tables/plates.txt"
},
]
ftr = RegexFeaturizer()
training_data = TrainingData()
training_data.lookup_tables = lookups
ftr.train(training_data)
# adds tokens to the message
message = Message(data={TEXT: sentence})
message.set("text_spacy_doc", spacy_nlp(sentence))
spacy_tokenizer.process([message])
sequence_features, sentence_features = ftr._features_for_patterns(
message, TEXT)
assert np.allclose(sequence_features.toarray(),
expected_sequence_features,
atol=1e-10)
assert np.allclose(sentence_features.toarray(),
expected_sentence_features,
atol=1e-10)
# the tokenizer should have added tokens
assert len(message.get(TOKENS_NAMES[TEXT], [])) > 0
# the number of regex matches on each token should match
for i, token in enumerate(message.get(TOKENS_NAMES[TEXT])):
token_matches = token.get("pattern").values()
num_matches = sum(token_matches)
assert num_matches == labeled_tokens.count(i)
def test_crf_use_dense_features(
crf_entity_extractor: Callable[[Dict[Text, Any]],
CRFEntityExtractorGraphComponent],
spacy_nlp: Any,
spacy_featurizer: SpacyFeaturizerGraphComponent,
spacy_tokenizer: SpacyTokenizerGraphComponent,
):
component_config = {
"features": [
["low", "title", "upper", "pos", "pos2"],
[
"low",
"suffix3",
"suffix2",
"upper",
"title",
"digit",
"pos",
"pos2",
"text_dense_features",
],
["low", "title", "upper", "pos", "pos2"],
]
}
crf_extractor = crf_entity_extractor(component_config)
text = "Rasa is a company in Berlin"
message = Message(data={TEXT: text})
message.set(SPACY_DOCS[TEXT], spacy_nlp(text))
spacy_tokenizer.process([message])
spacy_featurizer.process([message])
text_data = crf_extractor._convert_to_crf_tokens(message)
features = crf_extractor._crf_tokens_to_features(text_data)
assert "0:text_dense_features" in features[0]
dense_features, _ = message.get_dense_features(TEXT, [])
if dense_features:
dense_features = dense_features.features
for i in range(0, len(dense_features[0])):
assert (features[0]["0:text_dense_features"]["text_dense_features"][
str(i)] == dense_features[0][i])
def test_count_vector_featurizer_use_lemma(
spacy_nlp: Any,
sentence: Text,
sequence_features: List[List[int]],
sentence_features: List[List[int]],
use_lemma: bool,
create_featurizer: Callable[..., CountVectorsFeaturizerGraphComponent],
load_featurizer: Callable[..., CountVectorsFeaturizerGraphComponent],
spacy_tokenizer: SpacyTokenizerGraphComponent,
):
config = {"use_lemma": use_lemma, "OOV_words": ["drinks"], "OOV_token": "OOV"}
ftr = create_featurizer(config)
train_message = Message(data={TEXT: sentence})
train_message.set(SPACY_DOCS[TEXT], spacy_nlp(sentence))
test_message = Message(data={TEXT: sentence})
test_message.set(SPACY_DOCS[TEXT], spacy_nlp(sentence))
spacy_tokenizer.process([train_message])
spacy_tokenizer.process([test_message])
ftr.train(TrainingData([train_message]), spacy_nlp=SpacyModel(spacy_nlp, "en"))
ftr.process([test_message])
seq_vecs, sen_vecs = test_message.get_sparse_features(TEXT, [])
assert isinstance(seq_vecs.features, scipy.sparse.coo_matrix)
assert isinstance(sen_vecs.features, scipy.sparse.coo_matrix)
actual_seq_vecs = seq_vecs.features.toarray()
actual_sen_vecs = sen_vecs.features.toarray()
assert np.all(actual_seq_vecs[0] == sequence_features)
assert np.all(actual_sen_vecs[-1] == sentence_features)
loaded = load_featurizer(config)
assert loaded.OOV_words == ftr.OOV_words
def test_convert_training_examples(
spacy_nlp: Language,
text: Text,
intent: Optional[Text],
entities: Optional[List[Dict[Text, Any]]],
attributes: List[Text],
real_sparse_feature_sizes: Dict[Text, Dict[Text, List[int]]],
default_model_storage: ModelStorage,
default_execution_context: ExecutionContext,
):
message = Message(data={TEXT: text, INTENT: intent, ENTITIES: entities})
tokenizer = SpacyTokenizerGraphComponent.create(
SpacyTokenizerGraphComponent.get_default_config(),
default_model_storage,
Resource("tokenizer"),
default_execution_context,
)
count_vectors_featurizer = CountVectorsFeaturizerGraphComponent.create(
CountVectorsFeaturizerGraphComponent.get_default_config(),
default_model_storage,
Resource("count_featurizer"),
default_execution_context,
)
spacy_featurizer = SpacyFeaturizerGraphComponent.create(
SpacyFeaturizerGraphComponent.get_default_config(),
default_model_storage,
Resource("spacy_featurizer"),
default_execution_context,
)
message.set(SPACY_DOCS[TEXT], spacy_nlp(text))
training_data = TrainingData([message])
tokenizer.process_training_data(training_data)
count_vectors_featurizer.train(training_data)
count_vectors_featurizer.process_training_data(training_data)
spacy_featurizer.process_training_data(training_data)
entity_tag_spec = [
EntityTagSpec(
"entity",
{
0: "O",
1: "name",
2: "location"
},
{
"O": 0,
"name": 1,
"location": 2
},
3,
)
]
output, sparse_feature_sizes = model_data_utils.featurize_training_examples(
[message],
attributes=attributes,
entity_tag_specs=entity_tag_spec,
)
assert len(output) == 1
for attribute in attributes:
assert attribute in output[0]
for attribute in {INTENT, TEXT, ENTITIES} - set(attributes):
assert attribute not in output[0]
# we have sparse sentence, sparse sequence, dense sentence, and dense sequence
# features in the list
assert len(output[0][TEXT]) == 4
if INTENT in attributes:
# we will just have space sentence features
assert len(output[0][INTENT]) == 1
if ENTITIES in attributes:
# we will just have space sentence features
assert len(output[0][ENTITIES]) == len(entity_tag_spec)
# check that it calculates sparse_feature_sizes correctly
assert sparse_feature_sizes == real_sparse_feature_sizes
def spacy_tokenizer() -> SpacyTokenizerGraphComponent:
return SpacyTokenizerGraphComponent(
SpacyTokenizerGraphComponent.get_default_config()
)