def test_persist_load_for_finetuning(tmp_path: Path):
patterns = [
{"pattern": "[0-9]+", "name": "number", "usage": "intent"},
{"pattern": "\\bhey*", "name": "hello", "usage": "intent"},
{"pattern": "[0-1]+", "name": "binary", "usage": "intent"},
]
featurizer = RegexFeaturizer.create(
{"number_additional_patterns": 5}, RasaNLUModelConfig()
)
sentence = "hey how are you today 19.12.2019 ?"
message = Message(data={TEXT: sentence})
message.set(RESPONSE, sentence)
message.set(INTENT, "intent")
WhitespaceTokenizer().train(TrainingData([message]))
featurizer.train(
TrainingData([message], regex_features=patterns), RasaNLUModelConfig()
)
persist_value = featurizer.persist("ftr", str(tmp_path))
# Test all artifacts stored as part of persist
assert persist_value["file"] == "ftr"
assert (tmp_path / "ftr.patterns.pkl").exists()
assert (tmp_path / "ftr.vocabulary_stats.pkl").exists()
assert featurizer.vocabulary_stats == {
"max_number_patterns": 8,
"pattern_slots_filled": 3,
}
loaded_featurizer = RegexFeaturizer.load(
meta={"number_additional_patterns": 5, "file": persist_value["file"],},
should_finetune=True,
model_dir=str(tmp_path),
)
# Test component loaded in finetune mode and also with
# same patterns as before and vocabulary statistics
assert loaded_featurizer.known_patterns == featurizer.known_patterns
assert loaded_featurizer.finetune_mode
assert loaded_featurizer.pattern_vocabulary_stats == featurizer.vocabulary_stats
new_lookups = [{"name": "plates", "elements": "data/test/lookup_tables/plates.txt"}]
training_data = TrainingData()
training_data.lookup_tables = new_lookups
loaded_featurizer.train(training_data)
# Test merging of a new pattern to an already trained component.
assert len(loaded_featurizer.known_patterns) == 4
assert loaded_featurizer.vocabulary_stats == {
"max_number_patterns": 8,
"pattern_slots_filled": 4,
}
def test_regex_featurizer_train():
patterns = [
{"pattern": "[0-9]+", "name": "number", "usage": "intent"},
{"pattern": "\\bhey*", "name": "hello", "usage": "intent"},
{"pattern": "[0-1]+", "name": "binary", "usage": "intent"},
]
featurizer = RegexFeaturizer.create(
{"number_additional_patterns": 0}, RasaNLUModelConfig()
)
sentence = "hey how are you today 19.12.2019 ?"
message = Message(data={TEXT: sentence})
message.set(RESPONSE, sentence)
message.set(INTENT, "intent")
WhitespaceTokenizer().train(TrainingData([message]))
featurizer.train(
TrainingData([message], regex_features=patterns), RasaNLUModelConfig()
)
expected = np.array([0, 1, 0])
expected_cls = np.array([1, 1, 1])
seq_vecs, sen_vec = message.get_sparse_features(TEXT, [])
if seq_vecs:
seq_vecs = seq_vecs.features
if sen_vec:
sen_vec = sen_vec.features
assert (6, 3) == seq_vecs.shape
assert (1, 3) == sen_vec.shape
assert np.all(seq_vecs.toarray()[0] == expected)
assert np.all(sen_vec.toarray()[-1] == expected_cls)
seq_vecs, sen_vec = message.get_sparse_features(RESPONSE, [])
if seq_vecs:
seq_vecs = seq_vecs.features
if sen_vec:
sen_vec = sen_vec.features
assert (6, 3) == seq_vecs.shape
assert (1, 3) == sen_vec.shape
assert np.all(seq_vecs.toarray()[0] == expected)
assert np.all(sen_vec.toarray()[-1] == expected_cls)
seq_vecs, sen_vec = message.get_sparse_features(INTENT, [])
if seq_vecs:
seq_vecs = seq_vecs.features
if sen_vec:
sen_vec = sen_vec.features
assert seq_vecs is None
assert sen_vec is None
def test_regex_featurizer_train():
patterns = [
{
"pattern": "[0-9]+",
"name": "number",
"usage": "intent"
},
{
"pattern": "\\bhey*",
"name": "hello",
"usage": "intent"
},
{
"pattern": "[0-1]+",
"name": "binary",
"usage": "intent"
},
]
featurizer = RegexFeaturizer.create({}, RasaNLUModelConfig())
sentence = "hey how are you today 19.12.2019 ?"
message = Message(sentence)
message.set(RESPONSE_ATTRIBUTE, sentence)
message.set(INTENT_ATTRIBUTE, "intent")
WhitespaceTokenizer().train(TrainingData([message]))
featurizer.train(TrainingData([message], regex_features=patterns),
RasaNLUModelConfig())
expected = np.array([0, 1, 0])
expected_cls = np.array([1, 1, 1])
vecs = message.get(SPARSE_FEATURE_NAMES[TEXT_ATTRIBUTE])
assert (7, 3) == vecs.shape
assert np.all(vecs.toarray()[0] == expected)
assert np.all(vecs.toarray()[-1] == expected_cls)
vecs = message.get(SPARSE_FEATURE_NAMES[RESPONSE_ATTRIBUTE])
assert (7, 3) == vecs.shape
assert np.all(vecs.toarray()[0] == expected)
assert np.all(vecs.toarray()[-1] == expected_cls)
vecs = message.get(SPARSE_FEATURE_NAMES[INTENT_ATTRIBUTE])
assert vecs is None
def test_incremental_train_featurization(tmp_path: Path):
patterns = [
{
"pattern": "[0-9]+",
"name": "number",
"usage": "intent"
},
{
"pattern": "\\bhey*",
"name": "hello",
"usage": "intent"
},
{
"pattern": "[0-1]+",
"name": "binary",
"usage": "intent"
},
]
featurizer = RegexFeaturizer.create({"number_additional_patterns": 5},
RasaNLUModelConfig())
sentence = "hey how are you today 19.12.2019 ?"
message = Message(data={TEXT: sentence})
message.set(RESPONSE, sentence)
message.set(INTENT, "intent")
WhitespaceTokenizer().train(TrainingData([message]))
featurizer.train(TrainingData([message], regex_features=patterns),
RasaNLUModelConfig())
# Test featurization of message
expected = np.array([0, 1, 0, 0, 0, 0, 0, 0])
expected_cls = np.array([1, 1, 1, 0, 0, 0, 0, 0])
seq_vecs, sen_vec = message.get_sparse_features(TEXT, [])
if seq_vecs:
seq_vecs = seq_vecs.features
if sen_vec:
sen_vec = sen_vec.features
assert (6, 8) == seq_vecs.shape
assert (1, 8) == sen_vec.shape
assert np.all(seq_vecs.toarray()[0] == expected)
assert np.all(sen_vec.toarray()[-1] == expected_cls)
persist_value = featurizer.persist("ftr", str(tmp_path))
loaded_featurizer = RegexFeaturizer.load(
meta={
"number_additional_patterns": 5,
"file": persist_value["file"],
},
should_finetune=True,
model_dir=str(tmp_path),
)
new_patterns = [
{
"pattern": "\\btoday*",
"name": "day",
"usage": "intent"
},
{
"pattern": "\\bhey+",
"name": "hello",
"usage": "intent"
},
]
message = Message(data={TEXT: sentence})
message.set(RESPONSE, sentence)
message.set(INTENT, "intent")
WhitespaceTokenizer().train(TrainingData([message]))
loaded_featurizer.train(
TrainingData([message], regex_features=patterns + new_patterns),
RasaNLUModelConfig(),
)
# Test featurization of message, this time for the extra pattern as well.
expected_token_1 = np.array([0, 1, 0, 0, 0, 0, 0, 0])
expected_token_2 = np.array([0, 0, 0, 1, 0, 0, 0, 0])
expected_cls = np.array([1, 1, 1, 1, 0, 0, 0, 0])
seq_vecs, sen_vec = message.get_sparse_features(TEXT, [])
if seq_vecs:
seq_vecs = seq_vecs.features
if sen_vec:
sen_vec = sen_vec.features
assert (6, 8) == seq_vecs.shape
assert (1, 8) == sen_vec.shape
assert np.all(seq_vecs.toarray()[0] == expected_token_1)
assert np.all(seq_vecs.toarray()[-2] == expected_token_2)
assert np.all(sen_vec.toarray()[-1] == expected_cls)
# we also modified a pattern, check if that is correctly modified
pattern_to_check = [
pattern for pattern in loaded_featurizer.known_patterns
if pattern["name"] == "hello"
]
assert pattern_to_check == [new_patterns[1]]