def test_issue1915():
cfg = {"hidden_depth": 2} # should error out
nlp = Language()
ner = nlp.add_pipe("ner")
ner.add_label("answer")
with pytest.raises(ValueError):
nlp.initialize(**cfg)
def test_implicit_labels():
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
assert len(spancat.labels) == 0
train_examples = make_examples(nlp)
nlp.initialize(get_examples=lambda: train_examples)
assert spancat.labels == ("PERSON", "LOC")
def test_implicit_label():
nlp = Language()
nlp.add_pipe("tagger")
train_examples = []
for t in TRAIN_DATA:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
nlp.initialize(get_examples=lambda: train_examples)
def nlp():
nlp = Language(Vocab())
textcat = nlp.add_pipe("textcat")
for label in ("POSITIVE", "NEGATIVE"):
textcat.add_label(label)
nlp.initialize()
return nlp
def test_explicit_labels():
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
assert len(spancat.labels) == 0
spancat.add_label("PERSON")
spancat.add_label("LOC")
nlp.initialize()
assert spancat.labels == ("PERSON", "LOC")
def test_error_with_multi_labels():
nlp = Language()
nlp.add_pipe("textcat")
train_examples = []
for text, annotations in TRAIN_DATA_MULTI_LABEL:
train_examples.append(Example.from_dict(nlp.make_doc(text), annotations))
with pytest.raises(ValueError):
nlp.initialize(get_examples=lambda: train_examples)
def test_ner_labels_added_implicitly_on_greedy_parse():
nlp = Language()
ner = nlp.add_pipe("beam_ner")
for label in ["A", "B", "C"]:
ner.add_label(label)
nlp.initialize()
doc = Doc(nlp.vocab, words=["hello", "world"], ents=["B-D", "O"])
ner.greedy_parse([doc])
assert "D" in ner.labels
def test_implicit_labels():
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
assert len(spancat.labels) == 0
train_examples = []
for t in TRAIN_DATA:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
nlp.initialize(get_examples=lambda: train_examples)
assert spancat.labels == ("PERSON", "LOC")
def test_no_resize():
nlp = Language()
morphologizer = nlp.add_pipe("morphologizer")
morphologizer.add_label("POS" + Morphology.FIELD_SEP + "NOUN")
morphologizer.add_label("POS" + Morphology.FIELD_SEP + "VERB")
nlp.initialize()
# this throws an error because the morphologizer can't be resized after initialization
with pytest.raises(ValueError):
morphologizer.add_label("POS" + Morphology.FIELD_SEP + "ADJ")
def test_tagger_initialize_tag_map():
"""Test that Tagger.initialize() without gold tuples does not clobber
the tag map."""
nlp = Language()
tagger = nlp.add_pipe("tagger")
orig_tag_count = len(tagger.labels)
tagger.add_label("A")
nlp.initialize()
assert orig_tag_count + 1 == len(nlp.get_pipe("tagger").labels)
def tagger():
nlp = Language()
tagger = nlp.add_pipe("tagger")
# need to add model for two reasons:
# 1. no model leads to error in serialization,
# 2. the affected line is the one for model serialization
tagger.add_label("A")
nlp.initialize()
return tagger
def test_no_resize(name):
nlp = Language()
textcat = nlp.add_pipe(name)
textcat.add_label("POSITIVE")
textcat.add_label("NEGATIVE")
nlp.initialize()
assert textcat.model.get_dim("nO") >= 2
# this throws an error because the textcat can't be resized after initialization
with pytest.raises(ValueError):
textcat.add_label("NEUTRAL")
def test_ner_labels_added_implicitly_on_predict():
nlp = Language()
ner = nlp.add_pipe("ner")
for label in ["A", "B", "C"]:
ner.add_label(label)
nlp.initialize()
doc = Doc(nlp.vocab, words=["hello", "world"], ents=["B-D", "O"])
ner(doc)
assert [t.ent_type_ for t in doc] == ["D", ""]
assert "D" in ner.labels
def test_ner_labels_added_implicitly_on_update():
nlp = Language()
ner = nlp.add_pipe("ner")
for label in ["A", "B", "C"]:
ner.add_label(label)
nlp.initialize()
doc = Doc(nlp.vocab, words=["hello", "world"], ents=["B-D", "O"])
example = Example(nlp.make_doc(doc.text), doc)
assert "D" not in ner.labels
nlp.update([example])
assert "D" in ner.labels
def test_no_resize():
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
spancat.add_label("Thing")
spancat.add_label("Phrase")
assert spancat.labels == ("Thing", "Phrase")
nlp.initialize()
assert spancat.model.get_dim("nO") == 2
# this throws an error because the spancat can't be resized after initialization
with pytest.raises(ValueError):
spancat.add_label("Stuff")
def test_issue2564():
"""Test the tagger sets has_annotation("TAG") correctly when used via Language.pipe."""
nlp = Language()
tagger = nlp.add_pipe("tagger")
tagger.add_label("A")
nlp.initialize()
doc = nlp("hello world")
assert doc.has_annotation("TAG")
docs = nlp.pipe(["hello", "world"])
piped_doc = next(docs)
assert piped_doc.has_annotation("TAG")
def test_no_resize():
nlp = Language()
tagger = nlp.add_pipe("tagger")
tagger.add_label("N")
tagger.add_label("V")
assert tagger.labels == ("N", "V")
nlp.initialize()
assert tagger.model.get_dim("nO") == 2
# this throws an error because the tagger can't be resized after initialization
with pytest.raises(ValueError):
tagger.add_label("J")
def test_no_resize(name, textcat_config):
"""The old textcat architectures weren't resizable"""
nlp = Language()
pipe_config = {"model": textcat_config}
textcat = nlp.add_pipe(name, config=pipe_config)
textcat.add_label("POSITIVE")
textcat.add_label("NEGATIVE")
nlp.initialize()
assert textcat.model.maybe_get_dim("nO") in [2, None]
# this throws an error because the textcat can't be resized after initialization
with pytest.raises(ValueError):
textcat.add_label("NEUTRAL")
def test_label_types(name):
nlp = Language()
textcat = nlp.add_pipe(name)
textcat.add_label("answer")
with pytest.raises(ValueError):
textcat.add_label(9)
# textcat requires at least two labels
if name == "textcat":
with pytest.raises(ValueError):
nlp.initialize()
else:
nlp.initialize()
def test_issue9904():
nlp = Language()
textcat = nlp.add_pipe("textcat")
get_examples = make_get_examples_single_label(nlp)
nlp.initialize(get_examples)
examples = get_examples()
scores = textcat.predict([eg.predicted for eg in examples])
loss = textcat.get_loss(examples, scores)[0]
loss_double_bs = textcat.get_loss(examples * 2, scores.repeat(2, axis=0))[0]
assert loss == pytest.approx(loss_double_bs)
def test_resize(name, textcat_config):
"""The new textcat architectures are resizable"""
nlp = Language()
pipe_config = {"model": textcat_config}
textcat = nlp.add_pipe(name, config=pipe_config)
textcat.add_label("POSITIVE")
textcat.add_label("NEGATIVE")
assert textcat.model.maybe_get_dim("nO") in [2, None]
nlp.initialize()
assert textcat.model.maybe_get_dim("nO") in [2, None]
textcat.add_label("NEUTRAL")
assert textcat.model.maybe_get_dim("nO") in [3, None]
def test_doc_gc():
# If the Doc object is garbage collected, the spans won't be functional afterwards
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
spancat.add_label("PERSON")
nlp.initialize()
texts = ["Just a sentence.", "I like London and Berlin", "I like Berlin", "I eat ham."]
all_spans = [doc.spans for doc in nlp.pipe(texts)]
for text, spangroups in zip(texts, all_spans):
assert isinstance(spangroups, SpanGroups)
for key, spangroup in spangroups.items():
assert isinstance(spangroup, SpanGroup)
assert len(spangroup) > 0
with pytest.raises(RuntimeError):
span = spangroup[0]
def entity_linker():
nlp = Language()
def create_kb(vocab):
kb = KnowledgeBase(vocab, entity_vector_length=1)
kb.add_entity("test", 0.0, zeros((1, 1), dtype="f"))
return kb
entity_linker = nlp.add_pipe("entity_linker")
entity_linker.set_kb(create_kb)
# need to add model for two reasons:
# 1. no model leads to error in serialization,
# 2. the affected line is the one for model serialization
nlp.initialize()
return entity_linker
def test_initialize_examples():
nlp = Language()
lemmatizer = nlp.add_pipe("trainable_lemmatizer")
train_examples = []
for t in TRAIN_DATA:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
# you shouldn't really call this more than once, but for testing it should be fine
nlp.initialize(get_examples=lambda: train_examples)
with pytest.raises(TypeError):
nlp.initialize(get_examples=lambda: None)
with pytest.raises(TypeError):
nlp.initialize(get_examples=lambda: train_examples[0])
with pytest.raises(TypeError):
nlp.initialize(get_examples=lambda: [])
with pytest.raises(TypeError):
nlp.initialize(get_examples=train_examples)
def test_initialize_from_labels():
nlp = Language()
lemmatizer = nlp.add_pipe("trainable_lemmatizer")
lemmatizer.min_tree_freq = 1
train_examples = []
for t in TRAIN_DATA:
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
nlp.initialize(get_examples=lambda: train_examples)
nlp2 = Language()
lemmatizer2 = nlp2.add_pipe("trainable_lemmatizer")
lemmatizer2.initialize(
get_examples=lambda: train_examples,
labels=lemmatizer.label_data,
)
assert lemmatizer2.tree2label == {1: 0, 3: 1, 4: 2, 6: 3}
def test_simple_train():
nlp = Language()
textcat = nlp.add_pipe("textcat")
textcat.add_label("answer")
nlp.initialize()
for i in range(5):
for text, answer in [
("aaaa", 1.0),
("bbbb", 0),
("aa", 1.0),
("bbbbbbbbb", 0.0),
("aaaaaa", 1),
]:
nlp.update((text, {"cats": {"answer": answer}}))
doc = nlp("aaa")
assert "answer" in doc.cats
assert doc.cats["answer"] >= 0.5
def test_language_source_and_vectors(nlp2):
nlp = Language(Vocab())
textcat = nlp.add_pipe("textcat")
for label in ("POSITIVE", "NEGATIVE"):
textcat.add_label(label)
nlp.initialize()
long_string = "thisisalongstring"
assert long_string not in nlp.vocab.strings
assert long_string not in nlp2.vocab.strings
nlp.vocab.strings.add(long_string)
assert nlp.vocab.vectors.to_bytes() != nlp2.vocab.vectors.to_bytes()
vectors_bytes = nlp.vocab.vectors.to_bytes()
with pytest.warns(UserWarning):
nlp2.add_pipe("textcat", name="textcat2", source=nlp)
# strings should be added
assert long_string in nlp2.vocab.strings
# vectors should remain unmodified
assert nlp.vocab.vectors.to_bytes() == vectors_bytes
def test_simple_train():
fix_random_seed(0)
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
get_examples = make_get_examples(nlp)
nlp.initialize(get_examples)
sgd = nlp.create_optimizer()
assert len(spancat.labels) != 0
for i in range(40):
losses = {}
nlp.update(list(get_examples()), losses=losses, drop=0.1, sgd=sgd)
doc = nlp("I like London and Berlin.")
assert doc.spans[spancat.key] == doc.spans[SPAN_KEY]
assert len(doc.spans[spancat.key]) == 2
assert doc.spans[spancat.key][0].text == "London"
scores = nlp.evaluate(get_examples())
assert f"spans_{SPAN_KEY}_f" in scores
assert scores[f"spans_{SPAN_KEY}_f"] == 1.0
def test_set_candidates():
nlp = Language()
spancat = nlp.add_pipe("spancat", config={"spans_key": SPAN_KEY})
train_examples = make_examples(nlp)
nlp.initialize(get_examples=lambda: train_examples)
texts = [
"Just a sentence.",
"I like London and Berlin",
"I like Berlin",
"I eat ham.",
]
docs = [nlp(text) for text in texts]
spancat.set_candidates(docs)
assert len(docs) == len(texts)
assert type(docs[0].spans["candidates"]) == SpanGroup
assert len(docs[0].spans["candidates"]) == 9
assert docs[0].spans["candidates"][0].text == "Just"
assert docs[0].spans["candidates"][4].text == "Just a"
def test_initialize_examples(name, get_examples, train_data):
nlp = Language()
textcat = nlp.add_pipe(name)
for text, annotations in train_data:
for label, value in annotations.get("cats").items():
textcat.add_label(label)
# you shouldn't really call this more than once, but for testing it should be fine
nlp.initialize()
nlp.initialize(get_examples=get_examples(nlp))
with pytest.raises(TypeError):
nlp.initialize(get_examples=lambda: None)
with pytest.raises(TypeError):
nlp.initialize(get_examples=get_examples())