def test_get_main_verbs_of_sent(spacy_doc):
expected = [['going'], ['love', 'love'], ['damaged'], ['Thank']]
observed = [
[tok.text for tok in utils.get_main_verbs_of_sent(sent)]
for sent in spacy_doc.sents
]
for obs, exp in zip(observed, expected):
assert obs == exp
def test_get_objects_of_verb(spacy_doc):
expected = [[], ["Python"], ["incompatibilities"], [], ["God"]]
main_verbs = [
tok for sent in spacy_doc.sents
for tok in utils.get_main_verbs_of_sent(sent)
]
observed = [[tok.text for tok in utils.get_objects_of_verb(main_verb)]
for main_verb in main_verbs]
for obs, exp in zip(observed, expected):
assert obs == exp
def test_get_subjects_of_verb(spacy_doc):
expected = [["tests"], ["I"], ["I"], ["programmers"], []]
main_verbs = [
tok for sent in spacy_doc.sents
for tok in utils.get_main_verbs_of_sent(sent)
]
observed = [[tok.text for tok in utils.get_subjects_of_verb(main_verb)]
for main_verb in main_verbs]
for obs, exp in zip(observed, expected):
assert obs == exp
def __call__(self, text):
""""""
doc = self.nlp(text)
svo = []
for sent in doc.sents:
chunks = ''
# Return the main (non-auxiliary) verbs in a sentence.
verbs = utils.get_main_verbs_of_sent(sent)
for verb in verbs:
# Filter negations
negation = "".join([
t.text for t in sent if t.dep_ == 'neg' if t.head == verb
])
# Return all subjects of a verb according to the dependency parse.
subj = utils.get_subjects_of_verb(verb)
# Return all objects of a verb according to the dependency parse,
# including open clausal
# Get noun chunks of verb
obj = utils.get_objects_of_verb(verb)
# Return document indexes spanning all (adjacent) tokens around a verb
# that are auxiliary verbs or negations.
start, end = utils.get_span_for_verb_auxiliaries(verb)
aux = doc[start:end + 1].as_doc().text
for o in obj:
for nc in sent.noun_chunks:
# st.write('VERB', verb.text,
# 'OBJ HEAD:', o.head.text, 'OBJ:', o.text,
# 'NC HEAD:', nc.root.head.text, 'NC:', nc.text,
# 'NC ANC:', [a.text for a in nc.root.head.ancestors] )
if o.text in nc.text.split():
chunks += f' {nc.text}'
# st.write('CHUNK:', nc.text)
# obj = " ".join([f"{nc.text}" for nc in sent.noun_chunks if obj.text in nc.text])
snippet = f'{" ".join([s.text for s in subj])} {negation} {aux} {chunks}'
svo.append(snippet)
return '. '.join(svo)
def test_get_main_verbs_of_sent(spacy_doc):
expected = [["going"], ["love", "love"], ["damaged"], ["Thank"]]
observed = [[tok.text for tok in utils.get_main_verbs_of_sent(sent)]
for sent in spacy_doc.sents]
for obs, exp in zip(observed, expected):
assert obs == exp
# """Return the main (non-auxiliary) verbs in a sentence."""
# return [tok for tok in sent
# if tok.pos == VERB and tok.dep_ not in constants.AUX_DEPS]
# File: d:\miniconda3\envs\nlp\lib\site-packages\textacy\spacier\utils.py
# Type: function
toy_sentence = 'Shivangi is an engineer'
doc = nlp(toy_sentence)
"""What are the entities in this sentence?"""
displacy.render(doc, style='ent', jupyter=True)
# Let's find out the main verb in this sentence:
verbs = spacy_utils.get_main_verbs_of_sent(doc)
print(verbs)
# And what are nominal subjects of this verb?
for verb in verbs:
print(verb, spacy_utils.get_subjects_of_verb(verb))
"""*You will notice that this has a reasonable overlap with the noun phrases which we pulled from our part-of-speech tagging but can be different as well.*"""
[(token, token.tag_) for token in doc]
"""Tip: As an exercise, extend this approach to at least add Who, Where and When questions as practice.
## Level Up: Question and Answer
