def run(self, key, ctx: Context):
from sagas.nlu.ruleset_procs import list_words, cached_chunks, get_main_domains
from sagas.conf.conf import cf
logger.debug(f".. check against {key}")
if key not in ctx.indexes:
return False
# lemma = ctx.lemmas[key]
sents = ctx.sents
lang = ctx.lang
chunks = cached_chunks(sents, lang, cf.engine(lang))
doc = chunks['doc']
ents = get_entities(sents)
prt = ctx.indexes[key]
indexes = get_children_index(doc, prt)
idx_ent = {
el['index']: el['entity']
for el in get_entity_mapping(sents, doc, ents)
}
children_ents = [(idx, idx_ent[idx] if idx in idx_ent else '_')
for idx in indexes]
result = self.test_ent in {e[1] for e in children_ents}
if result:
ctx.add_result(self.name(), 'default', key, idx_ent)
return result
def vis_domains(sents, lang, domain=None, engine=None, all_subsents=False):
"""
>>> from sagas.kit.analysis_kit import vis_domains
>>> sents='What do you think about the war?'
>>> lang='en'
>>> domain='subj_domains' # 'verb_domains', 'aux_domains'
>>> vis_domains(sents, lang, domain)
:param sents:
:param lang:
:param domain:
:return:
"""
from sagas.nlu.ruleset_procs import cached_chunks, get_main_domains
from sagas.conf.conf import cf
engine = cf.engine(lang) if engine is None else engine
if domain is None:
domain, domains = get_main_domains(sents, lang, engine)
else:
chunks = cached_chunks(sents, lang, engine)
domains = chunks[domain]
if len(domains) == 0:
return None
if not all_subsents:
el = domains[0]
return vis_domains_data(domain, el)
else:
return [vis_domains_data(domain, el) for el in domains]
def vis_doc(sents, lang):
from sagas.nlu.ruleset_procs import cached_chunks
from sagas.nlu.uni_remote_viz import list_contrast, display_doc_deps
from sagas.conf.conf import cf
chunks = cached_chunks(sents, lang, cf.engine(lang))
return display_doc_deps(chunks['doc'], None)
def check_clause_sub(sents:Text, lang:Text, domain:Text, cla:Text,
rel:Text, cats:Union[Text, Set, List]):
"""
>>> from sagas.nlu.inspector_clauses import check_clause_sub
>>> check_clause_sub(sents, 'pt', 'verb_domains', 'obl', 'cop', {'be'})
:param sents:
:param lang:
:param domain:
:param cla:
:param rel:
:param cats:
:return:
"""
from sagas.nlu.uni_chunks import get_chunk
from sagas.nlu.ruleset_procs import cached_chunks
# cla = 'obl', rel = 'cop', cat='be'
chunks = cached_chunks(sents, lang, cf.engine(lang))
result = get_chunk(chunks, domain, cla,
lambda w: {'rel': w.dependency_relation,
'pos': w.upos.lower(),
'word': f"{w.text}/{w.lemma}"})
word = next((w['word'] for w in result if w['rel'] == rel), None)
if word:
if isinstance(cats, str):
return check_chain(cats, word, '*', lang)
else:
return any([check_chain(cat, word, '*', lang) for cat in cats])
return False
def run(self, key, ctx: Context):
from jsonpath_ng import jsonpath, parse
from sagas.nlu.inspector_wordnet import predicate
from sagas.nlu.ruleset_procs import cached_chunks
lang = ctx.lang
domain_name = f"{self.domains}_domains" # like: 'verb_domains'
parsers = [parse(normal_path(expr)) for expr in self.paths]
results = []
engine = cf.engine(lang) if self.engine is None else self.engine
chunks = cached_chunks(ctx.sents, lang, engine)
for chunk in chunks[domain_name]:
json_data = chunk
# for expr in exprs:
for idx, parser in enumerate(parsers):
# print([(match.value, str(match.full_path)) for match in parser.find(json_data)])
word = '/'.join(
[match.value for match in parser.find(json_data)])
pred_r = predicate(self.kind, word, lang, self.pos)
# tc.emp('yellow' if not pred_r else 'green', f".. {word} is {self.kind}: {pred_r}")
logger.debug(f".. {word} is {self.kind}: {pred_r}")
results.append(pred_r)
if pred_r:
ctx.add_result(self.name(),
'default',
f"{self.domains}:{self.paths[idx]}", {
'category': self.kind,
'pos': self.pos,
**word_values(word, lang)
},
delivery_type='sentence')
logger.debug(f"{results}")
return any(results) if self.match_method == 'any' else all(results)
def test_class_matcher():
from sagas.nlu.uni_chunks import get_chunk
from pampy import match, _
from dataclasses import dataclass
@dataclass
class WordData:
index: int
rel: str
pos: str
word: str
# She denied being my mother
sents = 'Ela negou ser minha mãe.'
lang = 'pt'
domain = 'verb_domains'
chunks = cached_chunks(sents, lang, cf.engine(lang))
cla = 'obl'
ana = get_chunk(
chunks, domain, cla, lambda w: WordData(index=w.index,
rel=w.dependency_relation,
pos=w.upos.lower(),
word=f"{w.text}/{w.lemma}"))
t_rs = []
for word_data in ana:
r = match(word_data, WordData(_, _, 'aux',
_), lambda *arg: f"aux: {arg[2]}",
WordData(_, 'obl', 'noun', _), lambda *arg: arg, _, None)
t_rs.append(r)
assert t_rs == ['aux: ser/ser', None, (5, 'mãe/mãe')]
def get_domains(self, ctx:Context):
from sagas.nlu.ruleset_procs import cached_chunks
from sagas.conf.conf import cf
# dn = lambda domain: f'{domain}_domains' if domain != 'predicts' else domain
chunks = cached_chunks(ctx.sents, ctx.lang, cf.engine(ctx.lang))
domains = chunks[ctx.domain_type]
return domains
def root_tree(self):
from sagas.nlu.nlu_tools import vis_tree
from sagas.nlu.ruleset_procs import cached_chunks
chunks = cached_chunks(self.meta.sents,
source=self.meta.lang,
engine=self.meta.engine)
tc.emp('cyan', f"✁ root tree {self.meta.engine} {'-' * 25}")
ds = chunks['root_domains'][0]
vis_tree(ds, self.meta.lang, trans=cf.is_enabled('trans_tree'))
def is_noun_desc(ctx: Context, domain):
sents, lang = ctx.sents, ctx.lang
chunks = cached_chunks(sents, lang, cf.engine(lang))
domains = chunks[domain]
domain = domains[0]
comps = [k for k, v in domain.items() if isinstance(v, list)]
logger.debug(f'.. {comps}')
return domain['upos']=='NOUN' and \
all(c for c in comps if c.endswith('mod') or c in ('punct'))
def run(self, key, ctx:Context):
from sagas.nlu.ruleset_procs import list_words, cached_chunks, get_main_domains
from sagas.conf.conf import cf
chunks = cached_chunks(ctx.sents, ctx.lang, cf.engine(ctx.lang))
index = next((x[1] for x in ctx.domains if x[0] == self.part), -1)
if index!=-1:
rs=self.collect_children(chunks, ctx.lang, index+1)
if rs:
ctx.add_result(self.name(), 'default', self.part, rs)
return True
def analyse_domains(self, sents, lang, engine=None, domain=None):
from sagas.nlu.ruleset_procs import cached_chunks, get_main_domains
from sagas.conf.conf import cf
engine = cf.engine(lang) if engine is None else engine
if domain is None:
domain, domains = get_main_domains(sents, lang, engine)
else:
chunks = cached_chunks(sents, lang, engine)
domains = chunks[domain]
return domains
def get_feats_map(sents, lang, domain, path):
domain_name = f'{domain}_domains' if domain != 'predicts' else domain
from sagas.nlu.ruleset_procs import cached_chunks
chunks = cached_chunks(sents, lang, cf.engine(lang))
parser = parse(feats_for_path(path))
results = []
for chunk in chunks[domain_name]:
vals = [match.value for match in parser.find(chunk)]
if vals:
results.extend([feats_map(val) for val in vals])
return results
def doc(self, sents, lang='en', engine='stanza'):
"""
$ python -m sagas.nlu.anal doc 'Nosotros estamos en la escuela.' es stanza
$ python -m sagas.nlu.anal doc '우리는 사람들을 이해하고 싶어요.' ko
:param sents:
:param lang:
:param engine:
:return:
"""
chunks = cached_chunks(sents, source=lang, engine=engine)
return chunks['doc'].as_json
def get_source(sents, lang, domain_type=None)-> Observable:
from sagas.nlu.ruleset_procs import cached_chunks, get_main_domains
from sagas.conf.conf import cf
import rx
engine=cf.engine(lang)
if domain_type is None:
domain_type, domains=get_main_domains(sents, lang, engine)
else:
chunks = cached_chunks(sents, lang, engine)
domains = chunks[domain_type]
table_rs = []
for ds in domains:
flat_table(ds, '', table_rs)
return rx.of(*table_rs)
def ex_chunk(key: Text, cnt: Text, comp: Text, ctx: cla_meta_intf, clo):
from sagas.nlu.uni_chunks import get_chunk
from sagas.nlu.ruleset_procs import list_words, cached_chunks
from sagas.conf.conf import cf
# get_chunk(f'verb_domains', 'xcomp/obj', lambda w: w.upos)
chunks = cached_chunks(ctx.sents, ctx.lang, cf.engine(ctx.lang))
domain, path = key.split(':')
result = get_chunk(chunks,
f'{domain}_domains' if domain != 'predicts' else domain,
path,
clo=clo)
logger.debug(f"extract chunk: {domain}, {path}, {result}")
if len(result) > 0:
ctx.add_result(extractor, comp, key, result)
return True
return False
def run(self, key: Text, ctx: Context) -> bool:
from sagas.nlu.predicts import predicate
from sagas.nlu.operators import ud
final_rs = []
sents, lang = ctx.sents, ctx.lang
chunks = cached_chunks(sents, lang, cf.engine(lang))
domains = chunks[self.domain]
for el in domains:
# logger.debug(f"`{el['lemma']}` >> *{el['dc']['lemma']}*")
# r1 = predicate(el, ud.__text('will') >> [ud.nsubj('what'), ud.dc_cat('weather')], lang)
rs: List[Any] = predicate(el, self.checker, lang)
# r2=predicate(el, ud.__cat('be') >> [ud.nsubj('what'), ud.dc_cat('animal/object')], lang)
result = all([r[0] for r in rs])
final_rs.append(result)
logger.debug(f'{[r[0] for r in rs]}, {result}')
return any(final_rs)
def has_pos_in_part(part: Text, pos: Union[list, str]):
from sagas.nlu.uni_chunks import get_chunk
from sagas.nlu.ruleset_procs import list_words, cached_chunks
from sagas.conf.conf import cf
chunks = cached_chunks(ctx.sents, ctx.lang, cf.engine(ctx.lang))
domain, path = part.split(':')
result = get_chunk(
chunks,
f'{domain}_domains' if domain != 'predicts' else domain, path,
lambda w: (w.upos.lower(), w.text))
if isinstance(pos, str):
pos = [pos]
succ = False
for el in result:
if el[0] in pos:
ctx.add_result(self.name(), f'has_pos_{"_or_".join(pos)}',
part, el[1])
succ = True
return succ
def chunks(self, sents, lang, domain, path):
"""
$ python -m sagas.nlu.extractor_cli chunks 'I like to eat sweet corn.' en verb 'xcomp/obj'
$ python -m sagas.nlu.extractor_cli chunks 'A casa tem dezenove quartos.' pt verb 'obj'
☇ [('dezenove', 'num'), ('quartos', 'noun')]
:param sents:
:param lang:
:param domain:
:param path:
:return:
"""
from sagas.nlu.uni_chunks import get_chunk
from sagas.nlu.ruleset_procs import list_words, cached_chunks
from sagas.conf.conf import cf
# get_chunk(f'verb_domains', 'xcomp/obj', lambda w: w.upos)
# get_chunk(f'domain_domains', path, lambda w: w.upos)
chunks = cached_chunks(sents, lang, cf.engine(lang))
result = get_chunk(
chunks, f'{domain}_domains' if domain != 'predicts' else domain,
path, lambda w: (w.text, w.upos.lower()))
print(result)
def test_chunk_matcher():
from sagas.nlu.uni_chunks import get_chunk
from pampy import match, _
# She denied being my mother
sents = 'Ela negou ser minha mãe.'
lang = 'pt'
domain = 'verb_domains'
chunks = cached_chunks(sents, lang, cf.engine(lang))
cla = 'obl'
raw = get_chunk(
chunks, domain, cla, lambda w: {
'rel': w.dependency_relation,
'pos': w.upos.lower(),
'word': f"{w.text}/{w.lemma}"
})
rs = {e['rel']: e for e in raw}
r = match(rs, {
'cop': {
'word': _
},
'obl': {
'pos': 'noun',
'word': _
}
}, lambda *arg: arg, _, "anything else")
assert r == ('ser/ser', 'mãe/mãe')
r = match(rs, {
_: {
'pos': 'aux'
},
'obl': {
'pos': 'noun',
'word': _
}
}, lambda *arg: arg, _, "anything else")
assert r == ('cop', 'mãe/mãe')
def domains_as_tree(sents, lang, engine='stanza', domain='root_domains'):
chunks = cached_chunks(sents, source=lang, engine=engine)
root = chunks[domain]
ds = treeing(root[0])
f = importer.import_(ds)
return f
def request_intents(sents, lang, domain):
chunks = cached_chunks(sents, lang, cf.engine(lang))
domains = chunks[domain]
return get_intents(domains, lang)
