def hertz_units(attr):
hertz_units = ["mhz", "khz"]
keywords = [
"product",
"gain",
"gain",
"unity",
"bandwidth",
"gbp",
"gbw",
"gbwp",
]
filter_keywords = ["-3 db", "maximum", "minimum", "impedance"]
related_ngrams = set(get_right_ngrams(attr, n_max=1, lower=True))
related_ngrams.update(get_row_ngrams(attr, n_max=1, spread=[-2, 2], lower=True))
cell_ngrams = set(get_cell_ngrams(attr, n_max=1, lower=True))
if "f" in cell_ngrams and "=" in cell_ngrams:
return False
if attr.get_span().strip() == "0":
return False
if overlap(filter_keywords, get_row_ngrams(attr, n_max=1, lower=True)):
return False
if overlap(hertz_units, related_ngrams) and overlap(keywords, related_ngrams):
return True
return False
def get_word_feats(span):
attrib = "words"
if span.stable_id not in unary_word_feats:
unary_word_feats[span.stable_id] = set()
for ngram in tokens_to_ngrams(span.get_attrib_tokens(attrib),
n_min=1,
n_max=2):
feature = f"CONTAINS_{attrib.upper()}_[{ngram}]"
unary_word_feats.add(feature)
for ngram in get_left_ngrams(
span,
window=settings["featurization"]["content"]["word_feature"]
["window"],
n_max=2,
attrib=attrib,
):
feature = f"LEFT_{attrib.upper()}_[{ngram}]"
unary_word_feats.add(feature)
for ngram in get_right_ngrams(
span,
window=settings["featurization"]["content"]["word_feature"]
["window"],
n_max=2,
attrib=attrib,
):
feature = f"RIGHT_{attrib.upper()}_[{ngram}]"
unary_word_feats.add(feature)
for f in unary_word_feats[span.stable_id]:
yield f
def _get_word_feats(span: SpanMention) -> Iterator[str]:
attrib = "words"
if span.stable_id not in unary_word_feats:
unary_word_feats[span.stable_id] = set()
for ngram in tokens_to_ngrams(span.get_attrib_tokens(attrib),
n_min=1,
n_max=2):
feature = f"CONTAINS_{attrib.upper()}_[{ngram}]"
unary_word_feats[span.stable_id].add(feature)
for ngram in get_left_ngrams(
span,
window=settings["featurization"]["textual"]["word_feature"]
["window"],
n_max=2,
attrib=attrib,
):
feature = f"LEFT_{attrib.upper()}_[{ngram}]"
unary_word_feats[span.stable_id].add(feature)
for ngram in get_right_ngrams(
span,
window=settings["featurization"]["textual"]["word_feature"]
["window"],
n_max=2,
attrib=attrib,
):
feature = f"RIGHT_{attrib.upper()}_[{ngram}]"
unary_word_feats[span.stable_id].add(feature)
unary_word_feats[span.stable_id].add((
f"SPAN_TYPE_["
f"{'IMPLICIT' if isinstance(span, ImplicitSpanMention) else 'EXPLICIT'}"
f"]"))
if span.get_span()[0].isupper():
unary_word_feats[span.stable_id].add("STARTS_WITH_CAPITAL")
unary_word_feats[span.stable_id].add(f"LENGTH_{span.get_num_words()}")
for f in unary_word_feats[span.stable_id]:
yield f
def current_units(attr):
# NOTE: These two symbols for mu are unique, not duplicates.
current_units = ["ma", "μa", "ua", "µa", "\uf06da"]
keywords = ["supply", "quiescent", "iq", "is", "idd", "icc"]
filter_keywords = ["offset", "bias", "logic", "shutdown"]
related_ngrams = set(get_right_ngrams(attr, n_max=1, lower=True))
related_ngrams.update(get_row_ngrams(attr, n_max=1, spread=[-5, 5], lower=True))
if attr.get_span().strip() == "0":
return False
if overlap(filter_keywords, get_row_ngrams(attr, n_max=1, lower=True)):
return False
if overlap(current_units, related_ngrams) and overlap(keywords, related_ngrams):
return True
return False
def LF_positive_number_right(c):
return (TRUE if any([
re.match(r"\d+", ngram) for ngram in get_right_ngrams(c[1], window=4)
]) else ABSTAIN)
def LF_to_right(c):
return TRUE if "to" in get_right_ngrams(c[1], window=2) else ABSTAIN
def LF_polarity_right_of_part(c):
right_ngrams = set(get_right_ngrams(c.part, lower=False))
return (TRUE if
((c[1].context.get_span() == "NPN" and "NPN" in right_ngrams) or
(c[1].context.get_span() == "PNP" and "PNP" in right_ngrams)) else
ABSTAIN)
