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 tablelib_unary_features(span):
"""
Table-/structure-related features for a single span
"""
if not span.sentence.is_tabular():
return
sentence = span.sentence
for attrib in settings["featurization"]["table"]["unary_features"]["attrib"]:
for ngram in get_cell_ngrams(
span,
n_max=settings["featurization"]["table"]["unary_features"][
"get_cell_ngrams"
]["max"],
attrib=attrib,
):
yield f"CELL_{attrib.upper()}_[{ngram}]", DEF_VALUE
for row_num in range(sentence.row_start, sentence.row_end + 1):
yield f"ROW_NUM_[{row_num}]", DEF_VALUE
for col_num in range(sentence.col_start, sentence.col_end + 1):
yield f"COL_NUM_[{col_num}]", DEF_VALUE
# NOTE: These two features could be accounted for by HTML_ATTR in
# structural features
yield f"ROW_SPAN_[{num_rows(sentence)}]", DEF_VALUE
yield f"COL_SPAN_[{num_cols(sentence)}]", DEF_VALUE
for axis in ["row", "col"]:
for ngram in get_head_ngrams(
span,
axis,
n_max=settings["featurization"]["table"]["unary_features"][
"get_head_ngrams"
]["max"],
attrib=attrib,
):
yield f"{axis.upper()}_HEAD_{attrib.upper()}_[{ngram}]", DEF_VALUE
for ngram in get_row_ngrams(
span,
n_max=settings["featurization"]["table"]["unary_features"][
"get_row_ngrams"
]["max"],
attrib=attrib,
):
yield f"ROW_{attrib.upper()}_[{ngram}]", DEF_VALUE
for ngram in get_col_ngrams(
span,
n_max=settings["featurization"]["table"]["unary_features"][
"get_col_ngrams"
]["max"],
attrib=attrib,
):
yield f"COL_{attrib.upper()}_[{ngram}]", DEF_VALUE
def neg_gain_too_many_words_in_cell(c):
cell_ngrams = list(get_cell_ngrams(c.gain))
if len(cell_ngrams) >= 4:
return FALSE
else:
return ABSTAIN
def neg_gain_keywords_in_cell(c):
cell_ngrams = set(get_cell_ngrams(c.gain, n_max=1, lower=True))
if overlap(["g", "vo", "vpp", "f=", "f", "="], cell_ngrams):
return FALSE
else:
return ABSTAIN