def LF_part_mismatch_header(c):
ngrams_part = _filter_non_parts(
set(list(get_head_ngrams(c[1], n_max=1, axis="col"))))
return (ABSTAIN if len(ngrams_part) == 0 or any([
c.part.context.get_span().lower().startswith(_.lower())
for _ in ngrams_part
]) else 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 LF_head_ends_with_ceo(c):
return (TRUE if any(
ngram.endswith("ceo") for ngram in get_head_ngrams(c[1])) else ABSTAIN)