def same_col(c):
"""Return True if all Spans in the given candidate are from the same Col.
:param c: The candidate whose Spans are being compared
:rtype: boolean
"""
return same_table(c) and all(
is_col_aligned(c[i].sentence, c[0].sentence) for i in range(len(c)))
def same_col(c: Candidate) -> bool:
"""Return True if all Mentions in the given candidate are from the same Col.
:param c: The candidate whose Mentions are being compared
:rtype: boolean
"""
return same_table(c) and all(
is_col_aligned(_to_span(c[i]).sentence,
_to_span(c[0]).sentence) for i in range(len(c)))
def col_filter(c):
(data, col) = c
# Ignore only empty candidate values
if (re.match("^[\., -]*$", data.context.get_span())):
return False
if same_table((data, col)):
d = data.context.sentence
c = col.context.sentence
return (is_col_aligned(d, c)) # and is_vert_aligned((data, col)))
return True
def is_tabular_aligned(c: Candidate) -> bool:
"""Return True if all Mentions in the given candidate are from the same Row or Col.
:param c: The candidate whose Mentions are being compared
"""
return same_table(c) and all(
is_col_aligned(_to_span(c[i]).sentence,
_to_span(c[0]).sentence)
or is_row_aligned(_to_span(c[i]).sentence,
_to_span(c[0]).sentence) for i in range(len(c)))
def mention_analysis(align_val, data_val, document_name, align_type, mentions,
mention_subclasses):
(data_mentions, row_mentions,
col_mentions) = split_mentions(mentions, mention_subclasses)
align_mentions = row_mentions if align_type == 'row' else col_mentions
s1s = [
x for x in data_mentions if data_val == x.context.get_span().upper()
and x.document.name == document_name
]
s2s = [
x for x in align_mentions if align_val in x.context.get_span().upper()
and x.document.name == document_name
]
print("######################################")
print(f"Mention Analysis {align_type}")
print(
f"{len(s1s)} mentions for the data value {data_val} in document {document_name}."
)
print(
f"{len(s2s)} mentions for the align value {align_val} in document {document_name}."
)
if (len(s1s) > 0 and len(s2s) > 0):
for s1 in s1s:
for s2 in s2s:
print("")
print(f"Sentence of the data value: {s1.context.sentence}")
print(f"Sentence of the align value: {s2.context.sentence}")
aligned = is_row_aligned(
s1.context.sentence, s2.context.sentence
) if align_type == 'row' else is_col_aligned(
s1.context.sentence, s2.context.sentence)
print(f"The values are {align_type} aligned: {aligned}")
hv_aligned = is_horz_aligned(
(s1, s2)) if align_type == 'row' else is_vert_aligned(
(s1, s2))
hv = "horizontally" if align_type == 'row' else "vertically"
print(f"The values are {hv} aligned: {hv_aligned}")
elif (len(s1s) > 0):
for s1 in s1s:
print(f"Sentence of the data value: {s1.context.sentence}")
print("")
print(
f"No align value found in all align mentions for the document {document_name}:"
)
pprint([x for x in align_mentions if x.document.name == document_name])
elif (len(s2s) > 0):
for s2 in s2s:
print(f"Sentence of the align value: {s2.context.sentence}")
print("")
print(
f"No data value found in all data mentions for the document {document_name}:"
)
pprint([x for x in data_mentions if x.document.name == document_name])
print("######################################")