def __str__(self):
buf = io.StringIO()
text = self._data['text']
tokens = text.split()
buf.write("Text ({:d}): {:s}\n".format(len(tokens), text))
def _fmt_span(s, e): return '[{:d},{:d})\t"{:s}"'.format(s, e, " ".join(tokens[s:e]))
for t in self._data['targets']:
buf.write("\n")
buf.write(" span1: {}\n".format(_fmt_span(*t['span1'])))
buf.write(" span2: {}\n".format(_fmt_span(*t['span2'])))
labels = utils.wrap_singleton_string(t['label'])
buf.write(" label: ({:d})\t {}\n".format(len(labels), ", ".join(labels)))
return buf.getvalue()
def _split_and_flatten_records(self, records: Iterable[Dict]):
ex_records = [] # long-form example records, minus targets
tr_records = [] # long-form target records with 'idx' column
for idx, r in enumerate(records):
d = {'text': r['text'], 'idx': idx}
d.update(_get_nested_vals(r, 'info'))
d.update(_get_nested_vals(r, 'preds'))
ex_records.append(d)
for t in r['targets']:
d = {'label': utils.wrap_singleton_string(t['label']),
'idx': idx}
if 'span1' in t:
d['span1'] = tuple(t['span1'])
if 'span2' in t:
d['span2'] = tuple(t['span2'])
d.update(_get_nested_vals(t, 'info'))
d.update(_get_nested_vals(t, 'preds'))
tr_records.append(d)
return ex_records, tr_records