Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fixing serialization error and span label issue #85

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fixing serialization error and span label issue #85

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6889cfa
fix unable to hash list and missing data issue
Oct 30, 2023
b2dd7e4
update doc
Oct 30, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 13 additions & 3 deletions skweak/aggregation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,10 +71,19 @@ def __call__(self, doc: Doc) -> Doc:
# And extract the full probability distributions
output_probs = self._get_probs(agg_df)

# Does not support list of Tuple during serialization, converting to list of Dict
output_prob_dicts = []
for (span_start, span_end), probs in output_probs.items():
output_prob_dicts.append({
"span_start": span_start,
"span_end": span_end,
"probs": probs
})

# Storing the results (both as spans and with the full probs)
doc.spans[self.name] = [Span(doc, start, end, label=label)
for (start, end, label) in output_spans]
doc.spans[self.name].attrs["probs"] = output_probs
doc.spans[self.name].attrs["probs"] = output_prob_dicts
doc.spans[self.name].attrs["aggregated"] = True
doc.spans[self.name].attrs["sources"] = list(df.columns)

Expand Down Expand Up @@ -285,9 +294,10 @@ def get_observation_df(self, doc: Doc):

for source_index, source in enumerate(sources):
for span in doc.spans[source]:
if span.label_ in observed_labels:
# Change from span.label_ to span.label. Otherwise, it will be "" for all and nothong will be added to the array.
if span.label in observed_labels:
span_index = spans_indices[(span.start, span.end)]
data[span_index, source_index] = label_indices[span.label_]
data[span_index, source_index] = label_indices[span.label]

# We only consider spans with at least one concrete prediction
masking = np.full(len(unique_spans), fill_value=True, dtype=bool)
Expand Down