Skip to content

fix fairness scores #709

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

Merged
ArshaanNazir merged 1 commit into from
Aug 16, 2023
Merged

fix fairness scores #709

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 7 additions & 2 deletions langtest/transform/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,7 @@
Result,
)
from ..utils.custom_types.helpers import default_user_prompt
from ..utils.util_metrics import calculate_f1_score

nest_asyncio.apply()

Expand Down Expand Up @@ -893,8 +894,12 @@ def run(
y_pred = y_pred[valid_indices]
y_true = y_true.explode()
y_pred = y_pred.explode()
y_pred = y_pred.apply(lambda x: x.split("-")[-1])
y_true = y_true.apply(lambda x: x.split("-")[-1])
y_pred = y_pred.apply(lambda x: x.split("-")[-1]).reset_index(
drop=True
)
y_true = y_true.apply(lambda x: x.split("-")[-1]).reset_index(
drop=True
)

elif isinstance(data[0], SequenceClassificationSample):
y_true = pd.Series(data).apply(
Expand Down
5 changes: 2 additions & 3 deletions langtest/transform/fairness.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -142,12 +142,11 @@ async def run(

"""
progress = kwargs.get("progress_bar", False)

for sample in sample_list:
data = gendered_data[sample.test_case]
if len(data[0]) > 0:
macro_f1_score = calculate_f1_score(
[x[0] for x in data[0]], data[1], average="macro", zero_division=0
data[0].to_list(), data[1].to_list(), average="macro", zero_division=0
)
else:
macro_f1_score = 1
Expand Down Expand Up @@ -232,7 +231,7 @@ async def run(
data = gendered_data[sample.test_case]
if len(data[0]) > 0:
macro_f1_score = calculate_f1_score(
[x[0] for x in data[0]], data[1], average="macro", zero_division=0
data[0].to_list(), data[1].to_list(), average="macro", zero_division=0
)
else:
macro_f1_score = 1
Expand Down