Skip to content

fix: resolve test patching failure in test_evaluate_multiple_models.py #26

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

Closed
federetyk wants to merge 1 commit into from
Closed

fix: resolve test patching failure in test_evaluate_multiple_models.py #26

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
15 changes: 9 additions & 6 deletions tests/test_evaluate_multiple_models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
4. Results are properly structured and returned
"""

import importlib
import time
from unittest.mock import patch

Expand All @@ -28,6 +29,8 @@
from workrb.tasks.abstract.base import DatasetSplit, Language
from workrb.types import ModelInputType

evaluate_module = importlib.import_module("workrb.evaluate")


class ToyModel(ModelInterface):
"""Simple toy model for testing - no actual model loading required."""
Expand Down Expand Up @@ -118,7 +121,7 @@ def test_evaluate_multiple_models_basic():
task_name = task.name

# Mock the evaluate function
with patch("workrb.evaluate.evaluate") as mock_evaluate:
with patch.object(evaluate_module, "evaluate") as mock_evaluate:
# Set up return values for each model
mock_evaluate.side_effect = [
create_mock_results("model1", task_name),
Expand Down Expand Up @@ -165,7 +168,7 @@ def test_evaluate_multiple_models_with_additional_kwargs():
task = ToyTask(split=DatasetSplit.VAL, languages=[Language.EN])
task_name = task.name

with patch("workrb.evaluate.evaluate") as mock_evaluate:
with patch.object(evaluate_module, "evaluate") as mock_evaluate:
mock_evaluate.return_value = create_mock_results("test_model", task_name)

results = evaluate_multiple_models(
Expand Down Expand Up @@ -227,7 +230,7 @@ def test_evaluate_multiple_models_error_handling():
task = ToyTask(split=DatasetSplit.VAL, languages=[Language.EN])
task_name = task.name

with patch("workrb.evaluate.evaluate") as mock_evaluate:
with patch.object(evaluate_module, "evaluate") as mock_evaluate:
# First model succeeds, second fails
mock_evaluate.side_effect = [
create_mock_results("model1", task_name),
Expand Down Expand Up @@ -256,7 +259,7 @@ def test_evaluate_multiple_models_output_folder_overrides_kwargs():
task = ToyTask(split=DatasetSplit.VAL, languages=[Language.EN])
task_name = task.name

with patch("workrb.evaluate.evaluate") as mock_evaluate:
with patch.object(evaluate_module, "evaluate") as mock_evaluate:
mock_evaluate.side_effect = [
create_mock_results("model1", task_name),
create_mock_results("model2", task_name),
Expand Down Expand Up @@ -287,7 +290,7 @@ def test_evaluate_multiple_models_single_model():
task = ToyTask(split=DatasetSplit.VAL, languages=[Language.EN])
task_name = task.name

with patch("workrb.evaluate.evaluate") as mock_evaluate:
with patch.object(evaluate_module, "evaluate") as mock_evaluate:
mock_evaluate.return_value = create_mock_results("single_model", task_name)

results = evaluate_multiple_models(
Expand All @@ -307,7 +310,7 @@ def test_evaluate_multiple_models_empty_models_list():
ToyTask = create_toy_task_class(SkillMatch1kSkillSimilarityRanking)
task = ToyTask(split=DatasetSplit.VAL, languages=[Language.EN])

with patch("workrb.evaluate.evaluate") as mock_evaluate:
with patch.object(evaluate_module, "evaluate") as mock_evaluate:
with pytest.raises(AssertionError) as excinfo:
evaluate_multiple_models(
models=[],
Expand Down