SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Apply ruff flake8-comprehensions (#21694)

Browse Source
This commit is contained in:
Aaron Gokaslan
2023-02-22 03:14:54 -05:00
committed by GitHub
parent df06fb1f0b
commit 5e8c8eb5ba
230 changed files with 971 additions and 955 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
tests/pipelines/test_pipelines_common.py
View File

@@ -606,7 +606,7 @@ class PipelineUtilsTest(unittest.TestCase):
dataset = PipelineIterator(dummy_dataset, add, {"extra": 2})
self.assertEqual(len(dataset), 4)
outputs = [item for item in dataset]
outputs = list(dataset)
self.assertEqual(outputs, [2, 3, 4, 5])
@require_torch
@@ -624,7 +624,7 @@ class PipelineUtilsTest(unittest.TestCase):
with self.assertRaises(TypeError):
len(dataset)
outputs = [item for item in dataset]
outputs = list(dataset)
self.assertEqual(outputs, [2, 3, 4, 5])
@require_torch
@@ -638,7 +638,7 @@ class PipelineUtilsTest(unittest.TestCase):
dataset = PipelineIterator(dummy_dataset, add, {"extra": 2}, loader_batch_size=3)
outputs = [item for item in dataset]
outputs = list(dataset)
self.assertEqual(outputs, [{"id": 2}, {"id": 3}, {"id": 4}, {"id": 5}])
@require_torch
@@ -654,7 +654,7 @@ class PipelineUtilsTest(unittest.TestCase):
dataset = PipelineIterator(dummy_dataset, add, {"extra": 2}, loader_batch_size=3)
outputs = [item for item in dataset]
outputs = list(dataset)
self.assertEqual(
nested_simplify(outputs), [{"id": [[12, 22]]}, {"id": [[2, 3]]}, {"id": [[2, 4]]}, {"id": [[5]]}]
)
@@ -671,7 +671,7 @@ class PipelineUtilsTest(unittest.TestCase):
dataset = PipelineChunkIterator(dataset, preprocess_chunk, {}, loader_batch_size=3)
outputs = [item for item in dataset]
outputs = list(dataset)
self.assertEqual(outputs, [0, 1, 0, 1, 2])
@@ -692,7 +692,7 @@ class PipelineUtilsTest(unittest.TestCase):
dataset = PipelinePackIterator(dataset, pack, {})
outputs = [item for item in dataset]
outputs = list(dataset)
self.assertEqual(
outputs,
[
@@ -719,7 +719,7 @@ class PipelineUtilsTest(unittest.TestCase):
dataset = PipelinePackIterator(dummy_dataset, add, {"extra": 2}, loader_batch_size=3)
outputs = [item for item in dataset]
outputs = list(dataset)
self.assertEqual(outputs, [[{"id": 2}, {"id": 3}], [{"id": 4}, {"id": 5}]])
# is_false Across batch
@@ -730,7 +730,7 @@ class PipelineUtilsTest(unittest.TestCase):
dataset = PipelinePackIterator(dummy_dataset, add, {"extra": 2}, loader_batch_size=3)
outputs = [item for item in dataset]
outputs = list(dataset)
self.assertEqual(outputs, [[{"id": 2}, {"id": 3}, {"id": 4}, {"id": 5}]])
@slow

14
tests/pipelines/test_pipelines_fill_mask.py
View File

@@ -281,7 +281,7 @@ class FillMaskPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
def run_test_targets(self, model, tokenizer):
vocab = tokenizer.get_vocab()
targets = list(sorted(vocab.keys()))[:2]
targets = sorted(vocab.keys())[:2]
# Pipeline argument
fill_masker = FillMaskPipeline(model=model, tokenizer=tokenizer, targets=targets)
outputs = fill_masker(f"This is a {tokenizer.mask_token}")
@@ -293,8 +293,8 @@ class FillMaskPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
],
)
target_ids = {vocab[el] for el in targets}
self.assertEqual(set(el["token"] for el in outputs), target_ids)
self.assertEqual(set(el["token_str"] for el in outputs), set(targets))
self.assertEqual({el["token"] for el in outputs}, target_ids)
self.assertEqual({el["token_str"] for el in outputs}, set(targets))
# Call argument
fill_masker = FillMaskPipeline(model=model, tokenizer=tokenizer)
@@ -307,8 +307,8 @@ class FillMaskPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
],
)
target_ids = {vocab[el] for el in targets}
self.assertEqual(set(el["token"] for el in outputs), target_ids)
self.assertEqual(set(el["token_str"] for el in outputs), set(targets))
self.assertEqual({el["token"] for el in outputs}, target_ids)
self.assertEqual({el["token_str"] for el in outputs}, set(targets))
# Score equivalence
outputs = fill_masker(f"This is a {tokenizer.mask_token}", targets=targets)
@@ -354,7 +354,7 @@ class FillMaskPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
fill_masker = FillMaskPipeline(model=model, tokenizer=tokenizer)
# top_k=2, ntargets=3
targets = list(sorted(vocab.keys()))[:3]
targets = sorted(vocab.keys())[:3]
outputs = fill_masker(f"This is a {tokenizer.mask_token}", top_k=2, targets=targets)
# If we use the most probably targets, and filter differently, we should still
@@ -369,7 +369,7 @@ class FillMaskPipelineTests(unittest.TestCase, metaclass=PipelineTestCaseMeta):
fill_masker = FillMaskPipeline(model=model, tokenizer=tokenizer)
vocab = tokenizer.get_vocab()
# String duplicates + id duplicates
targets = list(sorted(vocab.keys()))[:3]
targets = sorted(vocab.keys())[:3]
targets = [targets[0], targets[1], targets[0], targets[2], targets[1]]
outputs = fill_masker(f"My name is {tokenizer.mask_token}", targets=targets, top_k=10)

2
tests/pipelines/test_pipelines_video_classification.py
View File

@@ -63,7 +63,7 @@ class VideoClassificationPipelineTests(unittest.TestCase, metaclass=PipelineTest
def test_small_model_pt(self):
small_model = "hf-internal-testing/tiny-random-VideoMAEForVideoClassification"
small_feature_extractor = VideoMAEFeatureExtractor(
size=dict(shortest_edge=10), crop_size=dict(height=10, width=10)
size={"shortest_edge": 10}, crop_size={"height": 10, "width": 10}
)
video_classifier = pipeline(
"video-classification", model=small_model, feature_extractor=small_feature_extractor, frame_sampling_rate=4