Apply code autoformatting with Ruff to tasks/*.py an *__init__.py (#1469)

lm_eval/tasks/scrolls/task.py

 import re
+from abc import abstractmethod
+from functools import reduce
+
 import numpy as np
 import transformers.data.metrics.squad_metrics as squad_metrics
-
-from abc import abstractmethod
 from datasets import load_metric
 from transformers import AutoTokenizer
-from functools import reduce
 
-from lm_eval.api.task import Task
-from lm_eval.api.metrics import mean
 from lm_eval.api.instance import Instance
-from lm_eval.api.registry import register_task
+from lm_eval.api.metrics import mean
+from lm_eval.api.task import Task
+
 
 _CITATION = """
 @inproceedings{shaham-etal-2022-scrolls,
@@ -44,6 +44,7 @@ _CITATION = """
 def _download_metric():
     import os
     import shutil
+
     from huggingface_hub import hf_hub_download
 
     scrolls_metric_path = hf_hub_download(
@@ -148,7 +149,7 @@ class _SCROLLSTask(Task):
         del self.dataset["test"]
         for split in self.dataset:
             self.dataset[split] = _drop_duplicates_in_input(self.dataset[split])
-        if self.PRUNE_TOKENIZERS is not None and self.PRUNE_TOKENIZERS is not None:
+        if self.PRUNE_TOKENIZERS is not None:
             self.prune()
 
     def _get_prune_text(self, sample):

lm_eval/tasks/squadv2/task.py

@@ -13,14 +13,15 @@ also determine when no answer is supported by the paragraph and abstain from ans
 
 Homepage: https://rajpurkar.github.io/SQuAD-explorer/
 """
-import datasets
-
-from math import exp
 from functools import partial
+from math import exp
+
+import datasets
 from packaging import version
 
-from lm_eval.api.task import ConfigurableTask
 from lm_eval.api.instance import Instance
+from lm_eval.api.task import ConfigurableTask
+
 
 _CITATION = """
 @misc{rajpurkar2018know,
@@ -35,7 +36,6 @@ _CITATION = """
 
 
 def _squad_metric(predictions, references):
-    # squad_metric = load("squad_v2")
     squad_metric = datasets.load_metric("squad_v2")
     return squad_metric.compute(predictions=predictions, references=references)
 
@@ -52,7 +52,7 @@ class SQuAD2(ConfigurableTask):
     DATASET_NAME = None
 
     def __init__(self):
-        super().__init__(config={'metadata': {'version': self.VERSION}})
+        super().__init__(config={"metadata": {"version": self.VERSION}})
 
     # HF changed squad on us so we have to make sure we aren't running the old one
     assert version.parse(datasets.__version__) >= version.parse(

lm_eval/tasks/super_glue/cb/aggregate.py

-import sklearn
 import numpy as np
+import sklearn
 
 
 def cb_multi_fi(items):

lm_eval/tasks/super_glue/record/t5_utils.py

+import collections
 import re
 import string
-import collections
-import numpy as np
 
+import numpy as np
 from datasets import Dataset
 
 from lm_eval.api.metrics import metric_max_over_ground_truths

lm_eval/tasks/super_glue/wsc/t5_utils.py

 import re
 from typing import List
 
+
 def doc_to_text(x):
     text = re.sub(r" X ", " *" + x["span2_text"] + "* ", _wsc_inputs(x))
     return "wsc: " + text
@@ -23,14 +24,14 @@ def _wsc_inputs(x):
             [
                 " ".join(words[:pronoun_index]),
                 "X",
-                " ".join(words[pronoun_index + 1:]),
+                " ".join(words[pronoun_index + 1 :]),
             ]
         )
 
     # Handle some special cases.
     if (
-            x["text"]
-            == 'The boy continued to whip the pony , and eventually the pony threw him over. John laughed out quite loud. "Good for him," he said. '
+        x["text"]
+        == 'The boy continued to whip the pony , and eventually the pony threw him over. John laughed out quite loud. "Good for him," he said. '
     ):
         return (
             "The boy continued to whip the pony , and eventually the pony threw "
@@ -39,8 +40,8 @@ def _wsc_inputs(x):
 
     # Using the span2_index, we get 'use' instead of 'it'.
     if (
-            x["text"]
-            == "When they had eventually calmed down a bit , and had gotten home, Mr. Farley put the magic pebble in an iron safe . Some day they might want to use it , but really for now, what more could they wish for?"
+        x["text"]
+        == "When they had eventually calmed down a bit , and had gotten home, Mr. Farley put the magic pebble in an iron safe . Some day they might want to use it , but really for now, what more could they wish for?"
     ):
         return (
             "When they had eventually calmed down a bit , and had gotten home, "

lm_eval/tasks/truthfulqa/utils.py

 import datasets
-import sacrebleu
 import numpy as np
-
+import sacrebleu
 from rouge_score import rouge_scorer, scoring
 
 

lm_eval/tasks/xwinograd/utils.py

@@ -51,7 +51,9 @@ def gen_lang_yamls(output_dir: str, overwrite: bool) -> None:
     for lang in LANGUAGES:
         file_name = f"xwinograd_{lang}.yaml"
         try:
-            with open(f"{output_dir}/{file_name}", "w" if overwrite else "x", encoding="utf-8") as f:
+            with open(
+                f"{output_dir}/{file_name}", "w" if overwrite else "x", encoding="utf-8"
+            ) as f:
                 f.write("# Generated by utils.py\n")
                 yaml.dump(
                     {

pyproject.toml

@@ -90,9 +90,6 @@ all = [
     "lm_eval[wandb]",
 ]
 
-[tool.ruff]
-extend-exclude = ["lm_eval/tasks/*.py"]
-
 [tool.ruff.lint]
 extend-select = ["I"]
 
@@ -101,5 +98,4 @@ lines-after-imports = 2
 known-first-party = ["lm_eval"]
 
 [tool.ruff.extend-per-file-ignores]
-"__init__.py" = ["F401","F402","F403","I"]
-"lm_eval/tasks/*"= ["E721"]
+"__init__.py" = ["F401","F402","F403"]