fix: lint errors (UP007, UP045, UP006 & UP035)

.github/benchmark/benchmark.py

@@ -2,7 +2,6 @@
 
 import argparse
 from dataclasses import dataclass
-from typing import Optional
 
 from lightning_sdk import Machine, Studio
 
@@ -19,8 +18,8 @@ class BenchmarkArgs:
 
     pr_number: int
     branch: str
-    org: Optional[str]
-    user: Optional[str]
+    org: str | None
+    user: str | None
     teamspace: str
     machine: Machine
     make_args: str
@@ -75,7 +74,7 @@ def __init__(self, config: BenchmarkArgs):
         self.org = config.org
         self.machine = config.machine
         self.make_args = config.make_args
-        self.studio: Optional[Studio] = None
+        self.studio: Studio | None = None
 
     def run(self) -> None:
         """Run the LitData benchmark."""

benchmarks/litdata/optimize_imagenet.py

@@ -10,7 +10,6 @@
 import os
 import time
 from functools import lru_cache, partial
-from typing import Union
 
 import numpy as np
 import requests
@@ -126,7 +125,7 @@ def main():
     seed_everything(args.seed)
 
     # Handle resize_size: if two ints are given, treat as tuple, else int or None
-    resize_size: Union[int, tuple[int, int], None] = None
+    resize_size: int | tuple[int, int] | None = None
     if args.resize_size is not None:
         if isinstance(args.resize_size, list):
             if len(args.resize_size) == 1:

examples/multi_modal/dataloader.py

@@ -2,7 +2,7 @@
 
 import logging
 import os
-from typing import Any, Union
+from typing import Any
 
 import joblib
 import lightning as pl
@@ -44,7 +44,7 @@ def load_tokenizer(self):
 class DocumentClassificationDataset(StreamingDataset):
     """Streaming dataset class."""
 
-    def __init__(self, input_dir: Union[str, Any], hyperparameters: Union[dict, Any] = None) -> None:
+    def __init__(self, input_dir: str | Any, hyperparameters: dict | Any = None) -> None:
         super().__init__(input_dir, shuffle=True, max_cache_size=hyperparameters["max_cache_size"])
         self.hyperparameters = hyperparameters
         self.image_transform = transforms.Compose(

examples/multi_modal/loop.py

@@ -3,7 +3,7 @@
 import logging
 import os
 from collections.abc import Sequence
-from typing import Any, Union
+from typing import Any
 
 import lightning as pl
 import pandas as pd
@@ -259,7 +259,7 @@ def configure_optimizers(self) -> Any:
         scheduler = StepLR(optimizer, step_size=1, gamma=0.1)
         return [optimizer], [{"scheduler": scheduler, "interval": "epoch"}]
 
-    def configure_callbacks(self) -> Union[Sequence[pl.pytorch.Callback], pl.pytorch.Callback]:
+    def configure_callbacks(self) -> Sequence[pl.pytorch.Callback] | pl.pytorch.Callback:
         """Configure Early stopping or Model Checkpointing."""
         early_stop = EarlyStopping(
             monitor="val_MulticlassAccuracy", patience=self.hyperparameters["patience"], mode="max"

pyproject.toml

@@ -45,10 +45,8 @@ lint.extend-select = [
   "SIM",    # see: https://pypi.org/project/flake8-simplify
 ]
 lint.ignore = [
-  "E731",  # Do not assign a lambda expression, use a def
-  "S101",  # todo: Use of `assert` detected
-  "UP007", # todo: non-pep604-annotation-union
-  "UP045", # todo: non-pep604-annotation-optional
+  "E731", # Do not assign a lambda expression, use a def
+  "S101", # todo: Use of `assert` detected
 ]
 lint.per-file-ignores."examples/**" = [
   "D100",
@@ -65,22 +63,20 @@ lint.per-file-ignores."examples/**" = [
 ]
 lint.per-file-ignores."setup.py" = [ "D100", "SIM115" ]
 lint.per-file-ignores."src/**" = [
-  "D100",  # Missing docstring in public module
-  "D101",  # todo: Missing docstring in public class
-  "D102",  # todo: Missing docstring in public method
-  "D103",  # todo: Missing docstring in public function
-  "D104",  # Missing docstring in public package
-  "D105",  # todo: Missing docstring in magic method
-  "D107",  # todo: Missing docstring in __init__
-  "D205",  # todo: 1 blank line required between summary line and description
+  "D100", # Missing docstring in public module
+  "D101", # todo: Missing docstring in public class
+  "D102", # todo: Missing docstring in public method
+  "D103", # todo: Missing docstring in public function
+  "D104", # Missing docstring in public package
+  "D105", # todo: Missing docstring in magic method
+  "D107", # todo: Missing docstring in __init__
+  "D205", # todo: 1 blank line required between summary line and description
   "D401",
-  "D404",  # todo: First line should be in imperative mood; try rephrasing
-  "S310",  # todo: Audit URL open for permitted schemes. Allowing use of `file:` or custom schemes is often unexpected.
-  "S602",  # todo: `subprocess` call with `shell=True` identified, security issue
-  "S605",  # todo: Starting a process with a shell: seems safe, but may be changed in the future; consider rewriting without `shell`
-  "S607",  # todo: Starting a process with a partial executable path
-  "UP006", # UP006 Use `list` instead of `List` for type annotation
-  "UP035", # UP035 `typing.Tuple` is deprecated, use `tuple` instead
+  "D404", # todo: First line should be in imperative mood; try rephrasing
+  "S310", # todo: Audit URL open for permitted schemes. Allowing use of `file:` or custom schemes is often unexpected.
+  "S602", # todo: `subprocess` call with `shell=True` identified, security issue
+  "S605", # todo: Starting a process with a shell: seems safe, but may be changed in the future; consider rewriting without `shell`
+  "S607", # todo: Starting a process with a partial executable path
 ]
 lint.per-file-ignores."tests/**" = [
   "D100",

src/litdata/helpers.py

@@ -1,6 +1,6 @@
 import functools
 import warnings
-from typing import Any, Optional
+from typing import Any
 
 import requests
 from packaging import version as packaging_version
@@ -24,7 +24,7 @@ def warn(self, message: str, stacklevel: int = 5, **kwargs: Any) -> None:
 
 
 @functools.lru_cache(maxsize=1)
-def _get_newer_version(curr_version: str) -> Optional[str]:
+def _get_newer_version(curr_version: str) -> str | None:
     """Check PyPI for newer versions of ``litdata``.
 
     Returning the newest version if different from the current or ``None`` otherwise.

src/litdata/imports.py

@@ -14,7 +14,7 @@
 import importlib
 from functools import lru_cache
 from importlib.util import find_spec
-from typing import Optional, TypeVar
+from typing import TypeVar
 
 import pkg_resources
 from typing_extensions import ParamSpec
@@ -83,7 +83,7 @@ class RequirementCache:
 
     """
 
-    def __init__(self, requirement: str, module: Optional[str] = None) -> None:
+    def __init__(self, requirement: str, module: str | None = None) -> None:
         self.requirement = requirement
         self.module = module