Skip to content

Fix Mypy typing invariance by updating List to Sequence in dataset loading functions (#5354) #8282

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

Open
Paramveersingh-S wants to merge 1 commit into
base: main
Choose a base branch
from
+18 −17
Open

Fix Mypy typing invariance by updating List to Sequence in dataset loading functions (#5354) #8282

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
15 changes: 8 additions & 7 deletions src/datasets/arrow_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,7 @@
from pathlib import Path
from random import sample
from typing import (
Sequence,
TYPE_CHECKING,
Any,
BinaryIO,
Expand Down Expand Up @@ -1290,7 +1291,7 @@ def from_list(

@staticmethod
def from_csv(
path_or_paths: Union[PathLike, list[PathLike]],
path_or_paths: Union[PathLike, Sequence[PathLike]],
split: Optional[NamedSplit] = None,
features: Optional[Features] = None,
cache_dir: str = None,
Expand Down Expand Up @@ -1430,7 +1431,7 @@ def from_generator(

@staticmethod
def from_json(
path_or_paths: Union[PathLike, list[PathLike]],
path_or_paths: Union[PathLike, Sequence[PathLike]],
split: Optional[NamedSplit] = None,
features: Optional[Features] = None,
cache_dir: str = None,
Expand Down Expand Up @@ -1489,12 +1490,12 @@ def from_json(

@staticmethod
def from_parquet(
path_or_paths: Union[PathLike, list[PathLike]],
path_or_paths: Union[PathLike, Sequence[PathLike]],
split: Optional[NamedSplit] = None,
features: Optional[Features] = None,
cache_dir: str = None,
keep_in_memory: bool = False,
columns: Optional[list[str]] = None,
columns: Optional[Sequence[str]] = None,
num_proc: Optional[int] = None,
filters: Optional[Union[pds.Expression, list[tuple], list[list[tuple]]]] = None,
fragment_scan_options: Optional[pds.ParquetFragmentScanOptions] = None,
Expand Down Expand Up @@ -1586,7 +1587,7 @@ def from_parquet(

@staticmethod
def from_text(
path_or_paths: Union[PathLike, list[PathLike]],
path_or_paths: Union[PathLike, Sequence[PathLike]],
split: Optional[NamedSplit] = None,
features: Optional[Features] = None,
cache_dir: str = None,
Expand Down Expand Up @@ -3671,11 +3672,11 @@ def _map_single(
function: Optional[Callable] = None,
with_indices: bool = False,
with_rank: bool = False,
input_columns: Optional[list[str]] = None,
input_columns: Optional[Sequence[str]] = None,
batched: bool = False,
batch_size: Optional[int] = 1000,
drop_last_batch: bool = False,
remove_columns: Optional[list[str]] = None,
remove_columns: Optional[Sequence[str]] = None,
keep_in_memory: bool = False,
cache_file_name: Optional[str] = None,
writer_batch_size: Optional[int] = 1000,
Expand Down
2 changes: 1 addition & 1 deletion src/datasets/dataset_dict.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1534,7 +1534,7 @@ def from_parquet(
features: Optional[Features] = None,
cache_dir: str = None,
keep_in_memory: bool = False,
columns: Optional[list[str]] = None,
columns: Optional[Sequence[str]] = None,
**kwargs,
) -> "DatasetDict":
"""Create [`DatasetDict`] from Parquet file(s).
Expand Down
18 changes: 9 additions & 9 deletions src/datasets/iterable_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
from functools import partial
from itertools import cycle, islice
from pathlib import Path
from typing import TYPE_CHECKING, Any, BinaryIO, Callable, Optional, Union
from typing import TYPE_CHECKING, Any, BinaryIO, Callable, Optional, Union, Sequence

import fsspec.asyn
import multiprocess as mp
Expand Down Expand Up @@ -1347,11 +1347,11 @@ def __init__(
ex_iterable: _BaseExamplesIterable,
function: Callable,
with_indices: bool = False,
input_columns: Optional[list[str]] = None,
input_columns: Optional[Sequence[str]] = None,
batched: bool = False,
batch_size: Optional[int] = 1000,
drop_last_batch: bool = False,
remove_columns: Optional[list[str]] = None,
remove_columns: Optional[Sequence[str]] = None,
fn_kwargs: Optional[dict] = None,
formatting: Optional["FormattingConfig"] = None,
features: Optional[Features] = None,
Expand Down Expand Up @@ -1799,7 +1799,7 @@ def __init__(
ex_iterable: _BaseExamplesIterable,
function: Callable,
with_indices: bool = False,
input_columns: Optional[list[str]] = None,
input_columns: Optional[Sequence[str]] = None,
batched: bool = False,
batch_size: Optional[int] = 1000,
fn_kwargs: Optional[dict] = None,
Expand Down Expand Up @@ -3157,7 +3157,7 @@ def from_list(

@staticmethod
def from_csv(
path_or_paths: Union[PathLike, list[PathLike]],
path_or_paths: Union[PathLike, Sequence[PathLike]],
split: Optional[NamedSplit] = None,
features: Optional[Features] = None,
keep_in_memory: bool = False,
Expand Down Expand Up @@ -3200,7 +3200,7 @@ def from_csv(

@staticmethod
def from_json(
path_or_paths: Union[PathLike, list[PathLike]],
path_or_paths: Union[PathLike, Sequence[PathLike]],
split: Optional[NamedSplit] = None,
features: Optional[Features] = None,
keep_in_memory: bool = False,
Expand Down Expand Up @@ -3247,11 +3247,11 @@ def from_json(

@staticmethod
def from_parquet(
path_or_paths: Union[PathLike, list[PathLike]],
path_or_paths: Union[PathLike, Sequence[PathLike]],
split: Optional[NamedSplit] = None,
features: Optional[Features] = None,
keep_in_memory: bool = False,
columns: Optional[list[str]] = None,
columns: Optional[Sequence[str]] = None,
filters: Optional[Union[pds.Expression, list[tuple], list[list[tuple]]]] = None,
fragment_scan_options: Optional[pds.ParquetFragmentScanOptions] = None,
on_bad_files: Literal["error", "warn", "skip"] = "error",
Expand Down Expand Up @@ -3332,7 +3332,7 @@ def from_parquet(

@staticmethod
def from_text(
path_or_paths: Union[PathLike, list[PathLike]],
path_or_paths: Union[PathLike, Sequence[PathLike]],
split: Optional[NamedSplit] = None,
features: Optional[Features] = None,
keep_in_memory: bool = False,
Expand Down