Skip to content

Fix misleading add_column() usage example in docstring #7648

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

Merged
merged 4 commits into from
Jul 17, 2025
+13 −6
Merged

Fix misleading add_column() usage example in docstring #7648

Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5848fd8
Fix misleading add_column() usage example in docstring
ArjunJagdale Jun 27, 2025
fa20ffe
Merge branch 'huggingface:main' into patch-12
ArjunJagdale Jul 7, 2025
5927192
Fix misleading docstring examples for select_columns, select, filter,…
ArjunJagdale Jul 7, 2025
60fd956
Apply suggestions from code review
lhoestq Jul 17, 2025
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
24 changes: 18 additions & 6 deletions src/datasets/arrow_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2041,7 +2041,9 @@ def flatten(self, new_fingerprint: Optional[str] = None, max_depth=16) -> "Datas
'question': Value('string'),
'answers': {'text': List(Value('string')),
'answer_start': List(Value('int32'))}}
>>> ds.flatten()
>>> # Note: this method returns a new dataset and does not modify in-place
>>> ds = ds.flatten()
>>> ds
Dataset({
features: ['id', 'title', 'context', 'question', 'answers.text', 'answers.answer_start'],
num_rows: 87599
Expand Down Expand Up @@ -2399,7 +2401,9 @@ def select_columns(self, column_names: Union[str, list[str]], new_fingerprint: O
```py
>>> from datasets import load_dataset
>>> ds = load_dataset("cornell-movie-review-data/rotten_tomatoes", split="validation")
>>> ds.select_columns(['text'])
>>> # Note: this method returns a new dataset and does not modify in-place
>>> ds = ds.select_columns(['text'])
>>> ds
Dataset({
features: ['text'],
num_rows: 1066
Expand Down Expand Up @@ -3869,12 +3873,15 @@ def filter(
```py
>>> from datasets import load_dataset
>>> ds = load_dataset("cornell-movie-review-data/rotten_tomatoes", split="validation")
>>> ds.filter(lambda x: x["label"] == 1)
>>> # Note: this method returns a new dataset and does not modify in-place
>>> ds = ds.filter(lambda x: x["label"] == 1)
>>> ds
Dataset({
features: ['text', 'label'],
num_rows: 533
})
```

"""
if len(self.list_indexes()) > 0:
raise DatasetTransformationNotAllowedError(
Expand Down Expand Up @@ -4041,7 +4048,9 @@ def select(
```py
>>> from datasets import load_dataset
>>> ds = load_dataset("cornell-movie-review-data/rotten_tomatoes", split="validation")
>>> ds.select(range(4))
>>> # Note: this method returns a new dataset and does not modify in-place
>>> ds = ds.select(range(4))
>>> ds
Dataset({
features: ['text', 'label'],
num_rows: 4
Expand Down Expand Up @@ -4936,7 +4945,9 @@ def shard(
features: ['text', 'label'],
num_rows: 1066
})
>>> ds.shard(num_shards=2, index=0)
>>> # Note: this method returns a new dataset and does not modify in-place
>>> ds = ds.shard(num_shards=2, index=0)
>>> ds
Dataset({
features: ['text', 'label'],
num_rows: 533
Expand Down Expand Up @@ -6005,7 +6016,8 @@ def add_column(
>>> from datasets import load_dataset
>>> ds = load_dataset("cornell-movie-review-data/rotten_tomatoes", split="validation")
>>> more_text = ds["text"]
>>> ds.add_column(name="text_2", column=more_text)
>>> ds = ds.add_column(name="text_2", column=more_text)
>>> ds
Dataset({
features: ['text', 'label', 'text_2'],
num_rows: 1066
Expand Down
Loading