Skip to content
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

Jump to bottom

with_format docstring #7203

Merged
merged 1 commit into from
Oct 8, 2024
Merged

with_format docstring #7203

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
26 changes: 23 additions & 3 deletions src/datasets/arrow_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2649,12 +2649,32 @@ def with_format(
'format_kwargs': {},
'output_all_columns': False,
'type': None}
>>> ds = ds.with_format(type='tensorflow', columns=['input_ids', 'token_type_ids', 'attention_mask', 'label'])
>>> ds = ds.with_format("torch")
>>> ds.format
{'columns': ['input_ids', 'token_type_ids', 'attention_mask', 'label'],
{'columns': ['text', 'label', 'input_ids', 'token_type_ids', 'attention_mask'],
'format_kwargs': {},
'output_all_columns': False,
'type': 'tensorflow'}
'type': 'torch'}
>>> ds[0]
{'text': 'compassionately explores the seemingly irreconcilable situation between conservative christian parents and their estranged gay and lesbian children .',
'label': tensor(1),
'input_ids': tensor([ 101, 18027, 16310, 16001, 1103, 9321, 178, 11604, 7235, 6617,
1742, 2165, 2820, 1206, 6588, 22572, 12937, 1811, 2153, 1105,
1147, 12890, 19587, 6463, 1105, 15026, 1482, 119, 102, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0]),
'token_type_ids': tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]),
'attention_mask': tensor([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])}
```
"""
dataset = copy.deepcopy(self)
Expand Down
64 changes: 51 additions & 13 deletions src/datasets/dataset_dict.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -693,12 +693,32 @@ def with_format(
'format_kwargs': {},
'output_all_columns': False,
'type': None}
>>> ds = ds.with_format(type='tensorflow', columns=['input_ids', 'token_type_ids', 'attention_mask', 'label'])
>>> ds = ds.with_format("torch")
>>> ds["train"].format
{'columns': ['input_ids', 'token_type_ids', 'attention_mask', 'label'],
{'columns': ['text', 'label', 'input_ids', 'token_type_ids', 'attention_mask'],
'format_kwargs': {},
'output_all_columns': False,
'type': 'tensorflow'}
'type': 'torch'}
>>> ds["train"][0]
{'text': 'compassionately explores the seemingly irreconcilable situation between conservative christian parents and their estranged gay and lesbian children .',
'label': tensor(1),
'input_ids': tensor([ 101, 18027, 16310, 16001, 1103, 9321, 178, 11604, 7235, 6617,
1742, 2165, 2820, 1206, 6588, 22572, 12937, 1811, 2153, 1105,
1147, 12890, 19587, 6463, 1105, 15026, 1482, 119, 102, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0]),
'token_type_ids': tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]),
'attention_mask': tensor([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])}
```
"""
dataset = copy.deepcopy(self)
Expand Down Expand Up @@ -1801,25 +1821,43 @@ def with_format(
) -> "IterableDatasetDict":
"""
Return a dataset with the specified format.
This method only supports the "torch" format for now.
The format is set to all the datasets of the dataset dictionary.
The 'pandas' format is currently not implemented.

Args:
type (`str`, *optional*, defaults to `None`):
If set to "torch", the returned dataset
will be a subclass of `torch.utils.data.IterableDataset` to be used in a `DataLoader`.

type (`str`, *optional*):
Either output type selected in `[None, 'numpy', 'torch', 'tensorflow', 'arrow', 'jax']`.
`None` means it returns python objects (default).

Example:

```py
>>> from datasets import load_dataset
>>> ds = load_dataset("rotten_tomatoes", streaming=True)
>>> from transformers import AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
>>> def encode(example):
... return tokenizer(examples["text"], truncation=True, padding="max_length")
>>> ds = ds.map(encode, batched=True, remove_columns=["text"])
>>> ds = load_dataset("rotten_tomatoes", split="validation", streaming=True)
>>> tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
>>> ds = ds.map(lambda x: tokenizer(x['text'], truncation=True, padding=True), batched=True)
>>> ds = ds.with_format("torch")
>>> next(iter(ds))
{'text': 'compassionately explores the seemingly irreconcilable situation between conservative christian parents and their estranged gay and lesbian children .',
'label': tensor(1),
'input_ids': tensor([ 101, 18027, 16310, 16001, 1103, 9321, 178, 11604, 7235, 6617,
1742, 2165, 2820, 1206, 6588, 22572, 12937, 1811, 2153, 1105,
1147, 12890, 19587, 6463, 1105, 15026, 1482, 119, 102, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0]),
'token_type_ids': tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]),
'attention_mask': tensor([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])}
```
"""
return IterableDatasetDict({k: dataset.with_format(type=type) for k, dataset in self.items()})
Expand Down
39 changes: 35 additions & 4 deletions src/datasets/iterable_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2178,13 +2178,44 @@ def with_format(
) -> "IterableDataset":
"""
Return a dataset with the specified format.
Supported formats: "arrow", or None for regular python objects.
The other formats are currently not implemented.
The 'pandas' format is currently not implemented.

Args:

type (`str`, optional, default None): if set to "torch", the returned dataset
will be a subclass of torch.utils.data.IterableDataset to be used in a DataLoader
type (`str`, *optional*):
Either output type selected in `[None, 'numpy', 'torch', 'tensorflow', 'arrow', 'jax']`.
`None` means it returns python objects (default).

Example:

```py
>>> from datasets import load_dataset
>>> from transformers import AutoTokenizer
>>> ds = load_dataset("rotten_tomatoes", split="validation", streaming=True)
>>> tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
>>> ds = ds.map(lambda x: tokenizer(x['text'], truncation=True, padding=True), batched=True)
>>> ds = ds.with_format("torch")
>>> next(iter(ds))
{'text': 'compassionately explores the seemingly irreconcilable situation between conservative christian parents and their estranged gay and lesbian children .',
'label': tensor(1),
'input_ids': tensor([ 101, 18027, 16310, 16001, 1103, 9321, 178, 11604, 7235, 6617,
1742, 2165, 2820, 1206, 6588, 22572, 12937, 1811, 2153, 1105,
1147, 12890, 19587, 6463, 1105, 15026, 1482, 119, 102, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0]),
'token_type_ids': tensor([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]),
'attention_mask': tensor([1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])}
```
"""
type = get_format_type_from_alias(type)
# TODO(QL): add format_kwargs
Expand Down
Loading