pip install -U rapidnlp-datasets

>>> import torch
>>> from rapidnlp_datasets.pt import DatasetForSequenceClassification
>>> dataset = DatasetForSequenceClassification.from_jsonl_files(
        input_files=["testdata/sequence_classification.jsonl"],
        vocab_file="testdata/vocab.txt",
    )
>>> dataloader = torch.utils.data.DataLoader(dataset, shuffle=True, batch_size=32, collate_fn=dataset.batch_padding_collate)
>>> for idx, batch in enumerate(dataloader):
...     print("No.{} batch: \n{}".format(idx, batch))
... 

>>> from rapidnlp_datasets.tf import TFDatasetForSequenceClassifiation
>>> dataset, d = TFDatasetForSequenceClassifiation.from_jsonl_files(
        input_files=["testdata/sequence_classification.jsonl"],
        vocab_file="testdata/vocab.txt",
        return_self=True,
    )
>>> for idx, batch in enumerate(iter(dataset)):
...     print("No.{} batch: \n{}".format(idx, batch))
... 

>>> d.save_tfrecord("testdata/sequence_classification.tfrecord")
2021-12-08 14:52:41,295    INFO             utils.py  128] Finished to write 2 examples to tfrecords.
>>> dataset = TFDatasetForSequenceClassifiation.from_tfrecord_files("testdata/sequence_classification.tfrecord")
>>> for idx, batch in enumerate(iter(dataset)):
...     print("No.{} batch: \n{}".format(idx, batch))
... 

>>> import torch
>>> from rapidnlp_datasets.pt import DatasetForQuestionAnswering
>>>
>>> dataset = DatasetForQuestionAnswering.from_jsonl_files(
        input_files="testdata/qa.jsonl",
        vocab_file="testdata/vocab.txt",
    )
>>> dataloader = torch.utils.data.DataLoader(dataset, shuffle=True, batch_size=32, collate_fn=dataset.batch_padding_collate)
>>> for idx, batch in enumerate(dataloader):
...     print("No.{} batch: \n{}".format(idx, batch))
... 

>>> from rapidnlp_datasets.tf import TFDatasetForQuestionAnswering
>>> dataset, d = TFDatasetForQuestionAnswering.from_jsonl_files(
        input_files="testdata/qa.jsonl",
        vocab_file="testdata/vocab.txt",
        return_self=True,
    )
2021-12-08 15:09:06,747    INFO question_answering_dataset.py  101] Read 3 examples in total.
>>> for idx, batch in enumerate(iter(dataset)):
        print()
        print("NO.{} batch: \n{}".format(idx, batch))
... 

>>> d.save_tfrecord("testdata/qa.tfrecord")
2021-12-08 15:09:31,329    INFO             utils.py  128] Finished to write 3 examples to tfrecords.
>>> dataset = TFDatasetForQuestionAnswering.from_tfrecord_files(
        "testdata/qa.tfrecord",
        batch_size=32,
        padding="batch",
    )
>>> for idx, batch in enumerate(iter(dataset)):
        print()
        print("NO.{} batch: \n{}".format(idx, batch))
...