textbook 0.3.2

Text classification datasets

Textbook

Universal NLU/NLI Dataset Processing Framework

It is designed with BERT in mind and currently support seven commonsense reasoning datsets(alphanli, hellaswag, physicaliqa, socialiqa, codah, cosmosqa, and commonsenseqa). It can be also applied to other datasets with few line of codes.

Architecture

Dependency

conda install av -c conda-forge

pip install -r requirements.txt
pip install --editable .

# or

pip install textbook

Download raw datasets

./fetch.sh

It downloads alphanli, hellaswag, physicaliqa, socialiqa, codah, cosmosqa, and commonsenseqa from AWS in data_cache. In case you want to use something-something, pelase download the dataset from 20bn's website.

Usage

1. Load a dataset with parallel pandas

from transformers import BertTokenizer
from textbook import *
import modin.pandas as pd

tokenizer = BertTokenizer.from_pretrained('bert-base-cased')

d1 = MultiModalDataset(
    df=pd.read_json("data_cache/alphanli/train.jsonl", lines=True),
    template=lambda x: template_anli(x, LABEL2INT['anli']),
    renderers=[lambda x: renderer_text(x, tokenizer)],
)
bt1 = BatchTool(tokenizer, source="anli")
i1 = DataLoader(d1, batch_sampler=TokenBasedSampler(d1, batch_size=64), collate_fn=bt1.collate_fn)

2. Create a multitask dataset with multiple datasets

from transformers import BertTokenizer
from textbook import *
import modin.pandas as pd

tokenizer = BertTokenizer.from_pretrained('bert-base-cased')

# add additional tokens for each task as special `cls_token`
tokenizer.add_special_tokens({"additional_special_tokens": [
        "[ANLI]", "[HELLASWAG]"
]})

d1 = MultiModalDataset(
    df=pd.read_json("data_cache/alphanli/train.jsonl", lines=True),
    template=lambda x: template_anli(x, LABEL2INT['anli']),
    renderers=[lambda x: renderer_text(x, tokenizer, "[ANLI]")],
)
bt1 = BatchTool(tokenizer, source="anli")
i1 = DataLoader(d1, batch_sampler=TokenBasedSampler(d1, batch_size=64), collate_fn=bt1.collate_fn)

d2 = MultiModalDataset(
        df=pd.read_json("data_cache/hellaswag/train.jsonl", lines=True),
        template=lambda x: template_hellaswag(x, LABEL2INT['hellaswag']),
        renderers=[lambda x: renderer_text(x, tokenizer, "[HELLASWAG]")],
    )
bt2 = BatchTool(tokenizer, source="hellaswag")
i2 = DataLoader(d2, batch_sampler=TokenBasedSampler(d1, batch_size=64), collate_fn=bt2.collate_fn)

d = MultiTaskDataset([i1, i2], shuffle=False)

#! batch size must be 1 for multitaskdataset, because we already batched in each sub dataset.
for batch in DataLoader(d, batch_size=1, collate_fn=BatchTool.uncollate_fn):

    pass

    # {
    #     "source": "anli" or "hellaswag",
    #     "labels": ...,
    #     "input_ids": ...,
    #     "attentions": ...,
    #     "token_type_ids": ...,
    #     "images": ...,
    # }