def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"tweet":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=[
"none", "anger", "joy", "sadness", "love", "sympathy",
"surprise", "fear"
]),
}),
homepage=_HOMEPAGE,
citation=_CITATION,
task_templates=[
TextClassification(text_column="tweet", label_column="label")
],
)
def _info(self):
# Labels: 0="Non-hate Speech", 1="Hate Speech"
features = datasets.Features({
"text":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=["0", "1"])
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
task_templates=[
TextClassification(text_column="text", label_column="label")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"news_title":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(
names=["Africa", "Health", "Nigeria", "Politics", "World"
]),
}),
homepage=
"https://github.com/uds-lsv/transfer-distant-transformer-african",
citation=_CITATION,
task_templates=[
TextClassification(text_column="news_title",
label_column="label")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{
"text": datasets.Value("string"),
"label": datasets.features.ClassLabel(
names=[
"Negative",
"Positive",
]
),
}
),
supervised_keys=None,
homepage="https://github.com/komari6/Arabic-twitter-corpus-AJGT",
citation=_CITATION,
task_templates=[TextClassification(text_column="text", label_column="label")],
)
def _info(self):
features = datasets.Features({
"review_body":
datasets.Value("string"),
"star_rating":
datasets.features.ClassLabel(names=["1", "2", "3", "4", "5"]),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage="https://github.com/wongnai/wongnai-corpus",
license=_LICENSE,
citation=_CITATION,
task_templates=[
TextClassification(text_column="review_body",
label_column="star_rating")
],
)
def test_remove_and_map_on_task_template(self):
features = Features({
"text": Value("string"),
"label": ClassLabel(names=("pos", "neg"))
})
task_templates = TextClassification(text_column="text",
label_column="label")
info = DatasetInfo(features=features, task_templates=task_templates)
dataset = Dataset.from_dict({
"text": ["A sentence."],
"label": ["pos"]
},
info=info)
def process(example):
return example
modified_dataset = dataset.remove_columns("label")
mapped_dataset = modified_dataset.map(process)
assert mapped_dataset.info.task_templates == []
def _info(self):
class_names = ["Sport", "Politic", "Business", "Entertainment"]
features = datasets.Features({
"text":
datasets.Value("string"),
"category":
datasets.ClassLabel(names=class_names),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage=
"https://github.com/ayehninnkhine/MyanmarNewsClassificationSystem",
license=_LICENSE,
citation=_CITATION,
task_templates=[
TextClassification(text_column="text", label_column="category")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{
"text": datasets.Value("string"),
"label": datasets.features.ClassLabel(
names=[
"1",
"2",
"3",
"4",
"5",
]
),
}
),
supervised_keys=None,
homepage="https://github.com/mohamedadaly/LABR",
citation=_CITATION,
task_templates=[TextClassification(text_column="text", label_column="label")],
)
def _info(self):
# This method specifies the datasets.DatasetInfo object which contains informations and typings for the dataset
if self.config.name == "first_domain": # This is the name of the configuration selected in BUILDER_CONFIGS above
features = datasets.Features(
{
"sequence": datasets.Value("string"),
"ECnumber": datasets.features.ClassLabel(names=["1", "2", "3", "4", "5", "6", "7"])
# TODO: specify the main classes of anzymes by name?
# These are the features of your dataset like images, labels ...
}
)
elif self.config.name == "second_domain": # This is an example to show how to have different features for "first_domain" and "second_domain"
features = datasets.Features(
{
"sequence": datasets.Value("string"),
"ECnumber_one": datasets.Value("string"),
"ECnumber_two": datasets.Value("string")
# These are the features of your dataset like images, labels ...
}
)
return datasets.DatasetInfo(
# This is the description that will appear on the datasets page.
description=_DESCRIPTION,
# This defines the different columns of the dataset and their types
features=features, # Here we define them above because they are different between the two configurations
# If there's a common (input, target) tuple from the features,
# specify them here. They'll be used if as_supervised=True in
# builder.as_dataset.
supervised_keys=None,
# Homepage of the dataset for documentation
homepage=_HOMEPAGE,
# License for the dataset if available
license=_LICENSE,
# Citation for the dataset
citation=_CITATION,
task_templates=[TextClassification(text_column="text", label_column="label")],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"category":
datasets.features.ClassLabel(names=[
"siyaset", "dunya", "ekonomi", "kultur", "saglik", "spor",
"teknoloji"
]),
"text":
datasets.Value("string"),
}),
supervised_keys=None,
# Homepage of the dataset for documentation
homepage=_HOMEPAGE,
# License for the dataset if available
license=_LICENSE,
# Citation for the dataset
citation=_CITATION,
task_templates=[
TextClassification(text_column="text", label_column="category")
],
)
def _info(self):
features = datasets.Features({
"label":
datasets.features.ClassLabel(names=[
"1 star",
"2 star",
"3 stars",
"4 stars",
"5 stars",
]),
"text":
datasets.Value("string"),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
task_templates=[
TextClassification(text_column="text", label_column="label")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"text":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=[
"Web",
"Panorama",
"International",
"Wirtschaft",
"Sport",
"Inland",
"Etat",
"Wissenschaft",
"Kultur",
]),
}),
homepage="https://tblock.github.io/10kGNAD/",
task_templates=[
TextClassification(text_column="text", label_column="label")
],
)
def _info(self):
if self.config.name == "Coarse_Grained":
features = datasets.Features(
{
"tweet": datasets.Value("string"),
"label": datasets.features.ClassLabel(names=["Abusive/Offensive", "Normal"]),
# These are the features of your dataset like images, labels ...
}
)
if self.config.name == "Fine_Grained":
features = datasets.Features(
{
"tweet": datasets.Value("string"),
"label": datasets.features.ClassLabel(
names=["Abusive/Offensive", "Normal", "Religious Hate", "Sexism", "Profane/Untargeted"]
),
# These are the features of your dataset like images, labels ...
}
)
return datasets.DatasetInfo(
# This is the description that will appear on the datasets page.
description=_DESCRIPTION,
# This defines the different columns of the dataset and their types
features=features, # Here we define them above because they are different between the two configurations
# If there's a common (input, target) tuple from the features, uncomment supervised_keys line below and
# specify them. They'll be used if as_supervised=True in builder.as_dataset.
# supervised_keys=("sentence", "label"),
# Homepage of the dataset for documentation
homepage=_HOMEPAGE,
# License for the dataset if available
license=_LICENSE,
# Citation for the dataset
citation=_CITATION,
task_templates=[TextClassification(text_column="tweet", label_column="label")],
)
def test_align_with_features(self):
task = TextClassification(text_column="input_text", label_column="input_label")
self.assertEqual(task.label_schema["labels"], ClassLabel)
task = task.align_with_features(Features({"input_label": ClassLabel(names=self.labels)}))
self.assertEqual(task.label_schema["labels"], ClassLabel(names=self.labels))
def test_column_mapping(self):
task = TextClassification(text_column="input_text", label_column="input_label")
self.assertDictEqual({"input_text": "text", "input_label": "labels"}, task.column_mapping)
def _info(self):
features = datasets.Features(
{
"text": datasets.Value("string"),
"label": datasets.features.ClassLabel(
names=[
"activate_my_card",
"age_limit",
"apple_pay_or_google_pay",
"atm_support",
"automatic_top_up",
"balance_not_updated_after_bank_transfer",
"balance_not_updated_after_cheque_or_cash_deposit",
"beneficiary_not_allowed",
"cancel_transfer",
"card_about_to_expire",
"card_acceptance",
"card_arrival",
"card_delivery_estimate",
"card_linking",
"card_not_working",
"card_payment_fee_charged",
"card_payment_not_recognised",
"card_payment_wrong_exchange_rate",
"card_swallowed",
"cash_withdrawal_charge",
"cash_withdrawal_not_recognised",
"change_pin",
"compromised_card",
"contactless_not_working",
"country_support",
"declined_card_payment",
"declined_cash_withdrawal",
"declined_transfer",
"direct_debit_payment_not_recognised",
"disposable_card_limits",
"edit_personal_details",
"exchange_charge",
"exchange_rate",
"exchange_via_app",
"extra_charge_on_statement",
"failed_transfer",
"fiat_currency_support",
"get_disposable_virtual_card",
"get_physical_card",
"getting_spare_card",
"getting_virtual_card",
"lost_or_stolen_card",
"lost_or_stolen_phone",
"order_physical_card",
"passcode_forgotten",
"pending_card_payment",
"pending_cash_withdrawal",
"pending_top_up",
"pending_transfer",
"pin_blocked",
"receiving_money",
"Refund_not_showing_up",
"request_refund",
"reverted_card_payment?",
"supported_cards_and_currencies",
"terminate_account",
"top_up_by_bank_transfer_charge",
"top_up_by_card_charge",
"top_up_by_cash_or_cheque",
"top_up_failed",
"top_up_limits",
"top_up_reverted",
"topping_up_by_card",
"transaction_charged_twice",
"transfer_fee_charged",
"transfer_into_account",
"transfer_not_received_by_recipient",
"transfer_timing",
"unable_to_verify_identity",
"verify_my_identity",
"verify_source_of_funds",
"verify_top_up",
"virtual_card_not_working",
"visa_or_mastercard",
"why_verify_identity",
"wrong_amount_of_cash_received",
"wrong_exchange_rate_for_cash_withdrawal",
]
),
}
)
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
task_templates=[TextClassification(text_column="text", label_column="label")],
)