def _info(self):
# ToDo: Consider adding an alternate configuration for the entity slots. The default is to only return the intent labels.
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"text":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=[
"ComparePlaces",
"RequestRide",
"GetWeather",
"SearchPlace",
"GetPlaceDetails",
"ShareCurrentLocation",
"GetTrafficInformation",
"BookRestaurant",
"GetDirections",
"ShareETA",
]),
}),
homepage=
"https://github.com/sonos/nlu-benchmark/tree/master/2016-12-built-in-intents",
citation=_CITATION,
task_templates=[
TextClassification(text_column="text", label_column="label")
],
)
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):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"text":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=[
"saree",
"kamel",
"mutakareb",
"mutadarak",
"munsareh",
"madeed",
"mujtath",
"ramal",
"baseet",
"khafeef",
"taweel",
"wafer",
"hazaj",
"rajaz",
]),
}),
supervised_keys=None,
homepage="https://github.com/zaidalyafeai/MetRec",
citation=_CITATION,
task_templates=[
TextClassification(text_column="text", label_column="label")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"label":
datasets.features.ClassLabel(names=[
"fragment",
"statement",
"question",
"command",
"rhetorical question",
"rhetorical command",
"intonation-dependent utterance",
]),
"text":
datasets.Value("string"),
}),
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({
"sentence":
datasets.Value("string"),
"target":
datasets.ClassLabel(names=[
"geogName",
"noEntity",
"orgName",
"persName",
"placeName",
"time",
]),
}),
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
task_templates=[
TextClassification(text_column="sentence",
label_column="target")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"news":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=[
"урлаг соёл",
"эдийн засаг",
"эрүүл мэнд",
"хууль",
"улс төр",
"спорт",
"технологи",
"боловсрол",
"байгал орчин",
]),
}),
homepage="http://eduge.mn",
task_templates=[
TextClassification(
text_column="news",
label_column="label",
)
],
)
def test_value_error_unique_labels(self):
with self.assertRaises(ValueError):
# Add duplicate labels
labels = self.labels + self.labels[:1]
task = TextClassification(text_column="input_text",
label_column="input_label",
labels=labels)
self.assertEqual("text-classification", task.task)
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 _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{"text": datasets.Value("string"), "label": datasets.features.ClassLabel(names=["neg", "pos"])}
),
supervised_keys=None,
homepage="http://ai.stanford.edu/~amaas/data/sentiment/",
citation=_CITATION,
task_templates=[TextClassification(text_column="text", label_column="label")],
)
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 = ["sadness", "joy", "love", "anger", "fear", "surprise"]
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{"text": datasets.Value("string"), "label": datasets.ClassLabel(names=class_names)}
),
supervised_keys=("text", "label"),
homepage=_URL,
citation=_CITATION,
task_templates=[TextClassification(text_column="text", label_column="label")],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{
"sentence": datasets.Value("string"),
"sentiment": datasets.ClassLabel(names=["negative", "positive"]),
}
),
citation=_CITATION,
homepage=_HOMEPAGE,
task_templates=[TextClassification(text_column="sentence", label_column="sentiment")],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{
"texts": datasets.Value("string"),
"category": datasets.features.ClassLabel(names=["pos", "neu", "neg", "q"]),
}
),
supervised_keys=None,
homepage="https://github.com/PyThaiNLP/wisesight-sentiment",
citation=_CITATION,
task_templates=[TextClassification(text_column="texts", label_column="category")],
)
def _info(self):
features = datasets.Features({
"review_body":
datasets.Value("string"),
"review_summary":
datasets.Value("string"),
"star_rating":
datasets.ClassLabel(names=[str(i) for i in range(1, 6)]),
})
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
supervised_keys=None,
homepage="http://www.lsi.us.es/~fermin/index.php/Datasets",
license=_LICENSE,
citation=_CITATION,
task_templates=[
TextClassification(text_column="review_body",
label_column="star_rating"),
TextClassification(text_column="review_summary",
label_column="star_rating"),
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{
"text": datasets.Value("string"),
"label": datasets.features.ClassLabel(names=["1", "2"]),
}
),
supervised_keys=None,
homepage="https://course.fast.ai/datasets",
citation=_CITATION,
task_templates=[TextClassification(text_column="text", label_column="label")],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{
"language_id": datasets.ClassLabel(names=["AWA", "BRA", "MAG", "BHO", "HIN"]),
"text": datasets.Value("string"),
}
),
supervised_keys=None,
homepage="https://github.com/kmi-linguistics/vardial2018",
citation=_CITATION,
task_templates=[TextClassification(text_column="text", label_column="language_id")],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features(
{
"text": datasets.Value("string"),
"label": datasets.features.ClassLabel(
names=["Positive", "Negative", "Mixed_feelings", "unknown_state", "not-Tamil"]
),
}
),
homepage="https://dravidian-codemix.github.io/2020/datasets.html",
citation=_CITATION,
task_templates=[TextClassification(text_column="text", label_column="label")],
)
def _info(self):
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=datasets.Features(
{"sentence": datasets.Value("string"), "label": datasets.features.ClassLabel(names=_CLASSES)}
),
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
task_templates=[TextClassification(text_column="sentence", label_column="label")],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"text":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=["neg", "pos"])
}),
supervised_keys=[""],
homepage="http://www.cs.cornell.edu/people/pabo/movie-review-data/",
citation=_CITATION,
task_templates=[
TextClassification(text_column="text", label_column="label")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"label":
datasets.ClassLabel(names=["no-hate-speech", "hate-speech"]),
"tweet":
datasets.Value("string"),
}),
homepage=
"https://github.com/sharmaroshan/Twitter-Sentiment-Analysis",
citation=_CITATION,
task_templates=[
TextClassification(text_column="tweet", label_column="label")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"text":
datasets.Value("string"),
"label":
datasets.ClassLabel(names=["negative", "positive"])
}),
supervised_keys=None,
homepage="https://github.com/timpal0l/swedish-sentiment",
citation=_CITATION,
task_templates=[
TextClassification(text_column="text", label_column="label")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"review":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=["neg", "pos"]),
}),
supervised_keys=None,
homepage=
"https://github.com/TheophileBlard/french-sentiment-analysis-with-bert",
citation=_CITATION,
task_templates=[
TextClassification(text_column="review", label_column="label")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"tokens":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=["no_sarcasm", "sarcasm"]),
}),
supervised_keys=None,
homepage=_HOMEPAGE,
license=_LICENSE,
task_templates=[
TextClassification(text_column="tokens", label_column="label")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"sms":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=["ham", "spam"]),
}),
supervised_keys=("sms", "label"),
homepage=
"http://archive.ics.uci.edu/ml/datasets/SMS+Spam+Collection",
citation=_CITATION,
task_templates=[
TextClassification(text_column="sms", label_column="label")
],
)
def _info(self):
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"text":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(
names=["World", "Sports", "Business", "Sci/Tech"]),
}),
homepage=
"http://groups.di.unipi.it/~gulli/AG_corpus_of_news_articles.html",
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=["others", "happy", "sad", "angry"]),
}),
supervised_keys=None,
homepage="https://www.aclweb.org/anthology/S19-2005/",
citation=_CITATION,
task_templates=[
TextClassification(text_column="text", label_column="label")
],
)
def _info(self):
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=datasets.Features({
"sentence":
datasets.Value("string"),
"relation":
datasets.ClassLabel(names=[
"Cause-Effect(e1,e2)",
"Cause-Effect(e2,e1)",
"Component-Whole(e1,e2)",
"Component-Whole(e2,e1)",
"Content-Container(e1,e2)",
"Content-Container(e2,e1)",
"Entity-Destination(e1,e2)",
"Entity-Destination(e2,e1)",
"Entity-Origin(e1,e2)",
"Entity-Origin(e2,e1)",
"Instrument-Agency(e1,e2)",
"Instrument-Agency(e2,e1)",
"Member-Collection(e1,e2)",
"Member-Collection(e2,e1)",
"Message-Topic(e1,e2)",
"Message-Topic(e2,e1)",
"Product-Producer(e1,e2)",
"Product-Producer(e2,e1)",
"Other",
]),
}),
# 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=datasets.info.SupervisedKeysData(
input="sentence", output="relation"),
# Homepage of the dataset for documentation
homepage=
"https://semeval2.fbk.eu/semeval2.php?location=tasks&taskid=11",
citation=_CITATION,
task_templates=[
TextClassification(text_column="sentence",
label_column="relation")
],
)
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):
# TODO: This method specifies the datasets.DatasetInfo object which contains informations and typings for the dataset
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=datasets.Features({
"text":
datasets.Value("string"),
"label":
datasets.features.ClassLabel(names=["ele", "int", "adv"])
}),
supervised_keys=[""],
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
task_templates=[
TextClassification(text_column="text", 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")
],
)