def setUp(self):
self.json_data_source = SquadDataSource.from_config(
SquadDataSource.Config(
train_filename=tests_module.test_file("squad_tiny.json"),
eval_filename=None,
test_filename=None,
)
)
self.tsv_data_source = SquadDataSource.from_config(
SquadDataSource.Config(
train_filename=tests_module.test_file("squad_tiny.tsv"),
eval_filename=None,
test_filename=None,
)
)
self.tensorizer_with_wordpiece = SquadTensorizer.from_config(
SquadTensorizer.Config(
tokenizer=WordPieceTokenizer.Config(
wordpiece_vocab_path="pytext/data/test/data/wordpiece_1k.txt"
),
max_seq_len=250,
)
)
self.tensorizer_with_alphanumeric = SquadTensorizer.from_config(
SquadTensorizer.Config(
tokenizer=Tokenizer.Config(split_regex=r"\W+"), max_seq_len=250
)
)
class ModelInput(BaseModel.Config.ModelInput):
squad_input: SquadTensorizer.Config = SquadTensorizer.Config()
has_answer: LabelTensorizer.Config = LabelTensorizer.Config(
column="has_answer")