def test_fail_using_reserved_words():
# This issue was reported and maybe gets resolved: https://github.com/huggingface/datasets/issues/1110
ds = Dataset.from_dict({
"a": [{
"a": 1,
"b": "two"
} for _ in range(0, 100)],
"_type": ["whatever" for _ in range(0, 100)],
})
split = ds.train_test_split()
new_ds = Dataset.from_datasets(split.values())
assert len(new_ds) == len(ds)
ds = ds.map(
lambda example: {
"new_field": {
"c": str(example["a"]["a"]),
"d": f"this {example['a']['b']}"
}
})
split = ds.train_test_split()
with pytest.raises(TypeError):
Dataset.from_datasets(split.values())
def dataset() -> Dataset:
data = {
"text": ["Test", "this", "shaight", "!"],
"label": ["0", "1", "0", "0"]
}
return Dataset.from_dict(data)
def test_extending_vocab_with_weights_file(pipeline_config, dataset, dataset2,
capsys, caplog):
pipeline = Pipeline.from_config(pipeline_config)
# create vocab
pipeline.create_vocab([dataset.to_instances(pipeline)])
# extending the vocab with the weights file available should apply the pretrained weights
pipeline.create_vocab([dataset2.to_instances(pipeline)])
instance = pipeline.head.featurize("this")
instance.index_fields(pipeline.vocab)
assert_allclose(
pipeline.backbone.embedder(instance.as_tensor_dict()["text"]),
torch.tensor([[0.25, 0.75]]),
)
# extending the vocab with the weights file deleted should trigger a warning
Path(pipeline_config["features"]["word"]["weights_file"]).unlink()
ds = Dataset.from_dict({"text": ["that"], "label": ["good"]})
pipeline.create_vocab([ds.to_instances(pipeline)])
assert caplog.record_tuples[-1][
0] == "allennlp.modules.token_embedders.embedding"
assert caplog.record_tuples[-1][1] == 30
assert (
"Embedding at model_path, "
"_head.backbone.embedder.token_embedder_word cannot locate the pretrained_file."
in caplog.record_tuples[-1][2])
def test_extending_vocab_with_weights_file(pipeline_config, dataset, dataset2,
deactivate_pipeline_trainer,
caplog):
pipeline = Pipeline.from_config(pipeline_config)
# create vocab
pipeline.train(
output="dummy",
training=dataset,
)
# extending the vocab with the weights file available should apply the pretrained weights
pipeline.train(
output="dummy",
training=dataset2,
)
instance = pipeline.head.featurize("this")
instance.index_fields(pipeline.vocab)
assert_allclose(
pipeline.backbone.embedder(instance.as_tensor_dict()["text"]),
torch.tensor([[0.25, 0.75]]),
)
# extending the vocab with the weights file deleted should trigger a warning
logging.captureWarnings(True)
Path(pipeline_config["features"]["word"]["weights_file"]).unlink()
pipeline.train(
output="dummy",
training=Dataset.from_dict({
"text": ["that"],
"label": ["good"]
}),
)
assert caplog.records[0].module == "embedding"
assert "cannot locate the pretrained_file" in caplog.records[0].message
def dataset():
return Dataset.from_dict(
{
"text": ["this is", "a test"],
"label": ["a", "b"],
}
)
def training_dataset() -> Dataset:
"""Creating the dataframe."""
data = {
"record1": [
{
"@first_name": "Hans",
"@last_name": "Peter"
},
{
"@first_name": "Heinrich",
"@last_name": "Meier"
},
{
"@first_name": "Hans",
"@last_name": "Peter"
},
],
"record2": [
{
"@first_name": "Hans",
"@last_name": "Petre"
},
{
"@first_name": "Heinz",
"@last_name": "Meier"
},
{
"@first_name": "Hansel",
"@last_name": "Peter"
},
],
"label": ["duplicate", "not_duplicate", "duplicate"],
}
return Dataset.from_dict(data)
def training_dataset() -> Dataset:
"""Creating the dataframe."""
data = {
"text": [
"this is a text",
"my name is dani",
"this is a table",
"my name is paco",
],
}
return Dataset.from_dict(data)
def dataset(tmp_path) -> Dataset:
data = {
"text":
["A common text", "This is why you get", "Seriosly?, I'm not sure"],
"label": ["one", "zero", "zero"],
}
ds = Dataset.from_dict(data)
# we save and load it here to be able to lazily read from it
ds_path = tmp_path / "test_pipeline_datasets" / "dataset"
ds.save_to_disk(str(ds_path))
return Dataset.load_from_disk(str(ds_path))
def test_trainer_configs(configurations_path):
configs = _read_configs(configurations_path, "Trainer")
pipeline = Pipeline.from_config(
{
"name": "test",
"head": {"type": "TextClassification", "labels": ["pos", "neg"]},
}
)
dataset = Dataset.from_dict({"text": ["test"], "label": ["pos"]})
linear = nn.Linear(2, 2)
for config_name, config in configs.items():
assert isinstance(config, TrainerConfiguration)
trainer = Trainer(
pipeline=pipeline, train_dataset=dataset, trainer_config=config
)
assert isinstance(trainer.trainer, pytorch_lightning.Trainer)
def training_dataset() -> Dataset:
"""Creating the dataframe."""
data = {
"text": [
"The most common audits were about waste and recycling.",
"The company fabricates plastic chairs.",
],
"entities": [
[
{
"start": 34,
"end": 39,
"label": "PN",
"text": "waste"
},
{
"start": 16,
"end": 22,
"label": "QTY",
"text": "audits"
},
],
[
{
"start": 4,
"end": 11,
"label": "OBJECT",
"text": "company"
},
{
"start": 31,
"end": 37,
"label": "SUBJECT",
"text": "chairs"
},
],
],
"label": ["Message-Topic(e1,e2)", "Product-Producer(e2,e1)"],
}
return Dataset.from_dict(data)
def test_from_dict():
ds = Dataset.from_dict({"a": [1, 2, 3], "b": [4, 5, 6]})
assert ds.dataset.column_names == ["a", "b"]
assert ds["a"] == [1, 2, 3]
assert len(ds) == 3
def dataset2() -> Dataset:
data = {"text": ["this"], "label": ["good"]}
return Dataset.from_dict(data)
def dataset() -> Dataset:
"""Creating the dataset"""
data = {"text": ["This is a simple test"], "label": ["a"]}
return Dataset.from_dict(data)
def dataset() -> Dataset:
data = {
"text": ["test", "this", "shaight", "good"],
"label": ["good", "good", "bad", "good"],
}
return Dataset.from_dict(data)
def valid_dataset():
data = {
"text": ["and what about the validation", "do not forget this one"],
"label": ["bad", "good"],
}
return Dataset.from_dict(data)
def train_dataset():
data = {
"text": ["this is a test", "and another one"],
"label": ["good", "bad"]
}
return Dataset.from_dict(data)
