def test_dataset_schema_bug():
schema = {"abc": Primitive("int32"), "def": "int64"}
ds = Dataset("./data/schema_bug", schema=schema, shape=(100, ))
ds.flush()
ds2 = Dataset("./data/schema_bug", schema=schema, shape=(100, ))
schema = {
"abc": "uint8",
"def": {
"ghi": Tensor((100, 100)),
"rst": Tensor((100, 100, 100)),
},
}
ds = Dataset("./data/schema_bug_2", schema=schema, shape=(100, ))
ds.flush()
ds2 = Dataset("./data/schema_bug_2", schema=schema, shape=(100, ))
def test_primitive_repr():
primitve_object = Primitive(int)
assert "'int64'" == primitve_object.__repr__()
def test_primitive_str():
primitve_object = Primitive("int64")
assert "'int64'" == primitve_object.__str__()
)
sentences = list(df.sentence.values)
labels = list(df.label.values)
data = list(zip(sentences, labels))
@transform(schema=self.schema)
def load_transform(sample):
return {"sentence": sample[0], "labels": sample[1]}
ds = load_transform(data)
return ds.store(self.tag)
def main(url, tag, schema):
R = Retrieve(url, tag, schema)
R.fetch()
R.unpack()
R.push()
if __name__ == "__main__":
url = "https://nyu-mll.github.io/CoLA/cola_public_1.1.zip"
tag = "activeloop/CoLA"
schema = {
"sentence": Text(shape=(None, ), max_shape=(500, )),
"labels": Primitive(dtype="int64"),
}
main(url, tag, schema)