def test_standalone_pandas_datasource(test_folder_connection_path):
datasource = PandasDatasource('PandasCSV',
base_directory=test_folder_connection_path)
assert datasource.get_available_data_asset_names() == {"default": ["test"]}
manual_batch_kwargs = PathBatchKwargs(
path=os.path.join(str(test_folder_connection_path), "test.csv"))
# Get the default (subdir_path) generator
generator = datasource.get_generator()
auto_batch_kwargs = generator.yield_batch_kwargs("test")
assert manual_batch_kwargs["path"] == auto_batch_kwargs["path"]
# Include some extra kwargs...
# Note that we are using get_data_asset NOT get_batch here, since we are standalone (no batch concept)
dataset = datasource.get_data_asset("test",
generator_name="default",
batch_kwargs=auto_batch_kwargs,
sep=",",
header=0,
index_col=0)
assert isinstance(dataset, PandasDataset)
assert (dataset["col_1"] == [1, 2, 3, 4, 5]).all()
## A datasource should always return an object with a typed batch_id
assert isinstance(dataset.batch_kwargs, PathBatchKwargs)
assert isinstance(dataset.batch_id, BatchId)
assert isinstance(dataset.batch_fingerprint, BatchFingerprint)
def test_standalone_pandas_datasource(test_folder_connection_path):
datasource = PandasDatasource('PandasCSV', base_directory=test_folder_connection_path)
assert datasource.get_available_data_asset_names() == {"default": {"test"}}
manual_batch_kwargs = datasource.build_batch_kwargs(os.path.join(str(test_folder_connection_path), "test.csv"))
# Get the default (subdir_path) generator
generator = datasource.get_generator()
auto_batch_kwargs = generator.yield_batch_kwargs("test")
assert manual_batch_kwargs["path"] == auto_batch_kwargs["path"]
# Include some extra kwargs...
dataset = datasource.get_batch("test", batch_kwargs=auto_batch_kwargs, sep=",", header=0, index_col=0)
assert isinstance(dataset, PandasDataset)
assert (dataset["col_1"] == [1, 2, 3, 4, 5]).all()
def test_standalone_pandas_datasource(test_folder_connection_path):
datasource = PandasDatasource(
"PandasCSV",
batch_kwargs_generators={
"subdir_reader": {
"class_name": "SubdirReaderBatchKwargsGenerator",
"base_directory": test_folder_connection_path,
}
},
)
assert datasource.get_available_data_asset_names() == {
"subdir_reader": {
"names": [("test", "file")],
"is_complete_list": True
}
}
manual_batch_kwargs = PathBatchKwargs(
path=os.path.join(str(test_folder_connection_path), "test.csv"))
generator = datasource.get_batch_kwargs_generator("subdir_reader")
auto_batch_kwargs = generator.yield_batch_kwargs("test")
assert manual_batch_kwargs["path"] == auto_batch_kwargs["path"]
# Include some extra kwargs...
auto_batch_kwargs.update(
{"reader_options": {
"sep": ",",
"header": 0,
"index_col": 0
}})
batch = datasource.get_batch(batch_kwargs=auto_batch_kwargs)
assert isinstance(batch, Batch)
dataset = batch.data
assert (dataset["col_1"] == [1, 2, 3, 4, 5]).all()
assert len(dataset) == 5
# A datasource should always return an object with a typed batch_id
assert isinstance(batch.batch_kwargs, PathBatchKwargs)
assert isinstance(batch.batch_markers, BatchMarkers)