def get_dataset(self, identifier):
"""Get the handle for the dataset with given identifier from the data
store. Returns None if no dataset with the given identifier exists.
Parameters
----------
identifier : string
Unique dataset identifier
Returns
-------
vizier.datastore.base.DatasetHandle
"""
url = self.urls.get_dataset(identifier)
r = requests.get(url)
if r.status_code == 404:
return None
elif r.status_code != 200:
r.raise_for_status()
# The result is the workflow handle
obj = json.loads(r.text)
ds = deserialize.DATASET_DESCRIPTOR(obj)
return RemoteDatasetHandle(
identifier=ds.identifier,
columns=ds.columns,
row_count=ds.row_count,
rows=[deserialize.DATASET_ROW(row) for row in obj[labels.ROWS]],
store=self)
def create_dataset(self,
columns: List[DatasetColumn],
rows: List[DatasetRow],
properties: Optional[Dict[str, Any]] = None,
human_readable_name: str = "Untitled Dataset",
backend_options: Optional[List[Tuple[str, str]]] = None,
dependencies: Optional[List[str]] = None
) -> DatasetDescriptor:
"""Create a new dataset in the project datastore using the API. Expects
a list of columns and the rows for the dataset. All columns and rows
should have unique non-negative identifier (although this may not
be enforced by all backend datastores). Depending on the backend
datastore the given identifier may change. They are, however, required
to reference the given properties properly.
Raises ValueError if the backend datastore rejects the given dataset.
Parameters
----------
columns: list(vizier.datastore.dataset.DatasetColumn)
List of columns. It is expected that each column has a unique
identifier.
rows: list(vizier.datastore.dataset.DatasetRow)
List of dataset rows.
properties: dict, optional
Properties for dataset components
Returns
-------
vizier.datastore.dataset.DatasetDescriptor
"""
url = self.urls.create_dataset()
data:Dict[str, Any] = {
labels.COLUMNS: [serialize.DATASET_COLUMN(col) for col in columns],
labels.ROWS: [serialize.DATASET_ROW(row) for row in rows]
}
if not properties is None:
data[labels.PROPERTIES] = properties
# Send request. Raise exception if status code indicates that the
# request was not successful.
r = requests.post(url, json=data)
r.raise_for_status()
obj = json.loads(r.text)
return deserialize.DATASET_DESCRIPTOR(obj)
def create_dataset(self, columns, rows, annotations=None):
"""Create a new dataset in the project datastore using the API. Expects
a list of columns and the rows for the dataset. All columns and rows
should have unique non-negative identifier (although this may not
be enforced by all backend datastores). Depending on the backend
datastore the given identifier may change. They are, however, required
to reference the given annotations properly.
Raises ValueError if the backend datastore rejects the given dataset.
Parameters
----------
columns: list(vizier.datastore.dataset.DatasetColumn)
List of columns. It is expected that each column has a unique
identifier.
rows: list(vizier.datastore.dataset.DatasetRow)
List of dataset rows.
annotations: vizier.datastore.annotation.dataset.DatasetMetadata, optional
Annotations for dataset components
Returns
-------
vizier.datastore.dataset.DatasetDescriptor
"""
url = self.urls.create_dataset()
data = {
labels.COLUMNS: [serialize.DATASET_COLUMN(col) for col in columns],
labels.ROWS: [serialize.DATASET_ROW(row) for row in rows]
}
if not annotations is None:
data[labels.ANNOTATIONS] = [
serialize.ANNOTATION(a) for a in annotations.values
]
# Send request. Raise exception if status code indicates that the
# request was not successful.
r = requests.post(url, json=data)
r.raise_for_status()
obj = json.loads(r.text)
return deserialize.DATASET_DESCRIPTOR(obj)
def get_descriptor(self, identifier):
"""Get the descriptor for the dataset with given identifier from the
data store. Returns None if no dataset with the given identifier exists.
Parameters
----------
identifier : string
Unique dataset identifier
Returns
-------
vizier.datastore.base.DatasetDescriptor
"""
url = self.urls.get_dataset_descriptor(identifier)
r = requests.get(url)
if r.status_code == 404:
return None
elif r.status_code != 200:
r.raise_for_status()
# The result is the workflow handle
obj = json.loads(r.text)
return deserialize.DATASET_DESCRIPTOR(obj)