def update_dataset(self, dataset_key, **kwargs):
"""Update an existing dataset
Parameters
----------
description : str, optional
Dataset description
summary : str, optional
Dataset summary markdown
tags : list, optional
Dataset tags
license : {'Public Domain', 'PDDL', 'CC-0', 'CC-BY', 'ODC-BY',
'CC-BY-SA', 'ODC-ODbL', 'CC BY-NC', 'CC BY-NC-SA', 'Other'}
Dataset license
visibility : {'OPEN', 'PRIVATE'}, optional
Dataset visibility
files : dict, optional
File names and source URLs to add or update
Raises
------
RestApiException
If a server error occurs
Examples
--------
>>> import datadotworld as dw
>>> api_client = dw.api_client()
>>> api_client.update_dataset(
... 'username/test-dataset',
... tags=['demo', 'datadotworld']) # doctest: +SKIP
"""
request = self.__build_dataset_obj(
lambda: _swagger.DatasetPatchRequest(),
lambda name, url: _swagger.FileCreateOrUpdateRequest(
name=name,
source=_swagger.FileSourceCreateOrUpdateRequest(url=url)),
kwargs)
owner_id, dataset_id = parse_dataset_key(dataset_key)
try:
self._datasets_api.patch_dataset(owner_id, dataset_id, request)
except _swagger.rest.ApiException as e:
raise RestApiError(cause=e)
def add_files_via_url(self, dataset_key, files={}):
"""Add or update dataset files linked to source URLs
:param dataset_key: Dataset identifier, in the form of owner/id
:type dataset_key: str
:param files: Dict containing the name of files and metadata
Uses file name as a dict containing File description, labels and
source URLs to add or update (Default value = {})
*description and labels are optional.*
:type files: dict
:raises RestApiException: If a server error occurs
Examples
--------
>>> import datadotworld as dw
>>> url = 'http://www.acme.inc/example.csv'
>>> api_client = dw.api_client()
>>> api_client.add_files_via_url(
... 'username/test-dataset',
... 'example.csv': {
... 'url': url,
... 'labels': ['raw data'],
... 'description': 'file description'}) # doctest: +SKIP
"""
file_requests = [
_swagger.FileCreateOrUpdateRequest(
name=file_name,
source=_swagger.FileSourceCreateOrUpdateRequest(
url=file_info['url'],
expand_archive=file_info.get('expand_archive', False)),
description=file_info.get('description'),
labels=file_info.get('labels'),
) for file_name, file_info in files.items()
]
owner_id, dataset_id = parse_dataset_key(dataset_key)
try:
self._datasets_api.add_files_by_source(
owner_id, dataset_id,
_swagger.FileBatchUpdateRequest(files=file_requests))
except _swagger.rest.ApiException as e:
raise RestApiError(cause=e)
def add_files_via_url(self, dataset_key, files={}):
"""Add or update dataset files linked to source URLs
Parameters
----------
dataset_key : str
Dataset identifier, in the form of owner/id
files : dict
File names and source URLs to add or update
Raises
------
RestApiException
If a server error occurs
Examples
--------
>>> import datadotworld as dw
>>> url = 'http://www.acme.inc/example.csv'
>>> api_client = dw.api_client()
>>> api_client.add_files_via_url(
... 'username/test-dataset',
... {'example.csv': url}) # doctest: +SKIP
"""
file_requests = [
_swagger.FileCreateOrUpdateRequest(
name=name,
source=_swagger.FileSourceCreateOrUpdateRequest(url=url))
for name, url in files.items()
]
owner_id, dataset_id = parse_dataset_key(dataset_key)
try:
self._datasets_api.add_files_by_source(
owner_id, dataset_id,
_swagger.FileBatchUpdateRequest(files=file_requests))
except _swagger.rest.ApiException as e:
raise RestApiError(cause=e)