def unified_dataset(self):
"""Unified dataset for this project.
:return: Unified dataset for this project.
:rtype: :class:`~tamr_unify_client.dataset.resource.Dataset`
"""
alias = self.api_path + "/unifiedDataset"
resource_json = self.client.get(alias).successful().json()
return Dataset.from_json(self.client, resource_json, alias)
def create(self, creation_spec):
"""
Create a Dataset in Tamr
:param creation_spec: Dataset creation specification should be formatted as specified in the `Public Docs for Creating a Dataset <https://docs.tamr.com/reference#create-a-dataset>`_.
:type creation_spec: dict[str, str]
:returns: The created Dataset
:rtype: :class:`~tamr_unify_client.dataset.resource.Dataset`
"""
data = self.client.post(self.api_path,
json=creation_spec).successful().json()
return Dataset.from_json(self.client, data)
def published_cluster_stats(self):
"""Retrieves published cluster stats for this project.
:returns: The published cluster stats dataset.
:rtype: :class:`~tamr_unify_client.dataset.resource.Dataset`
"""
# Replace this workaround with a direct API call once API
# is fixed. APIs that need to work are: fetching the dataset and
# being able to call refresh on resulting dataset. Until then, we grab
# the dataset by constructing its name from the corresponding Unified Dataset's name
unified_dataset = self.unified_dataset()
name = unified_dataset.name + "_dedup_published_cluster_stats"
dataset = self.client.datasets.by_name(name)
path = self.api_path + "/publishedClusterStats"
return Dataset.from_json(self.client, dataset._data, path)
def published_clusters(self):
"""Published record clusters generated by Tamr's pair-matching model.
:returns: The published clusters represented as a dataset.
:rtype: :class:`~tamr_unify_client.dataset.resource.Dataset`
"""
unified_dataset = self.unified_dataset()
# Replace this workaround with a direct API call once API
# is fixed. APIs that need to work are: fetching the dataset and
# being able to call refresh on resulting dataset. Until then, we grab
# the dataset by constructing its name from the corresponding Unified Dataset's name
name = unified_dataset.name + "_dedup_published_clusters"
canonical = self.client.datasets.by_name(name)
resource_json = canonical._data
alias = self.api_path + "/publishedClusters"
return Dataset.from_json(self.client, resource_json, alias)