def __init__(self, workspace, experiment, node_id, port_name, data_type_id): """ INTERNAL USE ONLY. Initialize an intermediate dataset. Parameters ---------- workspace : Workspace Parent workspace of the dataset. experiment : Experiment Parent experiment of the dataset. node_id : str Module node id from the experiment graph. port_name : str Output port of the module. data_type_id : str Serialization format of the raw data. See the azureml.DataTypeIds class for constants. """ _not_none('workspace', workspace) _not_none('experiment', experiment) _not_none_or_empty('node_id', node_id) _not_none_or_empty('port_name', port_name) _not_none_or_empty('data_type_id', data_type_id) self.workspace = workspace self.experiment = experiment self.node_id = node_id self.port_name = port_name self.data_type_id = data_type_id if is_supported(self.data_type_id): self.to_dataframe = self._to_dataframe
def __init__(self, workspace=None, metadata=None): """ INTERNAL USE ONLY. Initialize a dataset. Parameters ---------- workspace : Workspace Parent workspace of the dataset. metadata : dict Dictionary of dataset metadata as returned by the REST API. """ _not_none('metadata', metadata) _not_none('workspace', workspace) self.workspace = workspace self._metadata = metadata if is_supported(self.data_type_id): self.to_dataframe = self._to_dataframe if not self.is_example: self.update_from_raw_data = self._update_from_raw_data self.update_from_dataframe = self._update_from_dataframe