def __init__(self, workspace_id, authorization_token, endpoint=Endpoints.default):
"""
Initialize a workspace.
Parameters
----------
workspace_id : str
Unique identifier for the existing workspace. Can be obtained from
the URL in ML Studio when editing a workspace.
authorization_token: str
Access token for the workspace. Can be the primary or secondary
token managed in ML Studio.
endpoint: str
URL of the endpoint to connect to. Specify this only if you host
ML Studio on your own server(s).
"""
_not_none_or_empty('workspace_id', workspace_id)
_not_none_or_empty('authorization_token', authorization_token)
_not_none_or_empty('endpoint', endpoint)
self.workspace_id = workspace_id
self.authorization_token = authorization_token
self._rest = _RestClient(endpoint, authorization_token)
self.datasets = Datasets(workspace=self)
self.user_datasets = Datasets(workspace=self, example_filter=False)
self.example_datasets = Datasets(workspace=self, example_filter=True)
self.experiments = Experiments(workspace=self)
self.user_experiments = Experiments(workspace=self, example_filter=False)
self.example_experiments = Experiments(workspace=self, example_filter=True)
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, 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 serialize_dataframe(writer, data_type_id, dataframe):
"""
Serialize a dataframe.
Parameters
----------
writer : file
File-like object to write to. Must be opened in binary mode.
data_type_id : dict
Serialization format to use.
See the azureml.DataTypeIds class for constants.
dataframe: pandas.DataFrame
Dataframe to serialize.
"""
_not_none('writer', writer)
_not_none_or_empty('data_type_id', data_type_id)
_not_none('dataframe', dataframe)
serializer = _SERIALIZERS.get(data_type_id)
if serializer is None:
raise UnsupportedDatasetTypeError(data_type_id)
serializer[0](writer=writer, dataframe=dataframe)
def serialize_dataframe(writer, data_type_id, dataframe):
"""
Serialize a dataframe.
Parameters
----------
writer : file
File-like object to write to. Must be opened in binary mode.
data_type_id : dict
Serialization format to use.
See the azureml.DataTypeIds class for constants.
dataframe: pandas.DataFrame
Dataframe to serialize.
"""
_not_none('writer', writer)
_not_none_or_empty('data_type_id', data_type_id)
_not_none('dataframe', dataframe)
serializer = _SERIALIZERS.get(data_type_id)
if serializer is None:
raise UnsupportedDatasetTypeError(data_type_id)
serializer[0](writer=writer, dataframe=dataframe)
def deserialize_dataframe(reader, data_type_id):
"""
Deserialize a dataframe.
Parameters
----------
reader : file
File-like object to read from. Must be opened in binary mode.
data_type_id : dict
Serialization format of the raw data.
See the azureml.DataTypeIds class for constants.
Returns
-------
pandas.DataFrame
Dataframe object.
"""
_not_none('reader', reader)
_not_none_or_empty('data_type_id', data_type_id)
serializer = _SERIALIZERS.get(data_type_id)
if serializer is None:
raise UnsupportedDatasetTypeError(data_type_id)
return serializer[1](reader=reader)
def deserialize_dataframe(reader, data_type_id):
"""
Deserialize a dataframe.
Parameters
----------
reader : file
File-like object to read from. Must be opened in binary mode.
data_type_id : dict
Serialization format of the raw data.
See the azureml.DataTypeIds class for constants.
Returns
-------
pandas.DataFrame
Dataframe object.
"""
_not_none('reader', reader)
_not_none_or_empty('data_type_id', data_type_id)
serializer = _SERIALIZERS.get(data_type_id)
if serializer is None:
raise UnsupportedDatasetTypeError(data_type_id)
return serializer[1](reader=reader)
def __init__(self,
workspace_id=None,
authorization_token=None,
endpoint=None):
"""
Initialize a workspace.
Parameters
----------
workspace_id : str
Unique identifier for the existing workspace. Can be obtained from
the URL in ML Studio when editing a workspace.
authorization_token: str
Access token for the workspace. Can be the primary or secondary
token managed in ML Studio.
endpoint: str
URL of the endpoint to connect to. Specify this only if you host
ML Studio on your own server(s).
Parameters that are omitted will be read from ~/.azureml/settings.ini:
[workspace]
id = abcd1234
authorization_token = abcd1234
endpoint = https://studio.azureml.net
"""
workspace_id, authorization_token, endpoint, management_endpoint = _get_workspace_info(
workspace_id, authorization_token, endpoint, None)
_not_none_or_empty('workspace_id', workspace_id)
_not_none_or_empty('authorization_token', authorization_token)
_not_none_or_empty('endpoint', endpoint)
self.workspace_id = workspace_id
self.authorization_token = authorization_token
self.api_endpoint = endpoint
self.management_endpoint = management_endpoint
self._rest = _RestClient(endpoint, authorization_token)
self.datasets = Datasets(workspace=self)
self.user_datasets = Datasets(workspace=self, example_filter=False)
self.example_datasets = Datasets(workspace=self, example_filter=True)
self.experiments = Experiments(workspace=self)
self.user_experiments = Experiments(workspace=self,
example_filter=False)
self.example_experiments = Experiments(workspace=self,
example_filter=True)
def add_from_dataframe(self, dataframe, data_type_id, name, description):
"""
Serialize the specified DataFrame and upload it as a new dataset.
Parameters
----------
dataframe : pandas.DataFrame
Data to serialize.
data_type_id : str
Format to serialize to.
Supported formats are:
'PlainText'
'GenericCSV'
'GenericTSV'
'GenericCSVNoHeader'
'GenericTSVNoHeader'
See the azureml.DataTypeIds class for constants.
name : str
Name for the new dataset.
description : str
Description for the new dataset.
Returns
-------
SourceDataset
Dataset that was just created.
Use open(), read_as_binary(), read_as_text() or to_dataframe() on
the dataset object to get its contents as a stream, bytes, str or
pandas DataFrame.
"""
_not_none('dataframe', dataframe)
_not_none_or_empty('data_type_id', data_type_id)
_not_none_or_empty('name', name)
_not_none_or_empty('description', description)
try:
output = BytesIO()
serialize_dataframe(output, data_type_id, dataframe)
raw_data = output.getvalue()
finally:
output.close()
return self._upload(raw_data, data_type_id, name, description)
def add_from_dataframe(self, dataframe, data_type_id, name, description):
"""
Serialize the specified DataFrame and upload it as a new dataset.
Parameters
----------
dataframe : pandas.DataFrame
Data to serialize.
data_type_id : str
Format to serialize to.
Supported formats are:
'PlainText'
'GenericCSV'
'GenericTSV'
'GenericCSVNoHeader'
'GenericTSVNoHeader'
See the azureml.DataTypeIds class for constants.
name : str
Name for the new dataset.
description : str
Description for the new dataset.
Returns
-------
SourceDataset
Dataset that was just created.
Use open(), read_as_binary(), read_as_text() or to_dataframe() on
the dataset object to get its contents as a stream, bytes, str or
pandas DataFrame.
"""
_not_none('dataframe', dataframe)
_not_none_or_empty('data_type_id', data_type_id)
_not_none_or_empty('name', name)
_not_none_or_empty('description', description)
try:
output = BytesIO()
serialize_dataframe(output, data_type_id, dataframe)
raw_data = output.getvalue()
finally:
output.close()
return self._upload(raw_data, data_type_id, name, description)
def __init__(self, workspace_id = None, authorization_token = None, endpoint=None):
"""
Initialize a workspace.
Parameters
----------
workspace_id : str
Unique identifier for the existing workspace. Can be obtained from
the URL in ML Studio when editing a workspace.
authorization_token: str
Access token for the workspace. Can be the primary or secondary
token managed in ML Studio.
endpoint: str
URL of the endpoint to connect to. Specify this only if you host
ML Studio on your own server(s).
Parameters that are omitted will be read from ~/.azureml/settings.ini:
[workspace]
id = abcd1234
authorization_token = abcd1234
endpoint = https://studio.azureml.net
"""
workspace_id, authorization_token, endpoint, management_endpoint = _get_workspace_info(workspace_id, authorization_token, endpoint, None)
_not_none_or_empty('workspace_id', workspace_id)
_not_none_or_empty('authorization_token', authorization_token)
_not_none_or_empty('endpoint', endpoint)
self.workspace_id = workspace_id
self.authorization_token = authorization_token
self.api_endpoint = endpoint
self.management_endpoint = management_endpoint
self._rest = _RestClient(endpoint, authorization_token)
self.datasets = Datasets(workspace=self)
self.user_datasets = Datasets(workspace=self, example_filter=False)
self.example_datasets = Datasets(workspace=self, example_filter=True)
self.experiments = Experiments(workspace=self)
self.user_experiments = Experiments(workspace=self, example_filter=False)
self.example_experiments = Experiments(workspace=self, example_filter=True)
def add_from_raw_data(self, raw_data, data_type_id, name, description):
"""
Upload already serialized raw data as a new dataset.
Parameters
----------
raw_data: bytes
Dataset contents to upload.
data_type_id : str
Serialization format of the raw data.
Supported formats are:
'PlainText'
'GenericCSV'
'GenericTSV'
'GenericCSVNoHeader'
'GenericTSVNoHeader'
'ARFF'
See the azureml.DataTypeIds class for constants.
name : str
Name for the new dataset.
description : str
Description for the new dataset.
Returns
-------
SourceDataset
Dataset that was just created.
Use open(), read_as_binary(), read_as_text() or to_dataframe() on
the dataset object to get its contents as a stream, bytes, str or
pandas DataFrame.
"""
_not_none('raw_data', raw_data)
_not_none_or_empty('data_type_id', data_type_id)
_not_none_or_empty('name', name)
_not_none_or_empty('description', description)
return self._upload(raw_data, data_type_id, name, description)
def add_from_raw_data(self, raw_data, data_type_id, name, description):
"""
Upload already serialized raw data as a new dataset.
Parameters
----------
raw_data: bytes
Dataset contents to upload.
data_type_id : str
Serialization format of the raw data.
Supported formats are:
'PlainText'
'GenericCSV'
'GenericTSV'
'GenericCSVNoHeader'
'GenericTSVNoHeader'
'ARFF'
See the azureml.DataTypeIds class for constants.
name : str
Name for the new dataset.
description : str
Description for the new dataset.
Returns
-------
SourceDataset
Dataset that was just created.
Use open(), read_as_binary(), read_as_text() or to_dataframe() on
the dataset object to get its contents as a stream, bytes, str or
pandas DataFrame.
"""
_not_none('raw_data', raw_data)
_not_none_or_empty('data_type_id', data_type_id)
_not_none_or_empty('name', name)
_not_none_or_empty('description', description)
return self._upload(raw_data, data_type_id, name, description)
def is_supported(data_type_id):
"""Return if a serializer is available for the specified format."""
_not_none_or_empty('data_type_id', data_type_id)
return _SERIALIZERS.get(data_type_id) is not None
def is_supported(data_type_id):
"""Return if a serializer is available for the specified format."""
_not_none_or_empty('data_type_id', data_type_id)
return _SERIALIZERS.get(data_type_id) is not None
