def _update_from_dataframe(self,
dataframe,
data_type_id=None,
name=None,
description=None):
"""
Serialize the specified DataFrame and replace the existing dataset.
Parameters
----------
dataframe : pandas.DataFrame
Data to serialize.
data_type_id : str, optional
Format to serialize to.
If None, the existing format is preserved.
Supported formats are:
'PlainText'
'GenericCSV'
'GenericTSV'
'GenericCSVNoHeader'
'GenericTSVNoHeader'
See the azureml.DataTypeIds class for constants.
name : str, optional
Name for the dataset.
If None, the name of the existing dataset is used.
description : str, optional
Description for the dataset.
If None, the name of the existing dataset is used.
"""
_not_none('dataframe', dataframe)
if data_type_id is None:
data_type_id = self.data_type_id
if name is None:
name = self.name
if description is None:
description = self.description
try:
output = BytesIO()
serialize_dataframe(output, data_type_id, dataframe)
raw_data = output.getvalue()
finally:
output.close()
self._upload_and_refresh(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 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 _update_from_dataframe(self, dataframe, data_type_id=None, name=None,
description=None):
"""
Serialize the specified DataFrame and replace the existing dataset.
Parameters
----------
dataframe : pandas.DataFrame
Data to serialize.
data_type_id : str, optional
Format to serialize to.
If None, the existing format is preserved.
Supported formats are:
'PlainText'
'GenericCSV'
'GenericTSV'
'GenericCSVNoHeader'
'GenericTSVNoHeader'
See the azureml.DataTypeIds class for constants.
name : str, optional
Name for the dataset.
If None, the name of the existing dataset is used.
description : str, optional
Description for the dataset.
If None, the name of the existing dataset is used.
"""
_not_none('dataframe', dataframe)
if data_type_id is None:
data_type_id = self.data_type_id
if name is None:
name = self.name
if description is None:
description = self.description
try:
output = BytesIO()
serialize_dataframe(output, data_type_id, dataframe)
raw_data = output.getvalue()
finally:
output.close()
self._upload_and_refresh(raw_data, data_type_id, name, description)
