DownloadARFFGzip#

class capymoa.datasets.downloader.DownloadARFFGzip[source]#

Bases: DownloadableDataset

download(working_directory: Path) Path[source]#

Download the dataset and return the path to the downloaded dataset within the working directory.

Parameters:

working_directory – The directory to download the dataset to.

Returns:

The path to the downloaded dataset within the working directory.

extract(stream_archive: Path) Path[source]#

Extract the dataset from the archive and return the path to the extracted dataset.

Parameters:

stream_archive – The path to the archive containing the dataset.

Returns:

The path to the extracted dataset.

CLI_help() str[source]#

Return cli help string for the stream.

__init__(
directory: str = PosixPath('data'),
auto_download: bool = True,
CLI: str | None = None,
schema: str | None = None,
)[source]#
get_moa_stream() InstanceStream | None[source]#

Get the MOA stream object if it exists.

get_path()[source]#
get_schema() Schema[source]#

Return the schema of the stream.

has_more_instances() bool[source]#

Return True if the stream have more instances to read.

next_instance() LabeledInstance | RegressionInstance[source]#

Return the next instance in the stream.

Raises:

ValueError – If the machine learning task is neither a regression nor a classification task.

Returns:

A labeled instances or a regression depending on the schema.

restart()[source]#

Restart the stream to read instances from the beginning.

to_stream(stream: Path) Any[source]#

Convert the dataset to a MOA stream.

Parameters:

stream – The path to the dataset.

Returns:

A MOA stream.