weka_filter

Module: missions.operations.weka_filter

Use Weka’s Filter that transform one arff file into another.

A WEKA filter process consists of applying a filter to all arff-files contained in the input path. Filters may be using (un-)supervised training on the train datasets. For instance, feature selector filter is trained on a train set so that a subset of the features are selected. The results of the process consists of projecting both the train and the respective test set on the selected features. The results of all these processes are stored in a temporary directory and after the completion of all processes of the operation, the consolidate method of the WEKAFilterOperation is executed and the results are merged into a consistent representation of the operations result collection.

http://www.cs.waikato.ac.nz/ml/weka/

Inheritance diagram for pySPACE.missions.operations.weka_filter:

Inheritance diagram of pySPACE.missions.operations.weka_filter

Class Summary

WekaFilterOperation(processes, ...[, ...]) Operation for feature selection using Weka
WEKAFilterProcess(dataset_dir, ...[, ...]) Process for using Weka’s filters

Classes

WekaFilterOperation

class pySPACE.missions.operations.weka_filter.WekaFilterOperation(processes, operation_spec, result_directory, number_processes, create_process=None)[source]

Bases: pySPACE.missions.operations.base.Operation

Operation for feature selection using Weka

A WEKA Filter operation consists of a set of WEKA Filter processes. Each of these processes stores its results in a temporary directory. The operation collects the results of these processes using the consolidate method that produces a consistent representation of the result collections.

Class Components Summary

_createProcesses(processes, ...)
consolidate() Consolidates the results obtained by the single WEKA filter processes into a consistent summary of datasets that is stored on the file system.
create(operation_spec, result_directory[, ...]) A factory method that creates an WEKA operation based on the
__init__(processes, operation_spec, result_directory, number_processes, create_process=None)[source]
classmethod create(operation_spec, result_directory, debug=False, input_paths=[])[source]

A factory method that creates an WEKA operation based on the information given in the operation specification operation_spec

classmethod _createProcesses(processes, result_directory, operation_spec, parameter_settings, input_collections, command_template, hide_parameters)[source]
consolidate()[source]

Consolidates the results obtained by the single WEKA filter processes into a consistent summary of datasets that is stored on the file system.

WEKAFilterProcess

class pySPACE.missions.operations.weka_filter.WEKAFilterProcess(dataset_dir, command_template, parametrization, run_number, split_number, operation_result_dir, hide_parameters=[])[source]

Bases: pySPACE.missions.operations.base.Process

Process for using Weka’s filters

A WEKA filter process consists of applying a filter to all arff-files contained in the input_path. Filters may be using (un-)supervised training on the train datasets. For instance, the feature selector filter is trained on a train set so that a subset of the features are selected. The results of the process consists of projecting both the train and the respective test set on the selected features. The results of all these processes are stored in a temporary directory.

Class Components Summary

__call__() Executes this process on the respective modality
__init__(dataset_dir, command_template, parametrization, run_number, split_number, operation_result_dir, hide_parameters=[])[source]
__call__()[source]

Executes this process on the respective modality