random_feature_selection¶
Module: missions.nodes.feature_selection.random_feature_selection
¶
Randomly select a number of features
Inheritance diagram for pySPACE.missions.nodes.feature_selection.random_feature_selection
:
RandomFeatureSelectionNode
¶
-
class
pySPACE.missions.nodes.feature_selection.random_feature_selection.
RandomFeatureSelectionNode
(num_retained_features=None, selected_features_path=None, **kwargs)[source]¶ Bases:
pySPACE.missions.nodes.base_node.BaseNode
Randomly select a given number of features
Parameters
num_retained_features: The number of features that should be retained by the node. This information must be specified if selected_features_path is not specified.
(optional, default: None)
selected_features_path: An absolute path from which the selected features are loaded. If not specified, these features are learned from the training data. In this case, num_retained_features must be specified.
(optional, default: None)
Exemplary Call
- node : RandomFeatureSelection parameters : num_retained_features : 1
Author: Jan Hendrik Metzen (jhm@informatik.uni-bremen.de)
Created: 2009/02/03
POSSIBLE NODE NAMES: - RandomFeatureSelectionNode
- RandomFeatureSelection
POSSIBLE INPUT TYPES: - FeatureVector
Class Components Summary
_execute
(feature_vector)Projects the feature vector onto the retained features input_types
store_state
(result_dir[, index])Stores this node in the given directory result_dir -
input_types
= ['FeatureVector']¶